{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1063,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":1063,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a2bc99577290","filters":{"topic":"Retinal Imaging and Analysis"}},"results":[{"id":"W2606534623","doi":"10.1364/boe.8.003627","title":"ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks","year":2017,"lang":"en","type":"article","venue":"Biomedical Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":607,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Bayerisches Staatsministerium für Bildung und Kultus, Wissenschaft und Kunst; Nvidia","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Segmentation; Convolutional neural network; Deep learning; Pattern recognition (psychology); Benchmark (surveying); Computer vision; Ophthalmology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02657593600976555,"gpt":0.3095475841092514,"spread":0.2829716480994859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003308068,0.0001440304,0.0003463438,0.0001100815,0.0001969511,0.00006261185,0.0001520376,0.0001428597,0.00005426619],"category_scores_gemma":[0.0002006445,0.0001211932,0.000119633,0.0001065613,0.001090942,0.00009148633,0.0001153227,0.0002015466,0.000001894332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002138393,"about_ca_system_score_gemma":0.00005822775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004599236,"about_ca_topic_score_gemma":3.45037e-7,"domain_scores_codex":[0.9985459,0.00003824536,0.000357913,0.000281798,0.0005325754,0.0002436073],"domain_scores_gemma":[0.9989074,0.00007139544,0.0001970963,0.0003541276,0.0001827273,0.0002872009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007474861,0.0006772781,0.1260992,0.0004494529,0.0006999297,0.0004879469,0.0002007477,0.0003197623,0.8567908,0.002149435,0.0009457591,0.01043218],"study_design_scores_gemma":[0.006557778,0.00123292,0.1226154,0.002168659,0.002274237,0.0008251934,0.000368297,0.8229055,0.03784644,0.0005831348,0.00178162,0.0008408166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.887598,0.0007349472,0.110044,0.0007526192,0.0001409488,0.0001545684,0.00001517392,0.00002302512,0.000536733],"genre_scores_gemma":[0.9502638,0.0001014431,0.04920316,0.00008023815,0.0002246774,0.000005185116,0.00004677262,0.00001331779,0.00006139919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8225858,"threshold_uncertainty_score":0.4942116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107871626","doi":"10.1109/tmi.2009.2033909","title":"Retinopathy Online Challenge: Automatic Detection of Microaneurysms in Digital Color Fundus Photographs","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":516,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Hong Kong Government; Hong Kong Polytechnic University; National Eye Institute; Ministerio de Ciencia e Innovación; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Waikato Medical Research Foundation; Research to Prevent Blindness","keywords":"Computer science; Artificial intelligence; Fundus (uterus); Context (archaeology); Diabetic retinopathy; Data set; Test set; Software; Set (abstract data type); Computer vision; Task (project management); Medicine; Ophthalmology; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.0105087549924263,"gpt":0.2763501090616983,"spread":0.265841354069272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002579782,0.0001932899,0.0004336509,0.0005958603,0.00006424224,0.00002514565,0.0001038682,0.00009421495,0.0002401369],"category_scores_gemma":[0.00009235063,0.000172463,0.0002436304,0.0007493182,0.0001721333,0.0001483604,0.000001015388,0.000675538,0.00002919844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006553142,"about_ca_system_score_gemma":0.00007507411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005302,"about_ca_topic_score_gemma":0.00002267342,"domain_scores_codex":[0.9981696,0.00004446248,0.0005526445,0.0003226182,0.0006092435,0.0003014107],"domain_scores_gemma":[0.999191,0.0001135623,0.0001016334,0.0002537841,0.00009288147,0.000247123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002022103,0.002507005,0.0007315404,0.0001360082,0.00006273788,0.0005034222,0.0003951513,0.0001185381,0.08657213,0.000001216832,0.0000303371,0.9087397],"study_design_scores_gemma":[0.01080509,0.002162067,0.02087737,0.004129255,0.001086168,0.002830302,0.003207195,0.6966403,0.256331,0.000420775,0.0004127197,0.001097758],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9049274,0.000215685,0.08970091,0.003895439,0.0002084413,0.0002204505,0.000009598494,0.0001506409,0.0006713859],"genre_scores_gemma":[0.9987012,0.0001670668,0.0002914878,0.0005811506,0.00005103772,0.000009182267,0.000008867869,0.00001800036,0.0001719712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9076419,"threshold_uncertainty_score":0.7032838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148284840","doi":"10.1016/j.compbiomed.2010.02.008","title":"Retinal vessel extraction by matched filter with first-order derivative of Gaussian","year":2010,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":503,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Thresholding; Artificial intelligence; Computer science; Retinal; Gaussian; Pattern recognition (psychology); Blood vessel; Filter (signal processing); Matched filter; Computer vision; Gaussian filter; Image (mathematics); Ophthalmology; Medicine; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.009490541482063146,"gpt":0.3109564377106056,"spread":0.3014658962285425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001861504,0.0001059369,0.0003428914,0.0001221223,0.00003417901,0.000001748402,0.00004614041,0.00008817116,0.00006740745],"category_scores_gemma":[0.00008804382,0.000065338,0.0000167349,0.0001866115,0.0005501984,0.00002679368,0.00001605733,0.0002875819,8.9564e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006900212,"about_ca_system_score_gemma":0.00002023018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000114693,"about_ca_topic_score_gemma":0.0000264175,"domain_scores_codex":[0.99938,0.00003051723,0.0001951241,0.0002026984,0.00005995901,0.0001317238],"domain_scores_gemma":[0.9995027,0.0001330226,0.00009368978,0.000133851,0.00006659026,0.00007020844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007528985,0.000207019,0.6893181,0.0002161773,0.0001779923,0.00006421596,0.001621903,0.000002081946,0.2850447,0.0006375096,0.01039115,0.01156629],"study_design_scores_gemma":[0.01292581,0.004993163,0.9192792,0.002733682,0.000600106,0.001332388,0.001737934,0.005799007,0.01655538,0.00194754,0.03151302,0.0005827728],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9628674,0.0003007663,0.02049291,0.01500689,0.0001751058,0.0001049349,0.000001736495,0.00001745652,0.001032849],"genre_scores_gemma":[0.9888577,0.0001733741,0.01006762,0.000594375,0.0001178662,0.000004464523,0.00004725558,0.000006229507,0.0001311272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2684893,"threshold_uncertainty_score":0.2664406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135914471","doi":"10.1109/42.963823","title":"Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching","year":2001,"lang":"en","type":"letter","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":402,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Artificial intelligence; Hausdorff distance; Computer vision; Template matching; Computer science; Pixel; Edge detection; Object detection; Pattern recognition (psychology); Fundus (uterus); Tracking (education); Image processing; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01699763984896572,"gpt":0.2925216307973115,"spread":0.2755239909483457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003550465,0.0004727052,0.000672233,0.0007017569,0.0005095863,0.0002039852,0.00009400633,0.0004079342,0.0001567079],"category_scores_gemma":[0.00002086448,0.0004300403,0.000235234,0.0003349226,0.0004189823,0.0002066992,0.000003485038,0.002923922,0.000009326405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001911547,"about_ca_system_score_gemma":0.0001146698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005596355,"about_ca_topic_score_gemma":0.00002032852,"domain_scores_codex":[0.9972059,0.0001544864,0.0005281122,0.0007271495,0.000877545,0.0005068504],"domain_scores_gemma":[0.9988708,0.0002376271,0.0001636949,0.0002923367,0.00008910501,0.0003464211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009182418,0.0009590033,0.001687294,0.005040039,0.002000292,0.02249554,0.0008700175,0.06379347,0.03723899,0.000001415035,0.00834052,0.8566552],"study_design_scores_gemma":[0.002238691,0.0001064963,0.0001686912,0.003624436,0.002538322,0.006346653,0.0001976934,0.9794234,0.00286746,0.00004241028,0.001727583,0.0007181853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0599467,0.0001852698,0.8120321,0.1269944,0.0003717902,0.0002168501,0.00001420848,0.0001650873,0.00007356927],"genre_scores_gemma":[0.8713682,0.0003020033,0.009947317,0.1157412,0.001819072,0.00003985001,0.0001052344,0.0002036454,0.0004734654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9156299,"threshold_uncertainty_score":0.9998152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089653673","doi":"10.1016/s2589-7500(20)30240-5","title":"A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability","year":2020,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":333,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Medical Research Council; National Institute for Health and Care Research; Seva Foundation; Fred Hollows Foundation; Queen Elizabeth Diamond Jubilee Trust; Moorfields Eye Charity; Wellcome Trust","keywords":"Metadata; Computer science; Usability; Population; Data science; MEDLINE; Information retrieval; World Wide Web; Medicine; Environmental health; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1755210722985354,"gpt":0.4731320854712138,"spread":0.2976110131726785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001720574,0.0003612932,0.003695373,0.00003701368,0.0001047864,0.0001855406,0.0006587027,0.00006047307,0.00009574474],"category_scores_gemma":[0.004374026,0.0002038313,0.0004716618,0.0007649365,0.0002764123,0.0002100505,0.0004927306,0.0002510215,0.00001781508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001918154,"about_ca_system_score_gemma":0.001289295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002350332,"about_ca_topic_score_gemma":0.00000432208,"domain_scores_codex":[0.9971505,0.0002436566,0.0009930739,0.0007750097,0.0003305711,0.0005071753],"domain_scores_gemma":[0.9971886,0.0003188753,0.0004369268,0.00110609,0.0001241093,0.0008254037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000046254,0.00005311977,0.006451315,0.2226394,0.0001044701,0.000009397404,0.00000574084,4.20686e-8,6.307189e-9,0.00007192443,0.2370361,0.5335822],"study_design_scores_gemma":[0.0001911465,0.0001730368,0.0001003455,0.02609447,0.0004590211,0.0003276729,0.00000716922,0.00001592703,3.721723e-8,0.0002288315,0.9722394,0.0001629701],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001997079,0.9537843,0.0000331311,0.03365479,0.00004476093,0.002141806,0.009116317,0.00004418834,0.001160767],"genre_scores_gemma":[0.0001056405,0.9874171,0.0003929814,0.009396528,0.0002822199,0.000121049,0.002206819,0.000021714,0.00005595684],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7352033,"threshold_uncertainty_score":0.8311998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899951262","doi":"10.1038/s41598-018-35044-9","title":"Performance of Deep Learning Architectures and Transfer Learning for Detecting Glaucomatous Optic Neuropathy in Fundus Photographs","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":330,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Eye Institute; Genentech; Heidelberg Engineering; Aerie Pharmaceuticals; Valeant Pharmaceuticals International; Carl Zeiss Meditec AG; Allergan; Research to Prevent Blindness; EyeSight Foundation of Alabama","keywords":"Fundus (uterus); Transfer of learning; Optic neuropathy; Computer science; Ophthalmology; Glaucoma; Deep learning; Optometry; Optic nerve; Artificial intelligence; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.009959948440479174,"gpt":0.2502040291457541,"spread":0.2402440807052749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001283174,0.000118133,0.0002792728,0.0004504338,0.0002901526,0.0000643177,0.00003952652,0.00003670444,0.00001428694],"category_scores_gemma":[0.0004429086,0.00009985169,0.0001068298,0.0006242737,0.0003431913,0.00004503168,0.00002094651,0.0002438755,8.371655e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001138306,"about_ca_system_score_gemma":0.0000319625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003824398,"about_ca_topic_score_gemma":0.00001988314,"domain_scores_codex":[0.9985216,0.00005320853,0.0004211252,0.0004722746,0.0002533745,0.0002784582],"domain_scores_gemma":[0.999342,0.00006901035,0.000124522,0.0002283667,0.0001536524,0.00008248569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009082731,0.00003292143,0.7199451,0.0002306877,0.00002111182,0.0001362833,0.002066676,0.0008055931,0.2401186,5.367893e-7,0.000002655457,0.03654901],"study_design_scores_gemma":[0.001298498,0.001589571,0.2251867,0.0008884245,0.0003726528,0.004146175,0.001981466,0.4092441,0.3536135,0.0001885127,0.001013538,0.00047687],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980528,0.0002145513,0.0007794719,0.0000189865,0.0003131926,0.0002039283,7.45146e-8,0.00004487683,0.0003720545],"genre_scores_gemma":[0.9988676,0.000006898208,0.0007186885,0.000008564792,0.00004548778,0.00001133483,0.000004542858,0.00001816922,0.0003187633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4947584,"threshold_uncertainty_score":0.4071834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2973454555","doi":"10.1038/s41467-019-12242-1","title":"Non-invasive in vivo hyperspectral imaging of the retina for potential biomarker use in Alzheimer’s disease","year":2019,"lang":"en","type":"article","venue":"Nature Communications","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":301,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Optina Diagnostics (Canada); Hôpital Maisonneuve-Rosemont; Polytechnique Montréal; Concordia University; Douglas Mental Health University Institute; McGill University; Montreal Heart Institute; Montreal Neurological Institute and Hospital","funders":"Australian Research Council; Fondation Brain Canada; State Government of Victoria; Québec Consortium for Drug Discovery; Pratt Foundation; Sylvia and Charles Viertel Charitable Foundation","keywords":"Hyperspectral imaging; Retina; Biomarker; Imaging biomarker; Disease; In vivo; Neuroscience; Medicine; Neuroimaging; Preclinical imaging; Alzheimer's disease; Biology; Computational biology; Pathology; Magnetic resonance imaging; Computer science; Artificial intelligence; Radiology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02333970174386473,"gpt":0.318103451416579,"spread":0.2947637496727142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001884988,0.00008619338,0.0001818685,0.0001644649,0.00005289847,0.00001473579,0.0004031104,0.00005908911,0.0000134208],"category_scores_gemma":[0.0002794216,0.00006391935,0.0001794676,0.0004443248,0.0001188906,0.00008400704,0.0001336759,0.0004461244,0.00000226818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004320146,"about_ca_system_score_gemma":0.0001141095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002047941,"about_ca_topic_score_gemma":0.0002144343,"domain_scores_codex":[0.9992962,0.00007170903,0.0002141557,0.0001505297,0.000128383,0.0001389574],"domain_scores_gemma":[0.9981955,0.0002185251,0.00009242717,0.00130717,0.0001404433,0.00004597815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000119299,0.0002171848,0.9691871,0.00002433527,0.00006067009,0.000003459874,0.0001803826,0.00002995304,0.02810082,0.0004617626,0.001454611,0.0001603538],"study_design_scores_gemma":[0.00120795,0.00001359038,0.9747537,0.0003931571,0.0003873067,0.000007332414,0.0004399839,0.01858433,0.002672548,0.0001534416,0.001271757,0.0001149223],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638745,0.005987861,0.00001906614,0.02815971,0.00008820267,0.0006990767,0.00004302962,0.00001448622,0.001114031],"genre_scores_gemma":[0.9969304,0.0002478187,0.002154349,0.0004068049,0.00001374036,0.00002572832,0.00003401826,0.00001271571,0.0001744115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03305588,"threshold_uncertainty_score":0.2606556,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115278098","doi":"10.1046/j.1464-5491.2003.01085.x","title":"Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening","year":2003,"lang":"en","type":"article","venue":"Diabetic Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":300,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Medicine; Diabetic retinopathy; Retinal; Retinopathy; Ophthalmology; Optometry; Artificial intelligence; Diabetes mellitus; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01298865380334886,"gpt":0.2685494787292477,"spread":0.2555608249258989,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002011445,0.0005038191,0.001472645,0.0007962954,0.0001141457,0.00004188472,0.0002080755,0.0002221357,0.0001216601],"category_scores_gemma":[0.01018195,0.0004243637,0.0003015149,0.001401513,0.0005509326,0.0001837855,0.00004339391,0.0005115551,0.000019338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001207591,"about_ca_system_score_gemma":0.000116064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004508079,"about_ca_topic_score_gemma":0.000002027973,"domain_scores_codex":[0.9957783,0.0001992311,0.001459109,0.0008092034,0.0008670976,0.0008870427],"domain_scores_gemma":[0.9969329,0.0009289604,0.000495478,0.0007400017,0.0005841749,0.0003184357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001061795,0.001084537,0.5211665,0.003296542,0.0004273696,0.0003315634,0.001900724,0.00008868267,0.4249384,0.00015688,0.003195197,0.04235179],"study_design_scores_gemma":[0.04398457,0.01342022,0.3291564,0.02037,0.0054345,0.0005122459,0.004935327,0.09232853,0.4775472,0.003233747,0.005723414,0.003353842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877444,0.0009687584,0.006728392,0.000821428,0.0008949923,0.0009996215,0.00002697507,0.0003111769,0.001504289],"genre_scores_gemma":[0.9960312,0.00005228904,0.002274564,0.0002277169,0.0005789482,0.0001492893,0.0001178276,0.00009268695,0.0004755092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1920101,"threshold_uncertainty_score":0.9998208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3131059059","doi":"10.1002/hbm.25364","title":"Cortical thickness across the lifespan: Data from 17,075 healthy individuals aged 3–90 years","year":2021,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":294,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of British Columbia; Université de Montréal; Vancouver Coastal Health","funders":"National Center for Research Resources; National Cancer Institute; National Institute on Drug Abuse; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Seventh Framework Programme; School of Medicine, Indiana University; National Institutes of Health; National Center for Advancing Translational Sciences; Medical Research Council; Medical Research Council Canada; Rheinische Friedrich-Wilhelms-Universität Bonn; University of Cape Town; Instituto de Salud Carlos III; Universitat de Barcelona; Universidade de São Paulo; University of Galway; Cardiff University; King's College London; University of Edinburgh; National Institute on Aging; National Institute for Health and Care Research; Northwestern University; York University; Icahn School of Medicine at Mount Sinai; Eunice Kennedy Shriver National Institute of Child Health and Human Development; ZonMw; National Alliance for Research on Schizophrenia and Depression; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; Universiteit Leiden; National University of Ireland; Instituto de Investigación Marqués de Valdecilla; Norges Forskningsråd; University of Oxford; South London and Maudsley NHS Foundation Trust; Johns Hopkins University; Manitoba Health Research Council; FP7 Ideas: European Research Council; Psychiatry Research Trust; National Institute of Mental Health; Universität Basel; Vetenskapsrådet","keywords":"Psychology; Neuroscience; Healthy aging; Developmental psychology; Audiology; Gerontology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1011094664905792,"gpt":0.3820990350323029,"spread":0.2809895685417237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001524969,0.0001689955,0.0004314923,0.00005341634,0.0006198899,0.0002158608,0.0004742481,0.00009416066,0.0005517045],"category_scores_gemma":[0.001226498,0.000134485,0.0001107423,0.0004313846,0.0002208125,0.0001087235,0.0005287646,0.0007488551,0.0001172937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003571309,"about_ca_system_score_gemma":0.0001502178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002367155,"about_ca_topic_score_gemma":0.0001090263,"domain_scores_codex":[0.9976317,0.0004043281,0.0004272702,0.0005901773,0.0004976549,0.0004488288],"domain_scores_gemma":[0.9974652,0.0007083198,0.0001289051,0.00143015,0.00008802272,0.0001793922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001105126,0.0006506008,0.402537,0.0003528896,0.001842186,0.002244226,0.02661624,0.00002218866,0.1481307,0.0009998195,0.4068806,0.009613042],"study_design_scores_gemma":[0.00102204,0.00003226974,0.9061145,0.0003433406,0.0001836772,0.00007347627,0.005101142,0.0005999479,0.00004155024,0.000403481,0.08587626,0.0002082885],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9535614,0.0009046633,0.001303604,0.04258291,0.0001338792,0.000164147,0.000130235,0.0001143015,0.00110486],"genre_scores_gemma":[0.9745895,0.00003540873,0.0009290872,0.01867402,0.0008608279,0.000008862221,0.00129263,0.00003445541,0.003575211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5035775,"threshold_uncertainty_score":0.6040777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767040741","doi":"10.1371/journal.pone.0187336","title":"Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Yonsei University College of Medicine; Yonsei University","keywords":"Artificial intelligence; Deep learning; Computer science; Convolutional neural network; Transfer of learning; Retinal Disorder; Categorical variable; Pattern recognition (psychology); Classifier (UML); Machine learning; Retinal; Fundus (uterus); Kappa; Random forest; Computer-aided diagnosis; Artificial neural network; Cluster analysis; Medicine; Mathematics; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.1792205964387175,"gpt":0.3346165523014706,"spread":0.1553959558627531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005938537,0.0002582078,0.0006271511,0.0001209446,0.0007882642,0.0002496365,0.0003678047,0.00003383923,0.0000661083],"category_scores_gemma":[0.001592973,0.0002262221,0.00009548156,0.0001959163,0.00008585979,0.0001475222,0.000348665,0.0008055923,0.0002038001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006271353,"about_ca_system_score_gemma":0.00003040454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000509514,"about_ca_topic_score_gemma":0.0001027912,"domain_scores_codex":[0.9977543,0.000174706,0.00037527,0.0006074992,0.0005156274,0.0005725495],"domain_scores_gemma":[0.9981042,0.00010991,0.000205253,0.0009617537,0.0002072876,0.0004115803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007369155,0.006567807,0.9412415,0.0001223989,0.000589255,0.0008459076,0.00039191,0.0001743548,0.04679888,0.000003209598,0.0002536745,0.002274211],"study_design_scores_gemma":[0.006041786,0.008057528,0.8523329,0.001049689,0.00439697,0.00006860337,0.001424657,0.1239864,0.001567923,0.00001444913,0.0002014607,0.0008576291],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935141,0.000158253,0.002709575,0.002315314,0.00005318856,0.0005037417,0.000002000906,0.0001833681,0.0005604293],"genre_scores_gemma":[0.9716561,0.00002881924,0.02457057,0.000362677,0.0007559194,0.00005123344,0.00002806342,0.00005683989,0.002489757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.123812,"threshold_uncertainty_score":0.9225067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2177654152","doi":"10.1155/2015/180972","title":"Optic Disc and Optic Cup Segmentation Methodologies for Glaucoma Image Detection: A Survey","year":2015,"lang":"en","type":"review","venue":"Journal of Ophthalmology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"University of Waterloo; Ryerson University","keywords":"Optic disc; Optic cup (embryology); Glaucoma; Optical coherence tomography; Medicine; Optic nerve; Fundus (uterus); Segmentation; Artificial intelligence; Optometry; Optic disk; Computer vision; Ophthalmology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2397125583233228,"gpt":0.4918979483701521,"spread":0.2521853900468293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004975574,0.0002998849,0.002572702,0.0004721225,0.00005962766,0.00004882934,0.0001458862,0.0002331161,0.00003738037],"category_scores_gemma":[0.003116741,0.0001975796,0.0006000369,0.0002771782,0.0001581339,0.0001202651,0.00005215395,0.0004785689,0.000005545104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001481254,"about_ca_system_score_gemma":0.0002882275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002407417,"about_ca_topic_score_gemma":4.161078e-7,"domain_scores_codex":[0.9968773,0.001445465,0.0009769683,0.0002491715,0.0002201211,0.0002309743],"domain_scores_gemma":[0.9958277,0.001952633,0.001226017,0.0002010748,0.0006185201,0.0001739981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"case_report","study_design_scores_codex":[0.001049262,0.000201661,0.001871785,0.01867674,0.003291059,0.006709952,0.0001215229,0.000001483159,0.0001381126,0.000006142797,0.0007326686,0.9671996],"study_design_scores_gemma":[0.002800619,0.006114312,0.004223087,0.007097826,0.01985261,0.9011257,0.0003667203,0.000162091,0.00004709201,0.0006606032,0.05687514,0.0006741658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.009360907,0.9858668,0.003695228,0.0001055697,0.0004307342,0.0003912991,0.00002267345,0.000007979906,0.000118747],"genre_scores_gemma":[0.0006447541,0.9062455,0.09186681,0.000008855436,0.0004433284,0.00002999399,0.00006837973,0.00005172354,0.000640599],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9665254,"threshold_uncertainty_score":0.8057063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766593955","doi":"10.1097/ijg.0000000000000765","title":"Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects","year":2017,"lang":"en","type":"article","venue":"Journal of Glaucoma","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":224,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Columbia College","funders":"National Eye Institute","keywords":"Optical coherence tomography; Glaucoma; Medicine; Deep learning; Artificial intelligence; Optometry; Ophthalmology; Tomography; Radiology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03130174657549592,"gpt":0.305221897687085,"spread":0.2739201511115891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004593022,0.0002464947,0.0006694269,0.0003368301,0.0004474564,0.0003640596,0.0004408945,0.00008584371,0.0001205981],"category_scores_gemma":[0.002229831,0.0001872893,0.0005109555,0.0001347863,0.0002213866,0.0003273912,0.00007096043,0.0009955002,0.00003396956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007562933,"about_ca_system_score_gemma":0.00008688915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005237528,"about_ca_topic_score_gemma":0.00001950169,"domain_scores_codex":[0.9980127,0.00007405402,0.0006014778,0.0002452724,0.0006760596,0.0003904837],"domain_scores_gemma":[0.9974802,0.0004521004,0.0008150651,0.0004811343,0.0004183693,0.000353138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007246567,0.0003268411,0.9476114,0.00004048333,0.0003056376,0.002163489,0.00008714444,0.000001571147,0.01580317,0.0001286551,0.003431346,0.02937561],"study_design_scores_gemma":[0.001648672,0.004073262,0.9223306,0.0009754373,0.0005086755,0.001355979,0.0002947903,0.0007158237,0.06405456,0.0005530641,0.003207432,0.0002816737],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770094,0.0003489507,0.001037488,0.007213838,0.000305974,0.00007479134,7.9349e-7,0.00003377629,0.01397496],"genre_scores_gemma":[0.996905,0.0001077312,0.001120549,0.0005477043,0.0005010839,0.000001318042,0.000001997865,0.00002742902,0.0007871687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04825139,"threshold_uncertainty_score":0.7637437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801475611","doi":"10.1016/j.compmedimag.2018.04.005","title":"Retinal blood vessel segmentation using fully convolutional network with transfer learning","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":224,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Computer science; Segmentation; Artificial intelligence; Robustness (evolution); Transfer of learning; Retinal; Deep learning; Pattern recognition (psychology); Computer vision; Image segmentation; Convolutional neural network; Medical imaging; Computer-aided diagnosis; Medicine; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.01190647296337326,"gpt":0.2724129232104857,"spread":0.2605064502471124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005219983,0.0001933921,0.0003461177,0.0001361454,0.0003734736,0.0000707171,0.00007541775,0.00006893422,0.00006443761],"category_scores_gemma":[0.00005879415,0.0001526591,0.00008689319,0.0004536967,0.0008446273,0.00009270403,0.0000373644,0.0004742187,0.000002475234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001301797,"about_ca_system_score_gemma":0.0001476393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003759977,"about_ca_topic_score_gemma":0.000001537163,"domain_scores_codex":[0.998277,0.0001182227,0.0002880758,0.0003689037,0.0005925876,0.0003552246],"domain_scores_gemma":[0.9991224,0.00009462157,0.00005687647,0.0001295208,0.0002428002,0.0003537511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001851036,0.000682405,0.8872651,0.0005687225,0.001620866,0.001771755,0.001481464,0.0002312014,0.02967615,0.002592109,0.0022227,0.07003646],"study_design_scores_gemma":[0.009586185,0.0008618637,0.03391694,0.002511767,0.00191725,0.005458248,0.0003048065,0.938258,0.0007942071,0.00042244,0.005329185,0.0006391295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.63596,0.0005001355,0.3610635,0.002045906,0.0001171354,0.00008617534,9.775888e-7,0.0001034806,0.0001226629],"genre_scores_gemma":[0.9752333,0.0002313072,0.02150379,0.001815274,0.001080922,0.000003867993,0.00004965604,0.0000266468,0.00005523542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9380268,"threshold_uncertainty_score":0.6225256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041245457","doi":"10.1111/j.1755-3768.2009.01587.x","title":"Use of the retinal vessel analyzer in ocular blood flow research","year":2009,"lang":"en","type":"article","venue":"Acta Ophthalmologica","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":223,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Ophthalmology; Spectrum analyzer; Blood flow; Retinal; Medicine; Optometry; Optics; Cardiology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1032443457578689,"gpt":0.3718413651889435,"spread":0.2685970194310746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008667873,0.0001180117,0.0003345922,0.0002087353,0.00008511112,0.00002581096,0.0002552449,0.0000992025,0.0001924473],"category_scores_gemma":[0.001197416,0.00006862714,0.0001859916,0.001155729,0.0002015839,0.00006978322,0.00007286147,0.000532788,0.000009599335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002590677,"about_ca_system_score_gemma":0.0000560308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374425,"about_ca_topic_score_gemma":5.552094e-7,"domain_scores_codex":[0.9982322,0.0003360894,0.0002945046,0.0002968701,0.0005045318,0.000335844],"domain_scores_gemma":[0.9988307,0.0001932094,0.0000776796,0.0006204442,0.000201002,0.00007690223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003613169,0.001493501,0.8051737,0.00005309593,0.000148936,0.002425788,0.0002547249,0.00008970492,0.184526,0.0001396639,0.003213622,0.002119906],"study_design_scores_gemma":[0.0004827986,0.000658967,0.984583,0.0002199058,0.0001690196,0.0009606939,0.0001002787,0.000982236,0.009952585,0.0006958039,0.001078713,0.0001160525],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877313,0.0001999306,0.000002072249,0.007172775,0.00001823748,0.0001525599,0.000002294688,0.00001325857,0.004707554],"genre_scores_gemma":[0.9967694,0.00006452209,0.001383527,0.0001856964,0.00004591991,0.00000427936,0.000005910508,0.000007049211,0.001533723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1794093,"threshold_uncertainty_score":0.2798533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082677554","doi":"10.1364/oe.17.023719","title":"Intra-retinal layer segmentation in optical coherence tomography images","year":2009,"lang":"en","type":"article","venue":"Optics Express","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":219,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Optical coherence tomography; Retinal; Segmentation; Speckle noise; Artificial intelligence; Computer science; Speckle pattern; Computer vision; Optics; Image segmentation; Image resolution; Contrast (vision); Physics; Ophthalmology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01431179794228789,"gpt":0.2979187225262049,"spread":0.2836069245839171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001442037,0.000117664,0.0002110987,0.000155833,0.00003118359,0.00005071694,0.00007964868,0.00004913191,0.00005628476],"category_scores_gemma":[0.00005446988,0.0001029762,0.00008137852,0.0002873355,0.00006804233,0.0000916998,0.00001390365,0.0001961891,0.00001901925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002246635,"about_ca_system_score_gemma":0.00001871177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001421516,"about_ca_topic_score_gemma":5.780782e-7,"domain_scores_codex":[0.9990684,0.0000272686,0.0002199409,0.0002190951,0.000245377,0.0002199165],"domain_scores_gemma":[0.9995394,0.00003923661,0.00004418867,0.0001918306,0.00007981608,0.0001055444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002543046,0.00065061,0.07112104,0.00007184062,0.00005804526,0.0003724789,0.0006349199,0.0003156548,0.8939044,0.0008608674,0.001632356,0.03012348],"study_design_scores_gemma":[0.004055223,0.001140486,0.2528473,0.0009234259,0.0005314032,0.0001945847,0.001554773,0.01148568,0.7239376,0.00179113,0.0007559173,0.0007823999],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9707611,0.0001819916,0.006232865,0.002356483,0.00004647524,0.0001677369,0.000003523446,0.00005832475,0.0201915],"genre_scores_gemma":[0.9648706,0.00005245276,0.03416453,0.000361587,0.00007836457,0.00000742535,0.00001922031,0.000007939726,0.00043787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1817263,"threshold_uncertainty_score":0.4199247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810924486","doi":"10.1016/j.media.2018.07.001","title":"Synthesizing retinal and neuronal images with generative adversarial nets","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":214,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Chinese Government Scholarship; China Scholarship Council; Government of Jiangxi Province","keywords":"Computer science; Artificial intelligence; Annotation; Set (abstract data type); Generative grammar; Image (mathematics); Pattern recognition (psychology); Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.007527008097328543,"gpt":0.2789910835645772,"spread":0.2714640754672487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005679916,0.0002451527,0.0006882161,0.0003998464,0.0002233838,0.00009788508,0.0001343435,0.00008900345,0.002047432],"category_scores_gemma":[0.0008481909,0.0001664785,0.0002582573,0.001208471,0.00114935,0.0001543218,0.00008352619,0.0003441422,0.0000532244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002898989,"about_ca_system_score_gemma":0.0001284481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002497398,"about_ca_topic_score_gemma":0.00005716708,"domain_scores_codex":[0.9975199,0.000164107,0.0003438257,0.0005911402,0.001004293,0.0003767596],"domain_scores_gemma":[0.9985039,0.000170848,0.0001188968,0.0003448608,0.0003280109,0.0005334881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003985856,0.001411516,0.6746113,0.0002909878,0.03037152,0.009852442,0.002875102,0.00003326619,0.09119135,0.0002408398,0.03184532,0.1532905],"study_design_scores_gemma":[0.01100939,0.004857241,0.4430304,0.00107756,0.09240039,0.0022178,0.002792263,0.327174,0.0916795,0.0002736388,0.02078563,0.002702103],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8664334,0.0003571291,0.09935425,0.02295301,0.00006807947,0.0001631577,0.00001308118,0.0001551728,0.01050271],"genre_scores_gemma":[0.9806896,0.00009931054,0.01485429,0.002246696,0.0008310125,0.000007784129,0.00004125201,0.00002557037,0.001204486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3271408,"threshold_uncertainty_score":0.9988648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008531067","doi":"10.1109/isspit47144.2019.9001846","title":"Diabetic Retinopathy Classification Using a Modified Xception Architecture","year":2019,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Deep learning; Feature (linguistics); Feature extraction; Transfer of learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0296429327570147,"gpt":0.2917105030615436,"spread":0.2620675703045289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001203826,0.00008037608,0.0001631792,0.0001168543,0.00002967202,0.00001919357,0.00003578125,0.00004422461,0.0003083812],"category_scores_gemma":[0.00003162233,0.00006023082,0.00008714903,0.000198966,0.00002375938,0.00003374683,0.00001045383,0.0001268236,0.0001724953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003094913,"about_ca_system_score_gemma":0.00002312307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003379128,"about_ca_topic_score_gemma":5.721091e-7,"domain_scores_codex":[0.9993259,0.000032652,0.0001413573,0.0001988172,0.0001699235,0.0001313635],"domain_scores_gemma":[0.9995581,0.00001746938,0.00005162967,0.0002513631,0.00006022963,0.00006120917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006350958,0.000068464,0.08197828,0.00008524602,0.00003729484,0.000004167674,0.0001893101,0.0005089741,0.9001984,0.0003031216,0.0001186636,0.01644458],"study_design_scores_gemma":[0.001934305,0.0002972225,0.2081988,0.0003699555,0.0006244489,0.0001754809,0.0009175129,0.7699674,0.01502596,0.001044473,0.001020357,0.0004240069],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632548,0.00003032563,0.01714469,0.001289436,0.00005178658,0.0001441777,5.010351e-7,0.00007226845,0.01801199],"genre_scores_gemma":[0.9902399,0.000005288215,0.004598767,0.0003008546,0.00007826525,0.000002580856,0.00001971854,0.00001186047,0.00474272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8851724,"threshold_uncertainty_score":0.3376558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099733385","doi":"10.1016/j.artmed.2019.101758","title":"Ophthalmic diagnosis using deep learning with fundus images – A critical review","year":2019,"lang":"en","type":"review","venue":"Artificial Intelligence in Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":200,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Fundus (uterus); Artificial intelligence; Computer science; Diabetic retinopathy; Glaucoma; Macular degeneration; Segmentation; Optic disc; Ophthalmology; Optic cup (embryology); Optometry; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2746009303429246,"gpt":0.4895945420956003,"spread":0.2149936117526757,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001410155,0.0006889038,0.004377532,0.0007331427,0.0001073616,0.00003989273,0.0003288285,0.0002575629,0.001290958],"category_scores_gemma":[0.004411478,0.0004461874,0.0004768578,0.002047101,0.0006703381,0.0001198403,0.00008209608,0.001793874,0.0003894342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002468957,"about_ca_system_score_gemma":0.0002850316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004292771,"about_ca_topic_score_gemma":0.00001340939,"domain_scores_codex":[0.9953846,0.0004739922,0.001752191,0.0009429237,0.0007707837,0.0006754592],"domain_scores_gemma":[0.9967034,0.001581477,0.0004378455,0.000676555,0.0003155392,0.0002851287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002080258,0.0001217375,0.0002812425,0.05930278,0.0001417023,0.001008869,0.00007127786,0.00001973845,0.000003405782,0.00008704004,0.0001091386,0.9388323],"study_design_scores_gemma":[0.00007745239,0.0009438246,0.000006208188,0.7054904,0.01263223,0.002167712,0.0006112467,0.00215953,0.0000207414,0.0001783175,0.2749319,0.0007804247],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002257384,0.993216,0.002929983,0.001607753,0.0002326684,0.0009869065,0.000002914576,0.00006122597,0.0009399281],"genre_scores_gemma":[0.0005876496,0.9966754,0.00113793,0.0004450138,0.0006025012,0.0001335072,0.00007310457,0.0001060175,0.0002388501],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9380518,"threshold_uncertainty_score":0.999799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091921880","doi":"10.1002/alz.12179","title":"Retinal imaging in Alzheimer's and neurodegenerative diseases","year":2020,"lang":"en","type":"review","venue":"Alzheimer s & Dementia","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; Pratt Foundation; National Institutes of Health; National Foundation for Medical Research and Innovation; Alzheimer's Association","keywords":"Context (archaeology); Neuroscience; Dementia; Modalities; Disease; Retinal; Alzheimer's disease; Medicine; Psychology; Pathology; Ophthalmology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04426798778639232,"gpt":0.3371026048462719,"spread":0.2928346170598796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001533084,0.0005925267,0.001886383,0.0003285811,0.00009551381,0.0001073045,0.000185091,0.00008805173,0.0001212027],"category_scores_gemma":[0.00006410384,0.0004908069,0.0005097046,0.0005373799,0.0001610329,0.0001212536,0.0001979559,0.0005250233,0.00008733973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009279748,"about_ca_system_score_gemma":0.0002193219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007479521,"about_ca_topic_score_gemma":0.00000435635,"domain_scores_codex":[0.9973229,0.0002686131,0.0007547467,0.0009058776,0.000333895,0.0004140378],"domain_scores_gemma":[0.9988012,0.00009378646,0.0003065654,0.0003971371,0.00006481481,0.0003365187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001424475,0.00006352275,0.00133862,0.0003600547,0.01451488,0.0006729969,0.00004822083,1.877159e-7,0.000002050932,0.00002639925,0.001889646,0.9810691],"study_design_scores_gemma":[0.0002873523,0.00004715885,0.0001986915,0.00248522,0.2714059,0.0001664009,0.00002231174,0.0001495449,0.000009690308,0.0000127919,0.7248377,0.0003773201],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006334139,0.9979164,0.00002154931,0.0007615957,0.0001162192,0.0005198302,0.00003741848,0.00007259283,0.0005480703],"genre_scores_gemma":[0.002930498,0.9951669,0.0006330323,0.0004550103,0.0003328088,0.0000777882,0.0003017416,0.0000950055,0.000007195314],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9806919,"threshold_uncertainty_score":0.9997544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3212362219","doi":"10.1161/circulationaha.121.057709","title":"Deep Learning of the Retina Enables Phenome- and Genome-Wide Analyses of the Microvasculature","year":2021,"lang":"en","type":"article","venue":"Circulation","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Paul's Hospital","funders":"National Center for Advancing Translational Sciences; National Eye Institute; National Heart, Lung, and Blood Institute; Medical Research Council; British Heart Foundation","keywords":"Medicine; Retinal; Phenome; Angiogenesis; Retina; Bioinformatics; Pathology; Internal medicine; Ophthalmology; Biology; Neuroscience; Genetics; Genome; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.0176489263653393,"gpt":0.2685446548384245,"spread":0.2508957284730853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001506913,0.0000601467,0.0001826673,0.00003616372,0.00008245446,0.000009489528,0.00004717268,0.00003634408,0.00002512671],"category_scores_gemma":[0.0003801742,0.00003491973,0.0001827147,0.0004294552,0.00008305503,0.00002588759,0.00003891355,0.0001248429,4.280417e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001638335,"about_ca_system_score_gemma":0.0000316551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003216084,"about_ca_topic_score_gemma":0.000003303074,"domain_scores_codex":[0.9993479,0.000109434,0.0001757619,0.000126023,0.0001708068,0.00007003589],"domain_scores_gemma":[0.9993437,0.00005500871,0.000151925,0.0002548522,0.0001757512,0.00001877752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003700678,0.00001250578,0.6400342,0.00008562741,0.0001020664,8.227522e-7,0.0003220965,0.003713472,0.3549187,0.00002176395,0.000003342694,0.0007816511],"study_design_scores_gemma":[0.0001763156,0.00000404511,0.9624779,0.0001075202,0.0004859795,0.00001570778,0.0004063959,0.00399185,0.03192887,0.0001099341,0.0002590247,0.00003651698],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934438,0.004130063,0.0009465571,0.0006918964,0.00002156024,0.00005879162,4.424219e-7,0.000005968858,0.0007009308],"genre_scores_gemma":[0.9993602,0.00009251455,0.0001792113,0.00007131746,0.00003325624,7.439721e-7,0.00001071832,0.000006699001,0.0002453506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3229899,"threshold_uncertainty_score":0.1423985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3128375503","doi":"10.1002/hbm.25320","title":"Subcortical volumes across the lifespan: Data from 18,605 healthy individuals aged 3–90 years","year":2021,"lang":"en","type":"article","venue":"Human Brain Mapping","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":163,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto; Centre for Addiction and Mental Health; Vancouver Coastal Health; Université de Montréal","funders":"National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Institute on Drug Abuse; Helse Sør-Øst RHF; National Health and Medical Research Council; National Institutes of Health; Epilepsy Society; Instituto de Salud Carlos III; Siemens Healthineers; National Center for Advancing Translational Sciences; Medical Research Council; Hersenstichting; Medical Research Council Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Alliance for Research on Schizophrenia and Depression; Epilepsy Foundation of Victoria; Karolinska Institutet; The Research Council; Vetenskapsrådet; University of Queensland; King's College London; Instituto de Investigación Marqués de Valdecilla; Norges Forskningsråd; FP7 Ideas: European Research Council; Parents Against Childhood Epilepsy; Psychiatry Research Trust; National Institute on Aging; National Institute for Health and Care Research; National Institute of Child Health and Human Development; South London and Maudsley NHS Foundation Trust; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Icahn School of Medicine at Mount Sinai; Indiana State Department of Health; National Institute of Mental Health; American Epilepsy Society; Universiteit Utrecht; Stockholms Läns Landsting; National Cancer Institute; Knut och Alice Wallenbergs Stiftelse; Deutsches Zentrum für Herz-Kreislaufforschung; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Psychology; Neuroscience; Healthy aging; Gerontology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1161818807225056,"gpt":0.3878589504846428,"spread":0.2716770697621372,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001157418,0.0001665416,0.0004219473,0.00006013625,0.0005273264,0.0002299369,0.0004577121,0.00007901018,0.0009380232],"category_scores_gemma":[0.001292914,0.0001361497,0.0001386815,0.0003812438,0.0002138085,0.0001146812,0.0005061134,0.0005138606,0.0001623288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000439567,"about_ca_system_score_gemma":0.000151695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003606998,"about_ca_topic_score_gemma":0.0001399565,"domain_scores_codex":[0.997723,0.0003081786,0.0004317017,0.0006017527,0.000470139,0.0004651724],"domain_scores_gemma":[0.9977033,0.0004753665,0.0001226834,0.001408499,0.00006770519,0.0002224312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004715321,0.0003018113,0.6008753,0.0001700436,0.0009348893,0.001111507,0.008982599,0.000008666925,0.04383624,0.0002385167,0.3348352,0.008658053],"study_design_scores_gemma":[0.0009334129,0.00003513183,0.9036237,0.0002007411,0.0001677788,0.00004867855,0.004315609,0.0009183813,0.00004492497,0.0004173137,0.08909731,0.00019704],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9680564,0.001176139,0.0008578262,0.02889265,0.0001017128,0.0001335136,0.00009706891,0.000105671,0.0005789496],"genre_scores_gemma":[0.9804043,0.00004985695,0.001030256,0.01290147,0.0008213006,0.000007596595,0.001085781,0.0000325423,0.003666948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3027484,"threshold_uncertainty_score":0.9999753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2917393555","doi":"10.1016/j.media.2019.02.011","title":"Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":160,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Fondation pour la Recherche sur Alzheimer; Genome British Columbia; Simon Fraser University; Michael Smith Health Research BC; Canadian Institutes of Health Research; Alzheimer Society; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Optical coherence tomography; Artificial intelligence; Computer science; Convolutional neural network; Segmentation; Retinal; Pattern recognition (psychology); Computer vision; Cut; Retina; Pixel; Image segmentation; Ophthalmology; Medicine; Optics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.007756989084423179,"gpt":0.2748887174620818,"spread":0.2671317283776586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009642023,0.0002160341,0.0006000248,0.0006131512,0.0001255082,0.00008451418,0.0000891763,0.0001296647,0.0008414329],"category_scores_gemma":[0.0005528582,0.000191783,0.0003318312,0.002192515,0.0003004459,0.0001864798,0.00005094709,0.0005624504,0.00001854552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009180622,"about_ca_system_score_gemma":0.00006782568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003047552,"about_ca_topic_score_gemma":0.00005928088,"domain_scores_codex":[0.9973518,0.0003000829,0.0005156581,0.000529384,0.0008828038,0.000420236],"domain_scores_gemma":[0.9988341,0.0002947666,0.0001415257,0.0001989844,0.0002060814,0.0003245745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003066237,0.0001547691,0.9010406,0.00009854491,0.0006218084,0.0002557713,0.00007793517,0.02009266,0.06319029,0.000002973347,0.00001692424,0.01414106],"study_design_scores_gemma":[0.001162061,0.0001225484,0.1859899,0.00009548943,0.001639282,0.00004377592,0.0002051358,0.8090285,0.001537837,0.00000815834,0.0000111934,0.000156055],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8229982,0.0002966448,0.1757198,0.0006279142,0.00003784549,0.0001512361,0.000001109593,0.00004976581,0.0001174964],"genre_scores_gemma":[0.9840202,0.00002770639,0.01529902,0.0003475684,0.0001231237,0.00001195578,0.00007435455,0.00001670442,0.00007940182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7889358,"threshold_uncertainty_score":0.92131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049729972","doi":"10.1117/12.430999","title":"<title>Procedure to detect anatomical structures in optical fundus images</title>","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hôpital Maisonneuve-Rosemont; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Fundus (uterus); Histogram; Pixel; Pattern recognition (psychology); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.009786493955354296,"gpt":0.2516889520064435,"spread":0.2419024580510892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002686186,0.000214285,0.0003624668,0.0001582438,0.00003308614,0.00005790278,0.0003574375,0.0001542392,0.0001429071],"category_scores_gemma":[0.0005721044,0.0001710368,0.0004003255,0.0004142633,0.0001250673,0.0001225681,0.00008623945,0.0003160041,0.00002636349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135214,"about_ca_system_score_gemma":0.00003743119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003344636,"about_ca_topic_score_gemma":1.318791e-7,"domain_scores_codex":[0.9984772,1.801722e-8,0.0004019543,0.0003090331,0.0004971715,0.00031458],"domain_scores_gemma":[0.9990649,0.00005456468,0.0001003861,0.00005578228,0.0005658166,0.0001585243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002394164,0.0001426749,0.001584722,0.0004817291,0.0004952357,0.000003530491,0.0001097342,0.00007279783,0.6459453,0.2950471,0.05085787,0.005019882],"study_design_scores_gemma":[0.007967032,0.002137586,0.03778815,0.003175549,0.002171186,0.0009559358,0.001890673,0.1219052,0.3677941,0.01573869,0.435402,0.003073898],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9619916,0.0001631507,0.00006594904,0.003255052,0.0001201739,0.0002368866,0.0000121174,0.00006283666,0.03409221],"genre_scores_gemma":[0.9307732,0.0001496664,0.06583238,0.0003017411,0.0006159234,0.00004538511,0.000008730478,0.00006607114,0.002206917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3845442,"threshold_uncertainty_score":0.6974677,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3032728079","doi":"10.3390/electronics9060914","title":"Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction","year":2020,"lang":"en","type":"article","venue":"Electronics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Pooling; Dropout (neural networks); Pattern recognition (psychology); Deep learning; Cohen's kappa; Diabetic retinopathy; Convolutional neural network; Benchmark (surveying); Feature extraction","retraction":null,"screen_n_in":null,"score":{"opus":0.01288972425832501,"gpt":0.2640185328731716,"spread":0.2511288086148466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000141666,0.0001456746,0.0002877498,0.0000394829,0.00009080129,0.00002466826,0.00007739692,0.0000835777,0.00002803884],"category_scores_gemma":[0.0002510239,0.0001311958,0.0001641588,0.0001944192,0.00004000357,0.00004754784,0.00001805919,0.0003356726,0.00001392245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008454252,"about_ca_system_score_gemma":0.0001301268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004591155,"about_ca_topic_score_gemma":0.000008342595,"domain_scores_codex":[0.9989063,0.0000376625,0.0001890817,0.0003112355,0.0001839317,0.0003718373],"domain_scores_gemma":[0.9994463,0.00004260893,0.00006708454,0.0001662033,0.0001107082,0.0001670953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006917745,0.00218378,0.207444,0.002992166,0.003255934,0.0002066875,0.007576154,0.000994555,0.4922144,0.002079104,0.07827975,0.1958557],"study_design_scores_gemma":[0.01229632,0.005248463,0.06518579,0.0001717102,0.00310614,0.0001939573,0.00059047,0.6303486,0.1527843,0.0009050916,0.1281937,0.0009754708],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9210931,0.01442109,0.03631666,0.02535662,0.0002297895,0.001125073,0.0000731317,0.0005751616,0.0008093865],"genre_scores_gemma":[0.9930479,0.0004767465,0.003549756,0.001602857,0.0003266729,0.0000349252,0.0001863006,0.00003093271,0.0007438862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6293541,"threshold_uncertainty_score":0.5350009,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165733437","doi":"10.1109/tmi.2010.2087390","title":"Segmentation of Intra-Retinal Layers From Optical Coherence Tomography Images Using an Active Contour Approach","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Optical coherence tomography; Segmentation; Retinal; Artificial intelligence; Computer science; Computer vision; Ganglion cell layer; Image segmentation; Retina; Nerve fiber layer; Optics; Pattern recognition (psychology); Physics; Ophthalmology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01661832786320866,"gpt":0.3051264185756198,"spread":0.2885080907124111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003406418,0.0002105417,0.0004023696,0.0002814131,0.0001369461,0.00004142974,0.0001592971,0.0001087063,0.0005566897],"category_scores_gemma":[0.0000612542,0.0001829221,0.0002197562,0.0003864694,0.0005938684,0.0002785773,0.00000194551,0.00101392,0.000005570637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003661831,"about_ca_system_score_gemma":0.0001460133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006482179,"about_ca_topic_score_gemma":0.00001952345,"domain_scores_codex":[0.9979724,0.00009890422,0.0004005037,0.000423568,0.0008185494,0.0002860653],"domain_scores_gemma":[0.9987719,0.0001778939,0.0001178725,0.0002958134,0.0001873436,0.0004491536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002952517,0.001109627,0.003388785,0.00005124933,0.0002387018,0.0000671675,0.000600483,0.0002296613,0.8245603,0.000008329866,0.00003402464,0.1694165],"study_design_scores_gemma":[0.002214475,0.0001585435,0.003615657,0.0003063347,0.001053023,0.0002130009,0.003220242,0.1598368,0.8289388,0.00009632721,0.00001634571,0.000330443],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.486646,0.00001674462,0.5120718,0.0004616411,0.0001671126,0.0001118624,0.00002147385,0.00005250601,0.0004509006],"genre_scores_gemma":[0.9533998,0.00001429143,0.04603532,0.0003120888,0.0001509726,0.00001448956,0.00002714973,0.00002493577,0.00002097167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4667538,"threshold_uncertainty_score":0.7459347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388922836","doi":"10.1016/s2589-7500(23)00201-7","title":"Large language models and their impact in ophthalmology","year":2023,"lang":"en","type":"review","venue":"The Lancet Digital Health","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Janssen Pharmaceuticals; National Key Research and Development Program of China; Health and Medical Research Fund; National Medical Research Council; Janssen Research and Development; Allergan; National Institutes of Health; Carl Zeiss Meditec AG; Santen; U.S. Department of Agriculture; Regeneron Pharmaceuticals; Nvidia; National Eye Institute; National Institute on Aging; Mylan; Medical Research Council; Biogen; Novo Nordisk; Sanofi; Apellis Pharmaceuticals; Genentech; Research to Prevent Blindness","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1421734737718413,"gpt":0.4665683283218467,"spread":0.3243948545500054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006661073,0.0002686145,0.002324474,0.0001724468,0.00004536336,0.00005535319,0.0001576777,0.00008683543,0.000007998658],"category_scores_gemma":[0.00007554187,0.0001220418,0.0002929094,0.0004434055,0.0000538452,0.0000685698,0.00009819626,0.000513026,0.00005169875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008909216,"about_ca_system_score_gemma":0.0002753041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002152953,"about_ca_topic_score_gemma":0.00001014021,"domain_scores_codex":[0.9985844,0.0001289598,0.0003845139,0.0002714352,0.0001025673,0.0005280576],"domain_scores_gemma":[0.9989579,0.0002850227,0.0001692622,0.0004419335,0.00001306402,0.0001328586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003085237,0.00008806809,0.0004457853,0.02119956,0.0002910565,0.0003672697,0.001291593,0.000002494847,2.348369e-8,0.0001552505,0.001871553,0.9742565],"study_design_scores_gemma":[0.004186027,0.001646488,0.001802457,0.1281205,0.001063466,0.01793135,0.00451103,0.00557219,1.969277e-7,0.01268825,0.8206386,0.001839454],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001766181,0.9936575,0.00001153035,0.000888733,0.00002690943,0.0003832619,0.0004021577,0.00006654132,0.002797219],"genre_scores_gemma":[0.01415751,0.9837825,0.000006241607,0.000240163,0.0002635618,0.00002042203,0.000331292,0.000048136,0.00115016],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9724171,"threshold_uncertainty_score":0.497672,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2911612938","doi":"10.1016/j.preteyeres.2019.01.001","title":"Retinal capillary perfusion: Spatial and temporal heterogeneity","year":2019,"lang":"en","type":"review","venue":"Progress in Retinal and Eye Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Health and Medical Research Council; Australian Research Council","keywords":"Retina; Retinal; Microvessel; Perfusion; Microcirculation; Blood flow; Biology; Neuroscience; Internal medicine; Angiogenesis; Biochemistry; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1481939321611478,"gpt":0.4751047561933347,"spread":0.3269108240321869,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002968468,0.0004899454,0.002081514,0.0008142699,0.0002337643,0.0001838402,0.0002495107,0.0004097976,0.00007816133],"category_scores_gemma":[0.0002093566,0.0003464789,0.0003267595,0.0007323312,0.001002042,0.00006721307,0.0006322297,0.002147824,0.00005958579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001234,"about_ca_system_score_gemma":0.0003844502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003057969,"about_ca_topic_score_gemma":0.00001645155,"domain_scores_codex":[0.9952319,0.0009204446,0.0007367164,0.001089448,0.001158115,0.0008633594],"domain_scores_gemma":[0.9983264,0.000257337,0.0001840363,0.0005438855,0.0002834749,0.000404829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000155984,0.0001056647,0.1831824,0.02608686,0.00007090767,0.0006853099,0.00005496708,7.148403e-9,0.000001051326,0.00001255907,0.0001326551,0.7895117],"study_design_scores_gemma":[0.0009187486,0.001159,0.006605002,0.04311766,0.0008425943,0.001881166,0.0001337099,0.000389859,0.00001062391,0.0000394904,0.9442395,0.0006626435],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.02655635,0.9710634,0.00000221692,0.0006179949,0.00006412773,0.0009746014,0.00001275889,0.00003129073,0.0006772373],"genre_scores_gemma":[0.01256239,0.985171,0.0003409362,0.00001526243,0.0004351543,0.0001208674,0.0001309575,0.00006376105,0.001159687],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9441068,"threshold_uncertainty_score":0.9998987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806424800","doi":"10.1016/j.jcjo.2018.04.019","title":"Deep learning in ophthalmology: a review","year":2018,"lang":"en","type":"review","venue":"Canadian Journal of Ophthalmology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Deep learning; Optical coherence tomography; Macular degeneration; Modalities; Glaucoma; Optometry; Diabetic retinopathy; Medicine; Cataracts; Computer science; Artificial intelligence; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.06710786722469497,"gpt":0.3817603809811355,"spread":0.3146525137564405,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001515393,0.0004533836,0.004257665,0.001779923,0.00008252468,0.00002343106,0.0004734725,0.0004827181,0.004357704],"category_scores_gemma":[0.001829553,0.0003579511,0.00122639,0.00104226,0.0003403629,0.00006461007,0.00002863458,0.001968783,0.0002120933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004848884,"about_ca_system_score_gemma":0.004232326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001168724,"about_ca_topic_score_gemma":0.00003660612,"domain_scores_codex":[0.9963058,0.0007814918,0.001648941,0.0003775975,0.0001986679,0.0006875034],"domain_scores_gemma":[0.996797,0.0002172217,0.001217313,0.0003912311,0.0004042403,0.0009729917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"case_report","study_design_gemma":"case_report","study_design_scores_codex":[0.00001871724,0.00006040523,0.006625196,0.05076077,0.0009729363,0.728841,0.00007143028,0.00000187329,1.087375e-7,0.00001751685,0.003646273,0.2089838],"study_design_scores_gemma":[0.0001285932,0.0003452141,0.00007956814,0.05421386,0.001343557,0.5120848,0.000009959842,0.000002549168,2.577114e-8,0.00001716729,0.4316233,0.0001512989],"study_design_candidate":"case_report","study_design_consensus":"case_report","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001594905,0.9771001,0.000002891847,0.00033555,0.000420276,0.0002799403,0.000003911556,0.000003468373,0.02169435],"genre_scores_gemma":[0.000831161,0.9944205,0.0003289467,0.00008389301,0.0004765334,0.00001139264,0.00004522657,0.00007251616,0.003729854],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4279771,"threshold_uncertainty_score":0.9998872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3103855452","doi":"","title":"Blended multi-modal deep convnet features for diabetic retinopathy severity prediction","year":2020,"lang":"en","type":"article","venue":"Lancaster EPrints (Lancaster University)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"Ministry of Science and ICT, South Korea","keywords":"Computer science; Artificial intelligence; Pooling; Pattern recognition (psychology); Deep learning; Modal; Cohen's kappa; Dropout (neural networks); Convolutional neural network; Benchmark (surveying); Feature (linguistics); Feature extraction; Focus (optics); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02519661033229529,"gpt":0.2376209091698362,"spread":0.2124242988375409,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001102268,0.0002663615,0.0004945271,0.0001865775,0.0001209892,0.00004664512,0.0002058167,0.0001369182,0.0002519404],"category_scores_gemma":[0.00006340155,0.0002610236,0.000257551,0.0003916705,0.00009853475,0.0001831369,0.0001388444,0.0003259504,0.0001856784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008100731,"about_ca_system_score_gemma":0.00004923028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000152445,"about_ca_topic_score_gemma":0.00001064282,"domain_scores_codex":[0.9984189,0.00008594908,0.0002307737,0.0006275676,0.0002309936,0.0004057962],"domain_scores_gemma":[0.9989415,0.00005086999,0.0001241184,0.0003572748,0.0001695714,0.0003566296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00270996,0.0003787927,0.9699967,0.0007692073,0.0006340669,0.0006857025,0.002353659,0.000005045851,0.009861038,0.0001390282,0.00210743,0.01035937],"study_design_scores_gemma":[0.006959781,0.0004529159,0.9181453,0.0001713518,0.0008123239,0.0001132985,0.001155902,0.0257887,0.003566623,0.00002023382,0.04237365,0.0004399373],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9463685,0.00008315485,0.03875983,0.004995313,0.0002693856,0.0008206106,0.0001400763,0.0002577228,0.008305443],"genre_scores_gemma":[0.9827296,0.00001927177,0.005019727,0.001325153,0.0003182116,0.000003526468,0.0001248232,0.00003632456,0.01042336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0518514,"threshold_uncertainty_score":0.9999842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283773504","doi":"10.3390/diagnostics12071607","title":"Diabetic Retinopathy Detection from Fundus Images of the Eye Using Hybrid Deep Learning Features","year":2022,"lang":"en","type":"article","venue":"Diagnostics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"Prince Mohammad Bin Fahd University; Commonwealth Cyber Initiative","keywords":"Diabetic retinopathy; Artificial intelligence; Fundus (uterus); Computer science; Convolutional neural network; Pattern recognition (psychology); Retina; Feature (linguistics); Retinopathy; Feature extraction; Support vector machine; Computer vision; Ophthalmology; Medicine; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.008561041427438455,"gpt":0.247544086546006,"spread":0.2389830451185675,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001729085,0.0001017293,0.0002140502,0.00007378728,0.0002957179,0.00001901275,0.0001057303,0.00002079731,0.00009067654],"category_scores_gemma":[0.001614574,0.00008036889,0.0001398395,0.0002777823,0.00007639547,0.00002323267,0.0001285456,0.0004829344,0.000002957716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006606236,"about_ca_system_score_gemma":0.00002604706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000338828,"about_ca_topic_score_gemma":0.000003711996,"domain_scores_codex":[0.9989724,0.0001788649,0.0001828375,0.0001795351,0.000327301,0.0001590508],"domain_scores_gemma":[0.9990813,0.0003994998,0.0001528005,0.0002425291,0.00007756183,0.00004626868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006274951,0.0001778626,0.8514526,0.00005798831,0.0001557286,0.0001325508,0.0005323143,0.009357382,0.1133322,0.000006005409,0.0004131169,0.02431943],"study_design_scores_gemma":[0.0009164228,0.0003421771,0.6536951,0.0002420551,0.001921063,0.00008935701,0.001643698,0.0341847,0.3035325,0.0003750697,0.002747847,0.0003099643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961793,0.002127482,0.0006779718,0.0003205168,0.0002770562,0.00009778282,0.00002696513,0.00003486609,0.000258074],"genre_scores_gemma":[0.9988711,0.000135899,0.0003225327,0.0001689389,0.0001398237,0.000008379413,0.00002840882,0.00002135513,0.0003035407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1977576,"threshold_uncertainty_score":0.3277348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3015711121","doi":"10.1167/tvst.9.2.20","title":"Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography","year":2020,"lang":"en","type":"article","venue":"Translational Vision Science & Technology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Ensemble learning; Optical coherence tomography; Pattern recognition (psychology); Deep learning; Diabetic retinopathy; Majority rule; Classifier (UML); Machine learning; Medicine; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.02208978926930519,"gpt":0.3151593437827645,"spread":0.2930695545134593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003698474,0.0001343543,0.0002515858,0.001184983,0.0004042229,0.00004511796,0.0001882098,0.0001137915,0.0000309367],"category_scores_gemma":[0.000237596,0.0001217931,0.0002567717,0.005218478,0.0008868555,0.0001802851,0.00002446189,0.0002715221,0.0000144665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001874536,"about_ca_system_score_gemma":0.00006185342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000327966,"about_ca_topic_score_gemma":8.750494e-7,"domain_scores_codex":[0.9983656,0.00001959356,0.0002816912,0.000529859,0.0004623397,0.000340953],"domain_scores_gemma":[0.9991888,0.0000831742,0.00008436135,0.0001505176,0.0003310592,0.0001620673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001130748,0.0000512492,0.131242,0.00003414736,0.00002447532,0.000005196076,0.0001441271,0.001252908,0.80327,0.000381285,0.000002209393,0.06347931],"study_design_scores_gemma":[0.001622385,0.00186032,0.07599638,0.0001416004,0.0004686864,0.0001210986,0.000486552,0.6761539,0.2374205,0.004284725,0.0009837577,0.0004601336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6339887,0.0003159081,0.3609896,0.004032049,0.00003552543,0.0002217901,0.000001013649,0.0001588102,0.0002565662],"genre_scores_gemma":[0.9717624,0.00000559945,0.02797396,0.0001775523,0.00004001492,0.00001665109,0.000005067743,0.00001208716,0.000006704655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.674901,"threshold_uncertainty_score":0.4966579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075728937","doi":"10.1089/tmj.2011.0075","title":"Telehealth Practice Recommendations for Diabetic Retinopathy, Second Edition","year":2011,"lang":"en","type":"review","venue":"Telemedicine Journal and e-Health","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Eye Institute","keywords":"Telemedicine; Telehealth; Statutory law; Diabetic retinopathy; Quality (philosophy); Medicine; Matching (statistics); Key (lock); Medical emergency; Medical education; Nursing; Health care; Computer science; Political science; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.1151457807402409,"gpt":0.4374432777783284,"spread":0.3222974970380875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005065569,0.0004734954,0.002862502,0.0006680233,0.0006457639,0.00005779173,0.000142919,0.0001752509,0.0004700822],"category_scores_gemma":[0.0006182333,0.0003224791,0.0004713887,0.0004444484,0.0001079558,0.0001861495,0.00003784313,0.001662449,0.00002244773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003851521,"about_ca_system_score_gemma":0.001881046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009851046,"about_ca_topic_score_gemma":0.00001115933,"domain_scores_codex":[0.996088,0.0004434159,0.001933036,0.0004716089,0.0003515409,0.0007124584],"domain_scores_gemma":[0.9952039,0.0004344418,0.002541754,0.0003244052,0.000417598,0.001077895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002065205,0.000118847,0.000009890204,0.01697386,0.0002232776,0.00001380385,0.0002736351,4.132875e-9,1.03371e-7,0.00005508213,0.2391981,0.7431127],"study_design_scores_gemma":[0.0009919719,0.002354434,0.00002695478,0.03106246,0.002039312,0.006936357,0.0005215661,0.000008857752,1.604803e-7,0.0001758064,0.9556545,0.0002276375],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002620041,0.9305595,0.001291764,0.06517888,0.000841839,0.001125596,0.00007608015,0.00004862209,0.0008750605],"genre_scores_gemma":[0.00000805666,0.9771273,0.008063173,0.008201558,0.003890416,0.00006840379,0.0005909554,0.00007753039,0.001972636],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7428851,"threshold_uncertainty_score":0.9999228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2884292375","doi":"10.1109/tmi.2018.2854886","title":"Supervised Segmentation of Un-Annotated Retinal Fundus Images by Synthesis","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Chinese Government Scholarship; China Scholarship Council","keywords":"Computer science; Pipeline (software); Fundus (uterus); Artificial intelligence; Segmentation; Data set; Set (abstract data type); Image segmentation; Focus (optics); Pattern recognition (psychology); Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.01158039288741047,"gpt":0.2896817830643729,"spread":0.2781013901769624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004536594,0.0001908591,0.0003723233,0.0002529424,0.0001735686,0.00002489867,0.0001310855,0.0000717064,0.003751522],"category_scores_gemma":[0.0001308785,0.0001636486,0.0002000063,0.0005214469,0.0005355693,0.0001300328,0.000001559407,0.0003653665,0.00008502451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005647239,"about_ca_system_score_gemma":0.00009097584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001924985,"about_ca_topic_score_gemma":0.000002601366,"domain_scores_codex":[0.9979374,0.0001330428,0.0004637379,0.000340525,0.0008292675,0.0002959846],"domain_scores_gemma":[0.9988362,0.0002369757,0.00009689591,0.0002744424,0.0002519883,0.0003034558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004834789,0.0009607443,0.002268965,0.000162784,0.0004425696,0.0001298815,0.0005145748,0.00002607881,0.3655851,0.000002264067,0.006249297,0.6231743],"study_design_scores_gemma":[0.001269187,0.0001662004,0.0004096741,0.0005191615,0.0007596679,0.0001520518,0.0005861013,0.02821665,0.9673107,0.00002059873,0.0003847345,0.0002052705],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2361414,0.0001950951,0.7503187,0.01074663,0.000298392,0.0001998476,0.00005052136,0.000194849,0.001854555],"genre_scores_gemma":[0.9958382,0.0001366945,0.002490981,0.0008624292,0.0001084007,0.00002260368,0.00001423702,0.00003142625,0.0004950847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7596968,"threshold_uncertainty_score":0.9971592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366281042","doi":"10.3390/jimaging9040084","title":"Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review","year":2023,"lang":"en","type":"review","venue":"Journal of Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Deep learning; Convolutional neural network; Macular degeneration; Modalities; Artificial intelligence; Glaucoma; Diabetic retinopathy; Retinal; Grading (engineering); Retinal Disorder; Blindness; CAD; Machine learning; Optometry; Medicine; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.07344503460586009,"gpt":0.4173284557208994,"spread":0.3438834211150393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00101736,0.0004234015,0.002745333,0.0009563249,0.0001528539,0.00007510513,0.0001936708,0.00007022109,0.00002910588],"category_scores_gemma":[0.001051491,0.0003167574,0.001933966,0.001052028,0.0000812474,0.0001720491,0.00008149457,0.001747826,0.00003010932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003784222,"about_ca_system_score_gemma":0.000387819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001092092,"about_ca_topic_score_gemma":1.416831e-7,"domain_scores_codex":[0.9967365,0.0004267286,0.001572163,0.0003016024,0.0006409724,0.0003219843],"domain_scores_gemma":[0.9960799,0.0001978279,0.002323825,0.0002826971,0.0007737498,0.0003420497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001812347,0.00002294999,0.00006401438,0.09297697,0.0003323989,0.001853158,0.00001099714,0.000002512513,0.000030929,2.698775e-7,0.0001162639,0.9045714],"study_design_scores_gemma":[0.0001078155,0.00004472825,0.000009112055,0.3621552,0.01249055,0.005629718,0.00004899633,0.0005446793,0.000004240861,0.000007330264,0.618744,0.0002137015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000010996,0.9955503,0.003515919,0.0002565523,0.0001577633,0.0003461824,0.00000161621,0.00009309419,0.00006761518],"genre_scores_gemma":[0.0000153416,0.9957802,0.002828139,0.0002425555,0.0008477442,0.000007569439,0.00001302762,0.0001142323,0.0001512412],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9043577,"threshold_uncertainty_score":0.9999285,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045084177","doi":"10.1016/j.artmed.2020.101936","title":"Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network","year":2020,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Grading (engineering); Diabetic retinopathy; Convolutional neural network; Artificial intelligence; Fundus (uterus); Retinopathy; Pattern recognition (psychology); Deep learning; Artificial neural network; Blindness; Medicine; Diabetes mellitus; Optometry; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.2042992541879632,"gpt":0.3906956446763256,"spread":0.1863963904883623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007143465,0.0001986127,0.0005357072,0.0001884996,0.0001294081,0.00001997494,0.0001478046,0.00007151854,0.00011871],"category_scores_gemma":[0.001751821,0.0001735655,0.0001047566,0.001214252,0.0002312864,0.00006972454,0.0000312529,0.000279046,0.00003758122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009875741,"about_ca_system_score_gemma":0.00006450732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009744242,"about_ca_topic_score_gemma":0.0000195283,"domain_scores_codex":[0.9978474,0.00007678723,0.0007947208,0.0004764364,0.0003590917,0.0004455587],"domain_scores_gemma":[0.9987826,0.0003075371,0.0001465485,0.0002035887,0.0002330616,0.0003266661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003268941,0.0004851549,0.1339868,0.0006118417,0.0002155771,0.0002319453,0.006936851,0.08944748,0.4754409,0.03044453,0.007131143,0.2517988],"study_design_scores_gemma":[0.0001738021,0.0005779657,0.0023288,0.0004026808,0.0001953581,0.00001784685,0.001122611,0.9876451,0.003202324,0.003596701,0.0005523185,0.0001844308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7045603,0.000393223,0.2281752,0.06526373,0.0005175008,0.0007782257,0.00000558494,0.00009231398,0.0002139334],"genre_scores_gemma":[0.9856868,0.00001586716,0.008660463,0.003601281,0.001889141,0.00003324963,0.00005140809,0.00002798794,0.00003375662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8981977,"threshold_uncertainty_score":0.7077795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888994752","doi":"10.1109/ccece.2018.8447809","title":"Diabetic Retinopathy Detection Using Machine Learning and Texture Features","year":2018,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Support vector machine; Histogram; Artificial intelligence; Diabetic retinopathy; Pattern recognition (psychology); Computer science; Local binary patterns; Kernel (algebra); Radial basis function kernel; Blindness; Radial basis function; Feature extraction; Retinopathy; Computer vision; Diabetes mellitus; Mathematics; Medicine; Artificial neural network; Kernel method; Image (mathematics); Optometry","retraction":null,"screen_n_in":null,"score":{"opus":0.008613050664998748,"gpt":0.2759663458196579,"spread":0.2673532951546592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001200772,0.00007906244,0.0001371911,0.00008578629,0.0001409975,0.00002837279,0.00001580197,0.00004255963,0.0001101073],"category_scores_gemma":[0.000116421,0.00005615599,0.0000382269,0.0001568474,0.00007860439,0.00003207816,0.0000190945,0.0001882074,0.00001107392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001431762,"about_ca_system_score_gemma":0.000006812604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000203622,"about_ca_topic_score_gemma":0.00002695583,"domain_scores_codex":[0.9995047,0.00003255431,0.00008136337,0.0001596378,0.0001005442,0.0001211944],"domain_scores_gemma":[0.9997416,0.00001764783,0.00003256938,0.00007598976,0.00006513241,0.00006705745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009092004,0.00002956442,0.3874053,0.00006469796,0.00007077016,0.00002622362,0.0003054194,0.000002765501,0.5468349,0.000012646,0.00006861067,0.06508819],"study_design_scores_gemma":[0.002226622,0.00172996,0.2361959,0.000494186,0.001537327,0.001799438,0.001017299,0.3107431,0.4281862,0.0002459718,0.01516612,0.0006578795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934211,0.0005991312,0.001495044,0.0004484488,0.00004337434,0.00004329786,2.481181e-7,0.00007572272,0.003873636],"genre_scores_gemma":[0.9926238,0.00003146001,0.001599658,0.0002101158,0.0002359748,5.858533e-7,0.000002633412,0.00001120825,0.00528456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3107403,"threshold_uncertainty_score":0.2289975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196430628","doi":"10.3390/jimaging7090165","title":"Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey","year":2021,"lang":"en","type":"review","venue":"MDPI (MDPI AG)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Diabetic retinopathy; Optical coherence tomography; Fundus (uterus); Segmentation; Deep learning; Scope (computer science); Machine learning; Medicine; Optometry; Ophthalmology; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.05849450532614049,"gpt":0.3548473948317635,"spread":0.2963528895056231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004390462,0.0004406351,0.003024103,0.000375742,0.00007546392,0.0000477196,0.0001104302,0.0002807323,0.0001019027],"category_scores_gemma":[0.000751093,0.0003561072,0.0005721075,0.0009501434,0.0001595119,0.00003794793,0.0001050746,0.0004497481,0.00003429253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008616576,"about_ca_system_score_gemma":0.000173356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005140224,"about_ca_topic_score_gemma":0.00002907719,"domain_scores_codex":[0.9971998,0.0007563593,0.0008080098,0.0005952062,0.0003474311,0.0002932125],"domain_scores_gemma":[0.9974753,0.0008088324,0.0005233691,0.000544975,0.0004720985,0.0001754087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001559276,0.0001829416,0.007852414,0.02739433,0.001101316,0.0002186107,0.00009428745,8.165583e-7,0.00004108945,0.000001731841,0.001181471,0.9619154],"study_design_scores_gemma":[0.001168252,0.0005606888,0.02824884,0.0797635,0.01687007,0.0005127102,0.0001184678,0.001034905,0.0004071094,0.000008623851,0.8701447,0.001162144],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01225661,0.9866482,0.00001193087,0.0000426515,0.000166241,0.0004458999,0.00007979596,0.0001715156,0.0001771657],"genre_scores_gemma":[0.01004529,0.9886599,0.000104852,0.00004884214,0.00009853485,0.00009614735,0.0004853103,0.00007014265,0.0003910178],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9607533,"threshold_uncertainty_score":0.9998891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4223572678","doi":"10.1038/s41598-022-09675-y","title":"State-of-the-art retinal vessel segmentation with minimalistic models","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"DiagnoCure (Canada); École de Technologie Supérieure","funders":"Marie Curie","keywords":"Computer science; Segmentation; Benchmark (surveying); Artificial intelligence; Context (archaeology); Convolutional neural network; Task (project management); Pattern recognition (psychology); Domain adaptation; Deep learning; Domain (mathematical analysis); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01578420207779882,"gpt":0.2614645849652535,"spread":0.2456803828874547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008735859,0.00007856421,0.0001632872,0.000119994,0.0003369089,0.00004838669,0.00007315754,0.000006967041,0.0001471583],"category_scores_gemma":[0.00004443549,0.00005304124,0.00009037236,0.000730539,0.0002147382,0.00007399236,0.00006685682,0.0001212966,0.000002947342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000594505,"about_ca_system_score_gemma":0.0002077816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002938077,"about_ca_topic_score_gemma":0.000002704729,"domain_scores_codex":[0.9981936,0.00005616328,0.000331315,0.0003722411,0.0008933998,0.0001532314],"domain_scores_gemma":[0.9988973,0.00001458438,0.0003151833,0.0005447069,0.0001662346,0.00006195102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007933929,0.001332946,0.2501818,0.0005265831,0.0004784938,0.00459036,0.006814299,0.05955509,0.4217343,0.0001915309,0.2402531,0.01354804],"study_design_scores_gemma":[0.004251751,0.002394081,0.04761091,0.001321926,0.004534276,0.02688731,0.009140774,0.167487,0.5229301,0.0481826,0.1632922,0.001967169],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929001,0.00007871165,0.002020228,0.0007161448,0.000841077,0.0002286574,0.000004413805,0.00002731501,0.003183396],"genre_scores_gemma":[0.9719743,8.858943e-7,0.001156546,0.00005257702,0.00001272585,0.00002377933,0.00006002143,0.00001032063,0.02670884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2025709,"threshold_uncertainty_score":0.2591265,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2915212708","doi":"10.1016/j.artmed.2019.02.004","title":"Joint segmentation and classification of retinal arteries/veins from fundus images","year":2019,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":105,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St Mary's Hospital Centre; Polytechnique Montréal","funders":"","keywords":"Fundus (uterus); Segmentation; Joint (building); Diabetic retinopathy; Retinal; Image segmentation; Track (disk drive)","retraction":null,"screen_n_in":null,"score":{"opus":0.07126866799630192,"gpt":0.3514150413634922,"spread":0.2801463733671902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004393586,0.0001207095,0.0003956185,0.0002311022,0.00002440797,0.00001094965,0.00005565469,0.00005522354,0.0006245715],"category_scores_gemma":[0.0002534788,0.00009657897,0.00004135201,0.0003453804,0.0002828853,0.00009478704,0.00001827856,0.0001794362,0.00006989021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003882876,"about_ca_system_score_gemma":0.0000288502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009155074,"about_ca_topic_score_gemma":0.00005037903,"domain_scores_codex":[0.9985791,0.00005943857,0.0006247434,0.0002912627,0.0002948912,0.0001505083],"domain_scores_gemma":[0.9992511,0.000127157,0.0001787527,0.0002392593,0.0001275924,0.00007610075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001953778,0.0001348213,0.08919456,0.00006936271,0.00002729986,0.00001502801,0.001741551,0.00001432002,0.7938329,0.0008493754,0.0001236199,0.1138018],"study_design_scores_gemma":[0.0004660933,0.001714057,0.5027648,0.001617184,0.0003281099,0.00003462053,0.02833209,0.03401993,0.4174005,0.01272698,0.0002913521,0.0003042886],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837819,0.0002883144,0.008296099,0.005420043,0.0001372879,0.000220089,0.000004318121,0.00002018249,0.001831778],"genre_scores_gemma":[0.9976435,0.0002188473,0.001526639,0.0001818699,0.0001409066,0.000007064238,0.00005583228,0.00001023517,0.0002151167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4135703,"threshold_uncertainty_score":0.683862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387783953","doi":"10.1016/j.cell.2023.09.012","title":"Liquid-biopsy proteomics combined with AI identifies cellular drivers of eye aging and disease in vivo","year":2023,"lang":"en","type":"article","venue":"Cell","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of General Medical Sciences; National Institutes of Health; H. Lundbeck A/S; Lundbeckfonden; National Eye Institute; VitreoRetinal Surgery Foundation; Research to Prevent Blindness","keywords":"Biology; Proteomics; Disease; Cell; Cell type; Macular degeneration; Computational biology; Transcriptome; Neuroscience; Retinal; Bioinformatics; Pathology; Genetics; Gene; Gene expression; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.006793906641585929,"gpt":0.2426276258651501,"spread":0.2358337192235642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001092248,0.00007968612,0.0001935035,0.0001704566,0.00002708262,0.00001418093,0.00004124747,0.00001817363,0.00001704308],"category_scores_gemma":[0.0000263878,0.0000647529,0.00004069873,0.0003332243,0.00009534186,0.00004470054,0.00003151258,0.00008431407,0.000007952699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001222856,"about_ca_system_score_gemma":0.00004016493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006614161,"about_ca_topic_score_gemma":0.000002456882,"domain_scores_codex":[0.9994291,0.00001799167,0.0001288612,0.0001622741,0.0001320094,0.0001297437],"domain_scores_gemma":[0.999623,0.00001568699,0.00004770558,0.0001553943,0.00004286208,0.0001153372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003437025,0.00009259755,0.3605969,0.0007133538,0.00003682006,0.0004315495,0.0009255424,0.0001650353,0.6362604,0.00001188827,0.0004009089,0.00002123825],"study_design_scores_gemma":[0.004143682,0.0004778751,0.06179819,0.001109167,0.0006594825,0.00000342631,0.002398519,0.01860767,0.9098426,0.0002610211,0.0003362893,0.0003620708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981106,0.00008489032,0.0001438072,0.001175902,0.00001918711,0.0001459074,0.000003576601,0.00003482806,0.000281312],"genre_scores_gemma":[0.9953592,0.00004704012,0.000175688,0.00006166885,0.00001540169,0.00000610452,0.00001377196,0.00001224791,0.004308819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2987987,"threshold_uncertainty_score":0.2640547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386826466","doi":"10.1016/j.media.2023.102938","title":"GAMMA challenge: Glaucoma grAding from Multi-Modality imAges","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":102,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"DiagnoCure (Canada); École de Technologie Supérieure","funders":"","keywords":"Glaucoma; Optical coherence tomography; Fundus photography; Grading (engineering); Medicine; Optometry; Fundus (uterus); Ophthalmology; Optic disc; Modality (human–computer interaction); Modalities; Artificial intelligence; Blindness; Computer science; Retinal; Fluorescein angiography","retraction":null,"screen_n_in":null,"score":{"opus":0.02778191829118971,"gpt":0.3494678826587598,"spread":0.3216859643675701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001203433,0.0003221816,0.001157537,0.0009301575,0.0001897172,0.00009885024,0.0003554042,0.0001883186,0.003187837],"category_scores_gemma":[0.001912712,0.0002583994,0.001171641,0.003321148,0.0003461221,0.0001696768,0.0001846792,0.0005835181,0.001083751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007196612,"about_ca_system_score_gemma":0.00009079603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002783703,"about_ca_topic_score_gemma":0.0001535018,"domain_scores_codex":[0.9961387,0.0002295853,0.0006792493,0.0008193525,0.001506631,0.0006264611],"domain_scores_gemma":[0.9976083,0.0003544904,0.000151456,0.0008585713,0.0002227584,0.0008044177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001548356,0.00148342,0.7921714,0.0002548855,0.01969479,0.01153457,0.001368696,0.00001856371,0.01706553,0.0000403518,0.02706745,0.1291456],"study_design_scores_gemma":[0.00244044,0.0000848342,0.5145689,0.0001979908,0.01566839,0.00002676595,0.0008727188,0.4581045,0.00300611,0.0004875109,0.003903877,0.0006379038],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8263194,0.001380266,0.07419523,0.09313556,0.0001775589,0.0002291154,0.0000938736,0.001207254,0.003261772],"genre_scores_gemma":[0.9888029,0.0009949997,0.003881134,0.000831745,0.0004895465,0.00002619802,0.0007483506,0.00004490411,0.004180193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.458086,"threshold_uncertainty_score":0.9999868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4221095684","doi":"10.1038/s41572-022-00342-0","title":"Hypertensive eye disease","year":2022,"lang":"en","type":"review","venue":"Nature Reviews Disease Primers","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":102,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Jewish General Hospital","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research","keywords":"Medicine; Hypertensive retinopathy; Subclinical infection; Blood pressure; Retinopathy; Fundus photography; Disease; Epidemiology; Fundus (uterus); Diabetic retinopathy; Optic nerve; Eye examination; Kidney disease; Population; Ophthalmology; Diabetes mellitus; Internal medicine; Fluorescein angiography; Retinal; Visual acuity","retraction":null,"screen_n_in":null,"score":{"opus":0.05477241810475285,"gpt":0.4000509289752276,"spread":0.3452785108704748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005367025,0.0009988919,0.004900517,0.000506397,0.0002259058,0.0000574532,0.0005070922,0.0003008161,0.002086989],"category_scores_gemma":[0.00225975,0.0006869544,0.005221948,0.001347922,0.0001345679,0.00008328132,0.0002350829,0.002883495,0.0006542258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004171638,"about_ca_system_score_gemma":0.001498521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004312662,"about_ca_topic_score_gemma":9.574442e-8,"domain_scores_codex":[0.9953821,0.0007486944,0.001118239,0.001273645,0.0009088059,0.0005685043],"domain_scores_gemma":[0.9953602,0.0001703845,0.0007700857,0.001747626,0.0001292047,0.001822491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005027112,0.0001947079,0.00007124759,0.05644145,0.0006405108,0.001039849,0.000004619451,1.093735e-7,8.473108e-8,0.00002887728,0.01898914,0.9225391],"study_design_scores_gemma":[0.0001990008,0.00002208787,0.00005636092,0.02382592,0.04105727,0.00001772599,0.000005954227,0.000007239828,2.495578e-8,0.00001228446,0.9341801,0.0006160575],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[6.694382e-7,0.9945945,0.0000040009,0.0007201127,0.0004376927,0.002501977,0.000196051,0.000137323,0.001407636],"genre_scores_gemma":[0.000001878702,0.9879433,0.0002519493,0.003074371,0.0005909916,0.0006362617,0.002729241,0.0001683177,0.004603672],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9219231,"threshold_uncertainty_score":0.9995582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152896605","doi":"10.1007/978-3-642-04271-3_79","title":"Intra-retinal Layer Segmentation in Optical Coherence Tomography Using an Active Contour Approach","year":2009,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; McGill University; Michael Smith Health Research BC; California HIV/AIDS Research Program","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Segmentation; Retinal; Computer vision; Pattern recognition (psychology); Active contour model; Glaucoma; Contrast (vision); Image segmentation; Optics; Physics; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.0259654486208485,"gpt":0.315407472745822,"spread":0.2894420241249736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004250536,0.0001351175,0.0002315642,0.0004153979,0.00007334707,0.0001004903,0.0002040569,0.00005117443,0.000005149336],"category_scores_gemma":[0.00006987416,0.0001102489,0.00004692248,0.001675844,0.0002632667,0.0002988397,0.00002964122,0.0003007355,9.075141e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078394,"about_ca_system_score_gemma":0.0001052194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007223179,"about_ca_topic_score_gemma":0.00001048493,"domain_scores_codex":[0.9985574,0.00005711931,0.0002020614,0.0004807844,0.0003836302,0.0003190027],"domain_scores_gemma":[0.9994531,0.00006311149,0.00005471881,0.0002128942,0.00009988075,0.0001163395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001332141,0.0006064802,0.06777634,0.00002196989,0.00001057223,0.0001241018,0.003003202,0.07935894,0.1812363,0.00003325981,0.000001279481,0.6676943],"study_design_scores_gemma":[0.000534985,0.0003082246,0.09941982,0.0001148704,0.00002068469,0.0001192125,0.00002267658,0.8276199,0.07087477,0.0008118618,4.817409e-7,0.0001525874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4889046,0.0000176791,0.5106131,0.0002924387,0.00003081731,0.00008710494,2.354639e-7,0.00001452987,0.0000395087],"genre_scores_gemma":[0.7320626,0.000001068503,0.2671351,0.0007100702,0.00008337762,0.000001634006,0.000002887984,0.000003017806,2.504657e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7482609,"threshold_uncertainty_score":0.4495819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206468898","doi":"10.1016/j.xops.2021.100069","title":"Federated Learning for Microvasculature Segmentation and Diabetic Retinopathy Classification of OCT Data","year":2021,"lang":"en","type":"article","venue":"Ophthalmology Science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC; Compute Canada","keywords":"Artificial intelligence; Segmentation; Diabetic retinopathy; Receiver operating characteristic; F1 score; Computer science; Medicine; Deep learning; Retinal; Pattern recognition (psychology); Machine learning; Ophthalmology; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.05372158880732469,"gpt":0.3603125295494699,"spread":0.3065909407421452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005816555,0.00005325935,0.0001506553,0.00007362632,0.0001620414,0.00002907,0.00008570033,0.00003565856,0.00001709625],"category_scores_gemma":[0.00074121,0.00004671016,0.00002340312,0.000443989,0.0003403296,0.0001113213,0.00006640011,0.00008873819,0.000001258412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001462007,"about_ca_system_score_gemma":0.0001387473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007215102,"about_ca_topic_score_gemma":2.410591e-7,"domain_scores_codex":[0.9991995,0.0000491928,0.0001353506,0.0003609515,0.000129711,0.0001253611],"domain_scores_gemma":[0.9993165,0.0000705003,0.00008406779,0.0002161461,0.0002667217,0.00004612752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001515852,0.00002813973,0.1651964,0.00004520628,0.00001429497,0.00002109539,0.00005587998,0.000005545235,0.8306905,0.00001566207,0.00002144044,0.003890641],"study_design_scores_gemma":[0.0006964257,0.0002159549,0.7639883,0.00009394997,0.0002287504,0.002172142,0.0008750317,0.05304484,0.1783741,0.00008719527,0.0001121371,0.0001112469],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970881,0.0003910876,0.0009832409,0.0009076087,0.00004933384,0.00008441314,0.000003328131,0.000007810517,0.0004850727],"genre_scores_gemma":[0.9926692,0.00001928445,0.006559185,0.00003383624,0.00001631294,0.000003474992,0.0001459325,0.000003994863,0.0005487324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6523165,"threshold_uncertainty_score":0.1904785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3096061254","doi":"10.1167/tvst.9.2.55","title":"Artificial Intelligence Algorithms to Diagnose Glaucoma and Detect Glaucoma Progression: Translation to Clinical Practice","year":2020,"lang":"en","type":"article","venue":"Translational Vision Science & Technology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Moorfields Eye Hospital NHS Foundation Trust; Heidelberg Engineering; Moorfields Eye Charity; Academy of Medical Sciences; Carl Zeiss Meditec AG; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Allergan; UK Research and Innovation","keywords":"Glaucoma; Fundus photography; Artificial intelligence; Machine learning; Computer science; Optical coherence tomography; Algorithm; Receiver operating characteristic; Medicine; Gonioscopy; Fundus (uterus); Ophthalmology; Visual acuity","retraction":null,"screen_n_in":null,"score":{"opus":0.06925677442073568,"gpt":0.4542396510534507,"spread":0.384982876632715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312895,0.0001823662,0.0003581247,0.0007350965,0.0002819397,0.0000874747,0.0003180293,0.0001501118,0.00004925565],"category_scores_gemma":[0.002120957,0.0001534491,0.00009249413,0.004473931,0.0007065302,0.000371803,0.00007079008,0.0003928899,0.0001126111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002630119,"about_ca_system_score_gemma":0.0001747818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007037319,"about_ca_topic_score_gemma":0.000005519339,"domain_scores_codex":[0.9971109,0.00006692119,0.0007089686,0.0008642887,0.0008998989,0.0003490415],"domain_scores_gemma":[0.9982727,0.0004018889,0.0001039186,0.0002758553,0.0004202654,0.0005253942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003629266,0.000125079,0.01777149,0.0000115545,0.00001136341,0.00004987823,0.0003804362,0.00001856704,0.02459255,0.0009801296,0.00004539845,0.9556506],"study_design_scores_gemma":[0.00214497,0.01792146,0.3333436,0.001072398,0.000996522,0.001592691,0.00282086,0.3332167,0.1670685,0.02347145,0.114102,0.002248943],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3882842,0.0003711609,0.3336706,0.2765388,0.00009591733,0.0005600553,0.000005314034,0.0002197552,0.0002542124],"genre_scores_gemma":[0.7742382,0.00003762064,0.223149,0.002405018,0.0001281487,0.00002275108,0.000003834116,0.00001099067,0.000004462166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9534017,"threshold_uncertainty_score":0.6257474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3082598879","doi":"10.1109/embc44109.2020.9175664","title":"Explainable Diabetic Retinopathy using EfficientNET","year":2020,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Diabetic retinopathy; Blindness; Convolutional neural network; Computer science; Retinopathy; Diabetes mellitus; Artificial intelligence; Deep learning; Medicine; Optometry","retraction":null,"screen_n_in":null,"score":{"opus":0.04594965067966714,"gpt":0.2857072304884308,"spread":0.2397575798087637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008396222,0.00007722207,0.0001890071,0.00004115485,0.00005044327,0.00002096139,0.00004370165,0.00002131914,0.0004142907],"category_scores_gemma":[0.0001216653,0.00005974802,0.00008084441,0.0003137003,0.00003133858,0.00002913259,0.00002719971,0.00008997278,0.0001361935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001780703,"about_ca_system_score_gemma":0.00002584014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000350218,"about_ca_topic_score_gemma":1.137137e-7,"domain_scores_codex":[0.9993192,0.00001932375,0.0001310035,0.0001885783,0.0001620748,0.0001798063],"domain_scores_gemma":[0.9996002,0.00001641534,0.00002716541,0.0001284066,0.00004980923,0.0001779472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003234014,0.0004857663,0.3798258,0.000818227,0.0002960109,0.001144597,0.002659881,0.002275312,0.5791261,0.0006398038,0.02301796,0.009387218],"study_design_scores_gemma":[0.002313482,0.0006701114,0.006310082,0.000234698,0.0009533087,0.0001363122,0.002148349,0.8546486,0.1089617,0.00005340982,0.02304629,0.0005236817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975021,0.0001491959,0.004952997,0.005544236,0.00002787435,0.00007457485,5.943142e-7,0.000107306,0.0141222],"genre_scores_gemma":[0.9917191,0.000004295391,0.003638882,0.002770602,0.0001147772,0.000001186093,0.000005017933,0.00001184559,0.001734351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8523733,"threshold_uncertainty_score":0.4536193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4383860708","doi":"10.3390/jimaging9070140","title":"Conv-ViT: A Convolution and Vision Transformer-Based Hybrid Feature Extraction Method for Retinal Disease Detection","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Athabasca University","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Feature extraction; Pixel; Deep learning; Computer vision; Preprocessor","retraction":null,"screen_n_in":null,"score":{"opus":0.01130555059973633,"gpt":0.3661486892471792,"spread":0.3548431386474429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019691,0.0001161928,0.0002643251,0.000427456,0.0001440397,0.000055963,0.00003331182,0.0000230811,0.00000752168],"category_scores_gemma":[0.0002877082,0.00009376364,0.0002584485,0.000253129,0.00004193323,0.0002698344,0.000003570874,0.0002721515,0.000002072666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007962069,"about_ca_system_score_gemma":0.0000859607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009872851,"about_ca_topic_score_gemma":0.000001060061,"domain_scores_codex":[0.9990116,0.0000720988,0.0003022117,0.0001568106,0.0002793148,0.0001779995],"domain_scores_gemma":[0.9989859,0.0001642338,0.0002587381,0.00008181285,0.0003168669,0.0001924742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003354053,0.0001044147,0.01167383,0.000510113,0.0001208367,0.0003624496,0.0001130116,0.0002710547,0.6310412,0.000006922212,0.003466043,0.348976],"study_design_scores_gemma":[0.006204293,0.0007062039,0.08497539,0.00144575,0.002411864,0.002362444,0.0006531209,0.7901371,0.09455545,0.0005646827,0.01568228,0.0003014427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2822065,0.0007301489,0.6983953,0.01815977,0.0002194878,0.0001807506,0.000008414959,0.00005006578,0.0000495625],"genre_scores_gemma":[0.9877345,0.00009909096,0.01137913,0.0002463134,0.000304121,0.000004503033,0.00001587885,0.00002029296,0.0001961454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.789866,"threshold_uncertainty_score":0.382357,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073911907","doi":"10.1007/s10278-009-9189-5","title":"Detection of the Optic Nerve Head in Fundus Images of the Retina Using the Hough Transform for Circles","year":2009,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":91,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hough transform; Computer science; Artificial intelligence; Optic nerve; Fundus (uterus); Computer vision; Corner detection; False positive paradox; Edge detection; Sensitivity (control systems); Receiver operating characteristic; Pattern recognition (psychology); Image processing; Image (mathematics); Ophthalmology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02237435526407604,"gpt":0.3027572738867569,"spread":0.2803829186226808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004224984,0.00009934195,0.0002922911,0.0001081658,0.00007651404,0.00006120952,0.0001912167,0.00002027423,8.992057e-7],"category_scores_gemma":[0.0002625039,0.00004722638,0.0004770128,0.0003915119,0.0001486799,0.0003585709,0.0000157319,0.0002617754,7.197355e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006133731,"about_ca_system_score_gemma":0.00007024367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002107437,"about_ca_topic_score_gemma":0.000001844701,"domain_scores_codex":[0.9988759,0.00003555184,0.0005462258,0.00008023057,0.0003042831,0.0001577787],"domain_scores_gemma":[0.9989837,0.0001042661,0.0004673022,0.0001818596,0.0002313826,0.00003148613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005377121,0.0004317347,0.06423512,0.0002548071,0.0002317879,0.0000464931,0.001974507,0.001608462,0.6112603,0.00001924688,0.00009190062,0.319308],"study_design_scores_gemma":[0.003059784,0.0005226795,0.2194042,0.003479305,0.001223121,0.003099446,0.005071823,0.01193974,0.7475963,0.00413317,0.000227531,0.0002428803],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879202,0.0007694745,0.00271348,0.007785774,0.0000892134,0.0001586072,0.000004769688,0.000003544764,0.0005549607],"genre_scores_gemma":[0.9995207,0.00001356718,0.0002236127,0.00007843185,0.00009844855,4.955776e-7,2.49661e-7,0.000009843927,0.00005471979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3190651,"threshold_uncertainty_score":0.1925836,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4295025017","doi":"10.1016/j.media.2022.102608","title":"Focused Attention in Transformers for interpretable classification of retinal images","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hôpital Maisonneuve-Rosemont; Polytechnique Montréal","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Transformer; Convolutional neural network; Pattern recognition (psychology); Machine learning; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.0139775278880238,"gpt":0.3144463017116677,"spread":0.3004687738236438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001471971,0.0001197738,0.0006027012,0.0008622379,0.00008885576,0.00001417913,0.0001419586,0.00004878791,0.001759858],"category_scores_gemma":[0.0004663077,0.0001073622,0.000701439,0.002097578,0.0001461807,0.00009732863,0.00003334975,0.0002977976,0.000003372986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062558,"about_ca_system_score_gemma":0.0001000898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002894528,"about_ca_topic_score_gemma":0.00003884812,"domain_scores_codex":[0.9978503,0.0001517215,0.0006210682,0.0003333787,0.0008036478,0.0002399105],"domain_scores_gemma":[0.9992163,0.0001271725,0.0001673466,0.000199457,0.0001482372,0.00014152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001694834,0.002055618,0.6216801,0.0006041598,0.004461869,0.0001730815,0.0008609736,0.0001196633,0.1934693,0.0001005089,0.004331255,0.1704486],"study_design_scores_gemma":[0.00524167,0.0007800536,0.3313189,0.0001775317,0.01405493,0.00004096593,0.00443497,0.6348895,0.006245734,0.0002097599,0.002175388,0.0004306937],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6494945,0.0002436118,0.3364293,0.01078309,0.00004533432,0.0003328403,0.00004908568,0.00004300993,0.002579156],"genre_scores_gemma":[0.9961098,0.00004857763,0.002214147,0.0001895791,0.0000308635,0.0001142471,0.0003249757,0.00001404513,0.0009537524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6347698,"threshold_uncertainty_score":0.9991527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065396718","doi":"10.1159/000265967","title":"Association between Colour Vision Losses and Diabetes mellitus","year":2009,"lang":"en","type":"article","venue":"Ophthalmic Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":87,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminant function analysis; Hue; Linear discriminant analysis; Medicine; Diabetes mellitus; Colour Vision; Optometry; Ophthalmology; Color vision; Audiology; Mathematics; Artificial intelligence; Statistics; Computer science; Endocrinology","retraction":null,"screen_n_in":null,"score":{"opus":0.05248267141685402,"gpt":0.425459236026147,"spread":0.372976564609293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001732896,0.00008516444,0.0002593315,0.0002438983,0.0001678242,0.0001074834,0.000080696,0.00008845162,0.00008218444],"category_scores_gemma":[0.0007506689,0.00006908856,0.00006076927,0.0004840274,0.00006546733,0.00009202815,0.00003637236,0.0003872007,0.00009800136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389934,"about_ca_system_score_gemma":0.00005021104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000503738,"about_ca_topic_score_gemma":3.285739e-7,"domain_scores_codex":[0.9982137,0.0001935908,0.0001742022,0.0002612814,0.0007512601,0.0004059689],"domain_scores_gemma":[0.9988382,0.0004441734,0.00004554051,0.0001997981,0.0003030806,0.0001691383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000271025,0.00009102538,0.9346216,0.00005045853,0.000104539,0.00005352165,0.00007027049,5.730998e-7,0.02102947,0.00002461869,0.005945193,0.03798166],"study_design_scores_gemma":[0.0005004113,0.0008135644,0.9849916,0.0001759413,0.0001065891,0.00001528156,0.00009896245,0.0004157237,0.007928759,0.001479126,0.003374142,0.00009995265],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766864,0.001260042,0.000003530619,0.01179518,0.00001377517,0.0001392419,0.000003186268,0.0000255893,0.01007311],"genre_scores_gemma":[0.9897474,0.0004849661,0.0002118233,0.00005740645,0.0001968115,0.00000371232,0.00002057756,0.000008784396,0.009268521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05036999,"threshold_uncertainty_score":0.281735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}