{"meta":{"query_hash":"7272f52356ba","filters":{"venue":"Diagnostic and Prognostic Research"},"cohort_total":35,"direct_labels_cover":1,"predictions_cover":35,"exported":35,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/7272f52356ba","api":"https://metacan.xera.ac/api/v1/cohort?venue=Diagnostic+and+Prognostic+Research"},"results":[{"id":"W2588203234","doi":"10.1186/s41512-016-0001-y","title":"Methods for Evaluating Medical Tests and Biomarkers","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Calgary; McGill University; Jewish General Hospital; McMaster University; Population Health Research Institute","funders":"National Health and Medical Research Council; Haukeland Universitetssjukehus; Universiteit Leiden; Assistance publique-Hôpitaux de Paris; Leids Universitair Medisch Centrum; Universitetet i Bergen; Albert-Ludwigs-Universität Freiburg; Universiteit van Amsterdam; Abbott Diagnostics; University of Oxford; University of New South Wales; Medical Research Council; University of Notre Dame","keywords":"Equivalence (formal languages); Confidence interval; Statistics; Margin (machine learning); Sample (material); Medicine; Mathematics; Computer science; Chromatography; Machine learning; Chemistry","score_opus":0.269673097928087,"score_gpt":0.6196684686333537,"score_spread":0.34999537070526665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588203234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754312,0.0048207752,0.007484303,0.008029074,0.00030738572,0.001928467,0.00000828774,0.0000471958,0.0019433303],"genre_scores_gemma":[0.9601881,0.0015506312,0.0371006,0.0000752546,0.00034329327,0.00039291522,0.000011077316,0.000029755482,0.0003083602],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979335,0.00032022616,0.00022897088,0.00041329055,0.00060219,0.0005017956],"domain_scores_gemma":[0.97177696,0.026820524,0.00005913559,0.00045492552,0.0003493347,0.00053914066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008305135,0.00013425863,0.00029013175,0.00012670795,0.0008943085,0.00018382011,0.00018222378,0.00016909563,0.000054884935],"category_scores_gemma":[0.1333587,0.00010417035,0.000040992833,0.000062384745,0.0006658016,0.00006588643,0.0001726586,0.00036269386,0.000007694427],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001133521,0.000064807384,0.2485907,0.00023302961,0.00008029071,0.000044173918,0.000154213,4.2139792e-8,0.00038366416,0.0006481828,0.00025401096,0.7494335],"study_design_scores_gemma":[0.0049032723,0.0025143283,0.93758804,0.0016332272,0.0001476475,0.00025425517,0.00027072107,0.031531096,0.0008619412,0.0123784,0.0076298416,0.00028722466],"about_ca_topic_score_codex":0.00014877367,"about_ca_topic_score_gemma":0.000004653888,"teacher_disagreement_score":0.74914634,"about_ca_system_score_codex":0.000025025874,"about_ca_system_score_gemma":0.00029655025,"threshold_uncertainty_score":0.87394136},"labels":[],"label_agreement":null},{"id":"W2594867411","doi":"10.1186/s41512-017-0008-z","title":"Systematic reviews of prognosis studies: a critical appraisal of five core clinical journals","year":2017,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Critical appraisal; Core (optical fiber); Systematic review; Medicine; MEDLINE; Political science; Computer science; Alternative medicine; Pathology","score_opus":0.980188190277515,"score_gpt":0.7828199083667856,"score_spread":0.19736828191072942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594867411","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007772994,0.9842169,0.00024159273,0.00016575796,0.0009989707,0.013256868,0.00018475222,0.000004278301,0.0008531196],"genre_scores_gemma":[0.0006880705,0.9935141,0.0013393025,0.000012190962,0.00043044594,0.0029295636,0.000017299139,0.00006133841,0.0010076787],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.7726757,0.13629918,0.068603955,0.0034808293,0.017505642,0.0014346729],"domain_scores_gemma":[0.033795565,0.9091361,0.03193001,0.009036417,0.015141575,0.0009603154],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.5289953,0.0011503693,0.04813793,0.0019155059,0.00056290923,0.001233804,0.006486299,0.00082363305,0.0017959173],"category_scores_gemma":[0.98389375,0.00050353096,0.008773118,0.0025897257,0.0032525975,0.00031725084,0.0016832517,0.002015863,0.0017595026],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066903463,0.0003687883,0.0034248852,0.5233034,0.0023267446,0.00008349298,0.0005113013,1.18077345e-7,2.4757473e-8,0.0014899076,0.036391906,0.43209273],"study_design_scores_gemma":[0.00022213363,0.00060493255,0.00029356315,0.4363207,0.009129196,0.00014267751,0.001204909,0.00008754125,1.1238151e-7,0.0030406308,0.54847205,0.00048157288],"about_ca_topic_score_codex":0.000014587603,"about_ca_topic_score_gemma":0.0000076497745,"teacher_disagreement_score":0.7728369,"about_ca_system_score_codex":0.0000562391,"about_ca_system_score_gemma":0.0010801933,"threshold_uncertainty_score":0.999803},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2602288447","doi":"10.1186/s41512-017-0011-4","title":"Erratum to: Methods for evaluating medical tests and biomarkers","year":2017,"lang":"en","type":"erratum","venue":"Diagnostic and Prognostic Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University Health Centre; University of Calgary; McGill University; South Health Campus; Jewish General Hospital; McMaster University; Population Health Research Institute","funders":"Institute of Genetics; School of Public Health, Imperial College London; Klinisk Institut, Syddansk Universitet; Medical Research Council; Institute of Psychiatry, Psychology and Neuroscience, King’s College London; Syddansk Universitet; Odense Universitetshospital; KU Leuven; iMinds; Newcastle upon Tyne Hospitals NHS Foundation Trust; Cambridge University Hospitals; Loughborough University; University of Glasgow; Warwick Medical School; Universiteit van Amsterdam; Newcastle University; Albert-Ludwigs-Universität Freiburg; King's College London; University of Oxford; University of Warwick; Vrije Universiteit Amsterdam; Imperial College London; University of Exeter; Cancer Research UK; University of Southampton; University College London; University of Cambridge; British Heart Foundation; National Institute for Health and Care Excellence; University of Leeds; National Institute for Health and Care Research; Inselspital, Universitätsspital Bern; King's College Hospital NHS Foundation Trust","keywords":"Medical physics; Computer science; Psychology; Medicine","score_opus":0.12967390453280553,"score_gpt":0.5536366208162352,"score_spread":0.4239627162834297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602288447","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026413698,0.2602126,0.085366726,0.32728618,0.06935165,0.045075893,0.00040127867,0.00086421927,0.18502775],"genre_scores_gemma":[0.036478754,0.06533086,0.5251108,0.009375921,0.02354522,0.009917744,0.003576461,0.001460301,0.32520393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99410325,0.0009055931,0.0006495514,0.0012629272,0.0018226678,0.001255995],"domain_scores_gemma":[0.95580214,0.0401616,0.00020832186,0.00085753936,0.0009427473,0.0020276324],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016914222,0.000480704,0.001130411,0.0006403398,0.001017786,0.0004705207,0.00054425345,0.00091899984,0.00014456698],"category_scores_gemma":[0.47610697,0.00038849912,0.00014169166,0.00025248682,0.0011971197,0.00007333883,0.00074609445,0.0036597177,0.000025590858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093215334,0.00006951162,0.0057847425,0.0013957422,0.00019134834,0.00018539758,0.00018674893,1.381142e-7,0.0000311206,0.00011764197,0.5358881,0.4560563],"study_design_scores_gemma":[0.0031786405,0.0035562231,0.058178794,0.012213464,0.0007721964,0.0006936663,0.00019591863,0.041571744,0.000013933133,0.0059358785,0.8728915,0.0007980636],"about_ca_topic_score_codex":0.00024819822,"about_ca_topic_score_gemma":0.000014824895,"teacher_disagreement_score":0.45919275,"about_ca_system_score_codex":0.00008879844,"about_ca_system_score_gemma":0.0020005913,"threshold_uncertainty_score":0.9998567},"labels":[],"label_agreement":null},{"id":"W2605897081","doi":"10.1186/s41512-017-0012-3","title":"Validation of prediction models: examining temporal and geographic stability of baseline risk and estimated covariate effects","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Covariate; Baseline (sea); Stability (learning theory); Statistics; Econometrics; Computer science; Mathematics; Machine learning; Biology","score_opus":0.3648981795435242,"score_gpt":0.46175307836447255,"score_spread":0.09685489882094833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605897081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93515944,0.0005370146,0.06290278,0.000027299122,0.000021878705,0.0010899826,0.00011160939,0.00005495192,0.00009505711],"genre_scores_gemma":[0.9773926,0.0018790788,0.020540627,0.0000012247704,0.000016374892,0.00012565446,0.000024310759,0.000017866123,0.000002235954],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979902,0.00055726303,0.000431078,0.0003516714,0.0004080942,0.00026168948],"domain_scores_gemma":[0.9757554,0.022831064,0.00032843524,0.00045584622,0.00051153655,0.00011773791],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004795097,0.00015350227,0.00036717692,0.00019216901,0.00032686285,0.00007590359,0.00013979526,0.00013043654,0.000006768288],"category_scores_gemma":[0.06939388,0.0001329962,0.00001898451,0.00012626403,0.00093281886,0.00036683565,0.0002622754,0.0003111243,1.913777e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073417315,0.00014127449,0.97402495,0.0012169824,0.000035914978,0.0000064739925,0.00050338946,0.000008449945,0.0010462529,0.0063626855,0.00001445471,0.016565753],"study_design_scores_gemma":[0.00076933595,0.0010925214,0.46232662,0.0012304472,0.00013266876,0.0000068632417,0.00015505872,0.033756606,0.018784143,0.4815931,0.0000015730642,0.00015106634],"about_ca_topic_score_codex":0.00056067813,"about_ca_topic_score_gemma":0.000016112432,"teacher_disagreement_score":0.5116983,"about_ca_system_score_codex":0.000012344181,"about_ca_system_score_gemma":0.000050421375,"threshold_uncertainty_score":0.93844503},"labels":[],"label_agreement":null},{"id":"W2607440911","doi":"10.1186/s41512-017-0013-2","title":"Systematic review of the effects of care provided with and without diagnostic clinical prediction rules","year":2017,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Health and Medical Research Council; National Medical Research Council; Medical Research Council","keywords":"Medicine; Triage; Chest pain; Randomized controlled trial; Physical therapy; Emergency medicine; Pneumonia; Medical prescription; Intensive care medicine; Internal medicine","score_opus":0.22082966790995673,"score_gpt":0.5047728361852114,"score_spread":0.2839431682752547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607440911","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014102987,0.975457,0.000002307644,0.00011756662,0.00017760316,0.022492813,0.00014102808,0.000020188825,0.00018120819],"genre_scores_gemma":[0.008585596,0.9861055,0.00007538319,0.000040004874,0.00012426607,0.0048027723,0.00012692435,0.00007790818,0.00006162924],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99357593,0.0019923574,0.0018166784,0.0008088585,0.0013199885,0.000486173],"domain_scores_gemma":[0.93047786,0.06541911,0.0012491276,0.0015610068,0.0009575395,0.0003353657],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002347751,0.0005732423,0.0050905226,0.00024089907,0.00028745207,0.00006883257,0.00042163386,0.00038749052,0.00000820404],"category_scores_gemma":[0.1660913,0.00027704227,0.00053509715,0.00032229142,0.001180648,0.000071037255,0.00036702037,0.00092617504,0.000009120888],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020632648,0.0003714607,0.083964355,0.8337774,0.0010367034,0.000068590714,0.00010100827,6.3071557e-9,2.0417419e-8,0.00009040526,0.00025078628,0.08031863],"study_design_scores_gemma":[0.0011579999,0.0032070803,0.02676726,0.9436274,0.01891595,0.00021792781,0.000057051966,0.0000012647715,0.000003980643,0.00002558713,0.0058135367,0.00020495515],"about_ca_topic_score_codex":0.000076298114,"about_ca_topic_score_gemma":0.000010478288,"teacher_disagreement_score":0.16374356,"about_ca_system_score_codex":0.00008498576,"about_ca_system_score_gemma":0.0010353609,"threshold_uncertainty_score":0.9999682},"labels":[],"label_agreement":null},{"id":"W2770017713","doi":"10.1186/s41512-018-0028-3","title":"Using ordinal outcomes to construct and select biomarker combinations for single-level prediction","year":2018,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Abbott Diagnostics; Pritzker School of Medicine; University of California, San Francisco; National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Institute for Clinical Evaluative Sciences; U.S. Department of Veterans Affairs","keywords":"Outcome (game theory); Logistic regression; Biomarker; Context (archaeology); Computer science; Selection (genetic algorithm); Construct (python library); Machine learning; Artificial intelligence; Data mining; Statistics; Mathematics","score_opus":0.5615408223281894,"score_gpt":0.5013232235527673,"score_spread":0.0602175987754221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770017713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99067575,0.00052082964,0.0024652195,0.0026560705,0.00016030553,0.0026068462,0.00015347498,0.000041061332,0.0007204154],"genre_scores_gemma":[0.9929977,0.0000935645,0.0059714303,0.00021636768,0.0001243219,0.00043631546,0.000053225107,0.000027128755,0.000079951744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828583,0.00010502579,0.00026839308,0.00044908503,0.00040734018,0.00048431117],"domain_scores_gemma":[0.9912817,0.007363431,0.000036473688,0.00019084314,0.0007757369,0.00035181022],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00068736624,0.0001746752,0.000307905,0.00035473038,0.0004980561,0.000116277675,0.00005603272,0.0000974736,0.000053613294],"category_scores_gemma":[0.0107312,0.00013756582,0.000048587644,0.0004306802,0.00045029717,0.0000949478,0.000089099,0.00012695268,0.00001572501],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012308951,0.00061702216,0.9653718,0.00009775873,0.00018166866,0.000023627708,0.00024354656,2.7162469e-7,0.00084359816,0.0018053435,0.0020755937,0.028616663],"study_design_scores_gemma":[0.003041529,0.0035649752,0.9861693,0.00039566346,0.0002705862,0.00020187693,0.00026660427,0.0011921647,0.0016935498,0.0015301964,0.0015205657,0.0001529884],"about_ca_topic_score_codex":0.00013953014,"about_ca_topic_score_gemma":0.000023866001,"teacher_disagreement_score":0.028463675,"about_ca_system_score_codex":0.00009022616,"about_ca_system_score_gemma":0.00014360396,"threshold_uncertainty_score":0.9976018},"labels":[],"label_agreement":null},{"id":"W2785428416","doi":"10.1186/s41512-018-0026-5","title":"The current application of the Royston-Parmar model for prognostic modeling in health research: a scoping review","year":2018,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Statistical Methods in Epidemiology","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Research Manitoba","keywords":"Current (fluid); Computer science; Risk analysis (engineering); Engineering; Management science; Data science; Medicine","score_opus":0.8581699158084114,"score_gpt":0.6892457691337626,"score_spread":0.16892414667464883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785428416","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025801353,0.7777141,0.19559759,0.0008218469,0.00017717197,0.025516989,0.00010673957,0.00002119043,0.000041826705],"genre_scores_gemma":[0.00005171093,0.95306706,0.02597807,0.00004297833,0.00023428623,0.020449158,0.000034163506,0.00011569529,0.000026848846],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9756254,0.015748054,0.0036460157,0.0013070644,0.0016683525,0.0020051461],"domain_scores_gemma":[0.55448633,0.4409501,0.0009663546,0.0016484254,0.0016293875,0.00031941533],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07353503,0.0005306162,0.0027419948,0.00041971746,0.0010920729,0.000084159496,0.0017334672,0.00033085237,0.0000036279955],"category_scores_gemma":[0.5923545,0.00030022455,0.0003607093,0.0017842861,0.0017700898,0.000057254787,0.0011263695,0.002928839,0.000012460942],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010450486,0.00011762561,0.00003480055,0.28390056,0.000032500717,7.8040375e-7,0.00010748306,0.0000143858715,7.538817e-9,0.0366701,0.0023103168,0.67680097],"study_design_scores_gemma":[0.00016609399,0.0001921764,0.0000029428481,0.4900841,0.00019445758,0.000009684717,0.0000214882,0.15886204,7.82869e-8,0.32632512,0.023911437,0.00023035026],"about_ca_topic_score_codex":0.00006932817,"about_ca_topic_score_gemma":0.00012813487,"teacher_disagreement_score":0.67657065,"about_ca_system_score_codex":0.0003470503,"about_ca_system_score_gemma":0.0032666542,"threshold_uncertainty_score":0.999945},"labels":[],"label_agreement":null},{"id":"W2806302551","doi":"10.1186/s41512-018-0032-7","title":"Ruling out pulmonary embolism across different subgroups of patients and healthcare settings: protocol for a systematic review and individual patient data meta-analysis (IPDMA)","year":2018,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Thrombosis and Atherosclerosis Research Institute; Ottawa Hospital; University of Ottawa","funders":"ZonMw; Ottawa Hospital Research Institute; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Heart and Stroke Foundation of Canada","keywords":"Medicine; Pulmonary embolism; MEDLINE; Protocol (science); Health care; Meta-analysis; Comorbidity; Intensive care medicine; Diagnosis code; Medical physics; Alternative medicine; Pathology; Internal medicine; Population","score_opus":0.3734064158965,"score_gpt":0.506414335431613,"score_spread":0.13300791953511298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806302551","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061154504,0.71897346,0.000024408724,0.00037916572,0.000028137963,0.27782866,0.0026705242,0.000021088525,0.000013417584],"genre_scores_gemma":[0.00031010908,0.6856077,0.00019014251,0.00022749,0.000070137496,0.31143323,0.0020612937,0.000077503544,0.000022413438],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9915218,0.0015252215,0.0025177384,0.001754431,0.0016038365,0.0010770094],"domain_scores_gemma":[0.98410755,0.011220533,0.0012759784,0.0016991602,0.0010831243,0.00061365566],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0052834433,0.00087979774,0.01017514,0.00059653184,0.00048538763,0.00021780843,0.00064085674,0.00037435183,0.000038148417],"category_scores_gemma":[0.013619529,0.0005476551,0.0008211671,0.0007608703,0.0005373577,0.00015030663,0.002380068,0.0006907191,0.0000054978577],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021468035,0.0008850465,0.0006430602,0.91778547,0.042578723,0.0000250295,0.00061289617,1.701976e-8,5.4312035e-9,0.00006142546,0.0015802891,0.035806555],"study_design_scores_gemma":[0.00092274655,0.0022659316,0.0018052245,0.31459782,0.6277051,0.000030422972,0.00037983718,0.000037146176,3.5554967e-7,0.00008680601,0.051468723,0.00069990236],"about_ca_topic_score_codex":0.00008326881,"about_ca_topic_score_gemma":0.000036742003,"teacher_disagreement_score":0.6031877,"about_ca_system_score_codex":0.00006644746,"about_ca_system_score_gemma":0.00023052104,"threshold_uncertainty_score":0.9996975},"labels":[],"label_agreement":null},{"id":"W2885733420","doi":"10.1186/s41512-018-0038-1","title":"OPTimal IMAging strategy in patients suspected of non-traumatic pulmonary disease at the emergency department: chest X-ray or ultra-low-dose CT (OPTIMACT)—a randomised controlled trial chest X-ray or ultra-low-dose CT at the ED: design and rationale","year":2018,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Radiation Dose and Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Universiteit van Amsterdam; ZonMw; Amsterdam University Medical Centers","keywords":"Medicine; Emergency department; Medical diagnosis; Radiology; Randomized controlled trial; Randomization; Emergency medicine; Surgery","score_opus":0.03896839631195267,"score_gpt":0.33409805108942914,"score_spread":0.2951296547774765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885733420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97737867,0.001933378,0.00016415742,0.0014917372,0.00021800259,0.017903848,0.00007862962,0.00003221493,0.0007993433],"genre_scores_gemma":[0.9933682,0.0022360866,0.00012556788,0.00012689916,0.00033627028,0.0026980487,0.00031726088,0.000066556495,0.00072509784],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.99422103,0.0014473218,0.0012938245,0.0007864171,0.0012937154,0.00095767336],"domain_scores_gemma":[0.9773874,0.02052595,0.0003581001,0.00061212503,0.00057662284,0.0005397796],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032143514,0.00048633313,0.0008988019,0.00032198406,0.0008804542,0.0001655732,0.00033826637,0.00006166818,0.0016731786],"category_scores_gemma":[0.022464529,0.00026516215,0.00017280705,0.00079720234,0.0010270549,0.00037804988,0.000113061484,0.00051862036,0.000057166482],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.70488924,0.0049671107,0.24962395,0.0011424931,0.0006666623,0.0012247211,0.002459254,0.000914947,0.0031738721,0.000021230095,0.00837723,0.02253929],"study_design_scores_gemma":[0.34965825,0.0022194884,0.61671007,0.00071283407,0.0006411203,0.00006355888,0.0010460495,0.026527753,0.0016799417,0.000068805784,0.00016692217,0.00050520175],"about_ca_topic_score_codex":0.00011674746,"about_ca_topic_score_gemma":0.00004006941,"teacher_disagreement_score":0.3670861,"about_ca_system_score_codex":0.00014946514,"about_ca_system_score_gemma":0.00085411966,"threshold_uncertainty_score":0.99998003},"labels":[],"label_agreement":null},{"id":"W2886902670","doi":"10.1186/s41512-018-0042-5","title":"Chronic Disease Population Risk Tool (CDPoRT): a study protocol for a prediction model that assesses population-based chronic disease incidence","year":2018,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Trillium Health Centre; University of Toronto; Toronto Public Health","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Population; Cohort; Disease; Incidence (geometry); Cohort study; Environmental health; Internal medicine","score_opus":0.13001671179050742,"score_gpt":0.45947348366280133,"score_spread":0.32945677187229394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886902670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6015685,0.00042547344,0.010082346,0.000888854,0.00014409321,0.38583347,0.0005219159,0.00035017426,0.00018518408],"genre_scores_gemma":[0.7274388,0.00003147945,0.00018650577,0.000035874804,0.0008196369,0.27061102,0.0006545683,0.00006022543,0.00016187639],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952632,0.00038370458,0.0006467929,0.0011367984,0.0016531283,0.00091636064],"domain_scores_gemma":[0.99415576,0.0032564085,0.00023639367,0.0009019222,0.0007040996,0.0007454131],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016442902,0.00041796712,0.0004325471,0.00047765227,0.00085928926,0.00036275006,0.00025765566,0.000101767444,0.0002488796],"category_scores_gemma":[0.012740929,0.00036374372,0.00014273234,0.0006093584,0.0003589371,0.0005296633,0.00021230603,0.00039504596,0.000032951888],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017327415,0.001239209,0.979292,0.0028693485,0.00010674799,0.0000960177,0.00007604742,0.0027326485,0.0000024711817,0.0006008877,0.0014175546,0.009834372],"study_design_scores_gemma":[0.004889196,0.0023464917,0.73367673,0.0011150701,0.00052244583,0.0000012166709,0.00008556329,0.25317344,0.0000045318516,0.0036378577,0.0002933152,0.00025413602],"about_ca_topic_score_codex":0.00062073,"about_ca_topic_score_gemma":0.00032286326,"teacher_disagreement_score":0.25044078,"about_ca_system_score_codex":0.00084439653,"about_ca_system_score_gemma":0.002616647,"threshold_uncertainty_score":0.99988145},"labels":[],"label_agreement":null},{"id":"W2910687296","doi":"10.1186/s41512-019-0047-8","title":"Development of a clinical decision support tool for diagnostic imaging use in patients with low back pain: a study protocol","year":2019,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; Health Sciences Centre; Queen's University; University of Ottawa; Nova Scotia Health Authority; Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Low back pain; Emergency department; Guideline; Cauda equina syndrome; Health care; Medical imaging; Back pain; Physical therapy; Radiology; Alternative medicine; Nursing; Pathology","score_opus":0.0558465045857909,"score_gpt":0.4294845113779942,"score_spread":0.3736380067922033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910687296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82549244,0.0000074682043,0.00061657414,0.00006518116,0.000045528937,0.1737077,0.0000060945376,0.000011865843,0.000047163427],"genre_scores_gemma":[0.92953587,0.0000034585178,0.010549535,0.000057785965,0.000038441216,0.059647147,0.000056790795,0.000036735142,0.00007425073],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995849,0.00066278974,0.0012237645,0.00066311494,0.0010655659,0.0005357398],"domain_scores_gemma":[0.9338026,0.06450849,0.00015100281,0.00041383418,0.00090408407,0.00022000828],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00861054,0.00022046136,0.00063339795,0.0003467256,0.00008922887,0.00005620588,0.00012914835,0.00010471619,0.00013318114],"category_scores_gemma":[0.0844072,0.00014964753,0.000081094906,0.00045849156,0.00023023061,0.00017631004,0.00012997133,0.00039333222,0.00005037403],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022153868,0.003907557,0.8895786,0.0025512509,0.00004203473,0.000012609226,0.0007100962,0.0000030922195,0.0000048647207,0.000015167805,0.00027032784,0.10068906],"study_design_scores_gemma":[0.015021428,0.0072632027,0.97301507,0.0027850603,0.000019844527,7.003884e-7,0.00051982125,0.0004258269,0.00000833738,0.000061406216,0.00069695787,0.00018234474],"about_ca_topic_score_codex":0.000026799662,"about_ca_topic_score_gemma":0.000036104197,"teacher_disagreement_score":0.11406054,"about_ca_system_score_codex":0.00005930997,"about_ca_system_score_gemma":0.00058310595,"threshold_uncertainty_score":0.9233052},"labels":[],"label_agreement":null},{"id":"W2933387395","doi":"10.1186/s41512-019-0052-y","title":"Challenges of rapid reviews for diagnostic test accuracy questions: a protocol for an international survey and expert consultation","year":2019,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health; Queen's University; University of Toronto; St. Michael's Hospital","funders":"Instituto de Salud Carlos III","keywords":"Protocol (science); Test (biology); Management science; Systematic review; Computer science; Diagnostic test; Critical appraisal; Best practice; Data science; Risk analysis (engineering); Medicine; MEDLINE; Engineering; Pathology; Alternative medicine; Political science","score_opus":0.8737448761086614,"score_gpt":0.6505695240934505,"score_spread":0.22317535201521088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2933387395","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06608039,0.023423247,0.016876092,0.0045766877,0.0005982623,0.8838146,0.0009924875,0.000025574513,0.003612656],"genre_scores_gemma":[0.41886616,0.009710712,0.008644781,0.00012731888,0.00025163704,0.5613637,0.00014959052,0.000043860317,0.0008422581],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98350745,0.007887303,0.004486874,0.0012744174,0.0024212948,0.00042265773],"domain_scores_gemma":[0.2951049,0.6946225,0.0020790822,0.0017722048,0.0061107087,0.00031059765],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12183328,0.00030099196,0.0019185133,0.000494515,0.00021475066,0.0006833031,0.0010515384,0.00013646313,0.0007274248],"category_scores_gemma":[0.90931594,0.00017118605,0.00031458697,0.0006035955,0.0002515076,0.00055224675,0.00017180468,0.00018243422,0.00017755803],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017133752,0.00064193265,0.35326383,0.0016041732,0.00013396767,0.0000016498774,0.0017936765,0.000005791141,0.000090074005,0.009459019,0.023874076,0.6089605],"study_design_scores_gemma":[0.0034021856,0.0034425932,0.5524462,0.0018093429,0.00009921565,0.000020300886,0.0017346888,0.010277018,0.00007180498,0.01950384,0.40668863,0.00050416833],"about_ca_topic_score_codex":0.000055345932,"about_ca_topic_score_gemma":0.000101527716,"teacher_disagreement_score":0.7874826,"about_ca_system_score_codex":0.000022725802,"about_ca_system_score_gemma":0.00016622778,"threshold_uncertainty_score":0.9042574},"labels":[],"label_agreement":null},{"id":"W3014535943","doi":"10.1186/s41512-020-00074-3","title":"State of the art in selection of variables and functional forms in multivariable analysis—outstanding issues","year":2020,"lang":"en","type":"editorial","venue":"Diagnostic and Prognostic Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":249,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Erasmus+; Medical Research Council; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Multivariable calculus; Selection (genetic algorithm); Computer science; Variable (mathematics); Variables; Feature selection; Management science; Artificial intelligence; Machine learning; Mathematics; Engineering","score_opus":0.11032277138808598,"score_gpt":0.4295645871614275,"score_spread":0.3192418157733415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014535943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38350362,0.0123958895,0.312332,0.003593179,0.24385121,0.02372312,0.00792477,0.0002143262,0.012461868],"genre_scores_gemma":[0.8930114,0.00510204,0.06511939,0.00001736018,0.03450119,0.00073286984,0.00026609306,0.00013496309,0.0011147244],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99673975,0.0007471804,0.00072266534,0.0004172269,0.0010121608,0.0003610394],"domain_scores_gemma":[0.91608584,0.08302428,0.00020269064,0.00016960503,0.00043796704,0.00007960681],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036006202,0.00019458239,0.000761674,0.00046237258,0.00007490599,0.00005373682,0.00016287218,0.0002564426,0.000084133506],"category_scores_gemma":[0.1589703,0.00013392333,0.00005667039,0.0016789016,0.0003242443,0.000061005714,0.00023594164,0.001035627,9.801048e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066671625,0.00078936794,0.6503866,0.0064738663,0.00090823555,0.000041704294,0.0027928245,0.00019814855,0.00023257903,0.1036119,0.22565314,0.008244959],"study_design_scores_gemma":[0.0017447349,0.0007758579,0.21537496,0.0034588282,0.00062108814,0.0000021315498,0.0004023926,0.01527536,0.0004458637,0.75199205,0.00942686,0.00047989312],"about_ca_topic_score_codex":0.00070026243,"about_ca_topic_score_gemma":0.0003370565,"teacher_disagreement_score":0.6483801,"about_ca_system_score_codex":0.000061010564,"about_ca_system_score_gemma":0.0003221072,"threshold_uncertainty_score":0.8481141},"labels":[],"label_agreement":null},{"id":"W3097626155","doi":"10.1186/s41512-020-00086-z","title":"A study protocol for a predictive algorithm to assess population-based premature mortality risk: Premature Mortality Population Risk Tool (PreMPoRT)","year":2020,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Bruyère; Ottawa Hospital; University of Ottawa; Institute for Clinical Evaluative Sciences; Statistics Canada; Public Health Ontario; University of Toronto","funders":"Economic and Social Research Council; Canadian Institutes of Health Research; University of Toronto; Canada Excellence Research Chairs, Government of Canada; UK Research and Innovation","keywords":"Medicine; Population; Population health; Cohort; Community health; Incidence (geometry); Demography; Public health; Environmental health; Internal medicine","score_opus":0.1776897348669443,"score_gpt":0.4730064597835983,"score_spread":0.29531672491665395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097626155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60111153,0.000047389436,0.0064993883,0.0006538689,0.000068390975,0.39028874,0.00082208903,0.00025005118,0.00025852834],"genre_scores_gemma":[0.7097623,0.0000065168183,0.0016667453,0.00012041748,0.00039215386,0.28735635,0.0006082907,0.000056533256,0.00003069367],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99411476,0.00092410337,0.00085696066,0.0013320566,0.0019669286,0.000805194],"domain_scores_gemma":[0.99272233,0.0046767327,0.0003210945,0.0007834958,0.00078007474,0.0007162647],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026558875,0.0004710136,0.0007463674,0.00024820227,0.0005581011,0.0003463634,0.00029310188,0.0002372717,0.00012121943],"category_scores_gemma":[0.029269721,0.00039408417,0.00017703621,0.0009787228,0.00011607107,0.0002840748,0.00026495065,0.0009579545,0.000013759837],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011043138,0.0015154588,0.9848715,0.0022177056,0.00049240387,0.00014561813,0.00076428667,0.00079545233,0.0000014800028,0.00010231199,0.0028849423,0.0051045064],"study_design_scores_gemma":[0.005207245,0.0035660912,0.9562987,0.00062711915,0.00096044166,0.0000023311486,0.0010073228,0.030202832,0.0000129747505,0.0014200686,0.0003368333,0.0003580256],"about_ca_topic_score_codex":0.0015912205,"about_ca_topic_score_gemma":0.00020326315,"teacher_disagreement_score":0.108650744,"about_ca_system_score_codex":0.0002164991,"about_ca_system_score_gemma":0.00053578534,"threshold_uncertainty_score":0.9998511},"labels":[],"label_agreement":null},{"id":"W3135659546","doi":"10.1186/s41512-021-00095-6","title":"Diabetes after pregnancy: a study protocol for the derivation and validation of a risk prediction model for 5-year risk of diabetes following pregnancy","year":2021,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Gestational Diabetes Research and Management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta; Health Sciences Centre; Sunnybrook Health Science Centre; Sinai Health System; St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto; Women's College Hospital","funders":"Physicians' Services Incorporated Foundation; Diabetes Action Canada; Ontario Ministry of Health and Long-Term Care; Diabetes Canada; Diabetes Action Research and Education Foundation","keywords":"Pregnancy; Medicine; Gestational diabetes; Population; Body mass index; Obstetrics; Percentile; Cohort; Demography; Statistics; Gestation; Internal medicine; Environmental health; Mathematics","score_opus":0.05755973319139719,"score_gpt":0.37732000273959587,"score_spread":0.3197602695481987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135659546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.840848,0.0010649343,0.0063799117,0.00018703775,0.000023685865,0.151163,0.0002987114,0.000014220307,0.000020503743],"genre_scores_gemma":[0.70279694,0.0001998243,0.0017934653,0.0000048172137,0.000026340702,0.29504484,0.000062722494,0.000018785504,0.00005228756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997736,0.00031415728,0.00044137053,0.00039331775,0.00070269307,0.00041248524],"domain_scores_gemma":[0.9845708,0.013790652,0.00014870403,0.00028196097,0.0010962863,0.000111582594],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016286519,0.00014473138,0.00030120113,0.00018120484,0.00024549794,0.000061792845,0.00008403133,0.00006594962,0.0000094618035],"category_scores_gemma":[0.03096981,0.00010413086,0.000100172765,0.00033091306,0.00016074593,0.00014389264,0.00013871575,0.00019292606,4.4223157e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021081818,0.00070494565,0.970179,0.0028852702,0.00038548763,0.0000019411382,0.001144162,0.00018596213,0.00020929937,0.00016809539,0.00010510157,0.023819908],"study_design_scores_gemma":[0.005751862,0.0024687375,0.89741045,0.0030270377,0.00059190916,1.7239097e-7,0.0008947952,0.0793597,0.0032348272,0.007113082,0.00004164859,0.00010576483],"about_ca_topic_score_codex":0.000014760484,"about_ca_topic_score_gemma":0.000011693185,"teacher_disagreement_score":0.14388186,"about_ca_system_score_codex":0.000023660901,"about_ca_system_score_gemma":0.00018949073,"threshold_uncertainty_score":0.97719276},"labels":[],"label_agreement":null},{"id":"W3149528813","doi":"10.1186/s41512-021-00097-4","title":"PRISMA-DTA for Abstracts: a new addition to the toolbox for test accuracy research","year":2021,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"University of Ottawa","keywords":"Toolbox; Guideline; Test (biology); Consolidated Standards of Reporting Trials; Observational study; Systematic review; Computer science; Medical physics; Clinical trial; MEDLINE; Information retrieval; Medicine; Data science; Political science; Pathology","score_opus":0.9094318379964861,"score_gpt":0.6543724124729947,"score_spread":0.25505942552349137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149528813","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2110879,0.031372935,0.2453304,0.4032678,0.0021987085,0.072847806,0.0032960048,0.000066046334,0.03053241],"genre_scores_gemma":[0.8984124,0.0008308788,0.022834998,0.0014938036,0.00232782,0.009157776,0.00029041053,0.00008068648,0.06457123],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97700113,0.0074520325,0.0047586416,0.0017728151,0.007798027,0.0012173511],"domain_scores_gemma":[0.095923394,0.8846796,0.00094994454,0.0041188817,0.013408375,0.00091978884],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1995884,0.00029190784,0.0014940472,0.00057742506,0.001371511,0.0040958067,0.0021228637,0.00016474411,0.00351664],"category_scores_gemma":[0.94622374,0.00014417416,0.00067829323,0.003402066,0.00022736427,0.00029450364,0.0004621791,0.0006161599,0.0030003225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027946508,0.00013570786,0.0036981464,0.00013331897,0.00006714712,0.000016430899,0.0008067165,0.00002375999,0.000055782224,0.004112067,0.8160928,0.1748302],"study_design_scores_gemma":[0.0004392388,0.0004926372,0.022286627,0.0002455552,0.00009313463,0.00001840588,0.002739264,0.0015505177,0.00023813713,0.06493417,0.90677065,0.00019167303],"about_ca_topic_score_codex":0.000069176895,"about_ca_topic_score_gemma":0.00019614902,"teacher_disagreement_score":0.88107777,"about_ca_system_score_codex":0.00006120311,"about_ca_system_score_gemma":0.0010734792,"threshold_uncertainty_score":0.9999286},"labels":[],"label_agreement":null},{"id":"W3165628081","doi":"10.1186/s41512-021-00101-x","title":"The development and validation of a prognostic model to PREDICT Relapse of depression in adult patients in primary care: protocol for the PREDICTR study","year":2021,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"NIHR School for Primary Care Research; National Institute for Health and Care Research; University College London; Department of Health and Social Care; Wellcome Trust","keywords":"Depression (economics); Medicine; Logistic regression; Anxiety; Quality of life (healthcare); Optimism; Cohort; Internal medicine; Psychiatry; Psychology; Psychotherapist","score_opus":0.08904236318636065,"score_gpt":0.44175638309321086,"score_spread":0.3527140199068502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165628081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8691493,0.0002886761,0.000073035924,0.00011973153,0.00005204542,0.13002159,0.000026151449,0.0000055358737,0.0002639012],"genre_scores_gemma":[0.74230254,0.000027158896,0.0002076993,0.000011321507,0.0000120120485,0.2573445,0.00003508783,0.000012646954,0.000046986886],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99737823,0.0005038886,0.000684431,0.0004247379,0.0005869211,0.00042177597],"domain_scores_gemma":[0.98790294,0.0111013,0.00011528425,0.00028571632,0.0004973428,0.00009739638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014932898,0.00014577653,0.00024532384,0.00015023266,0.00028210122,0.000039239232,0.00020905709,0.00008129445,0.000005281366],"category_scores_gemma":[0.004030501,0.00008799724,0.000019546358,0.0004562695,0.00012781937,0.000068568246,0.00025824492,0.00022893738,0.0000012629612],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087060145,0.0015351513,0.9223752,0.0006970064,0.00002673316,0.000008555601,0.011849161,0.000038079106,0.0000031727222,0.00011658722,0.0000899593,0.062389802],"study_design_scores_gemma":[0.0051119253,0.0011317766,0.98706114,0.00093611656,0.00002304143,7.7617784e-7,0.0046072947,0.00039025518,0.00040600693,0.00019762684,0.00005135262,0.00008271059],"about_ca_topic_score_codex":0.00015837526,"about_ca_topic_score_gemma":0.0003646352,"teacher_disagreement_score":0.12732294,"about_ca_system_score_codex":0.00008077819,"about_ca_system_score_gemma":0.00024089056,"threshold_uncertainty_score":0.48251775},"labels":[],"label_agreement":null},{"id":"W3181971677","doi":"10.1186/s41512-021-00102-w","title":"A relationship between the incremental values of area under the ROC curve and of area under the precision-recall curve","year":2021,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; St. Jude Children's Research Hospital","keywords":"Brier score; Receiver operating characteristic; Range (aeronautics); Statistics; Area under the curve; Mathematics; Area under curve; Recall; Value (mathematics); Computer science; Econometrics; Medicine; Internal medicine; Psychology; Cognitive psychology","score_opus":0.3304354519580382,"score_gpt":0.438720882686613,"score_spread":0.10828543072857483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181971677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96941143,0.013373818,0.00014442489,0.014552321,0.000052560987,0.0015591674,0.00008127863,0.000010218444,0.00081475644],"genre_scores_gemma":[0.99690807,0.0021715201,0.00007626836,0.00021631124,0.00009500958,0.00026647997,0.00008258201,0.000023051824,0.0001606831],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99661666,0.0010112026,0.0005106793,0.00039983503,0.0010710679,0.0003905376],"domain_scores_gemma":[0.9090139,0.08956664,0.00012787177,0.0005998204,0.00054393086,0.00014780485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002680838,0.00020492637,0.00040360613,0.00010297624,0.0005043878,0.00008861746,0.00022490602,0.000121800345,0.00013878927],"category_scores_gemma":[0.013147063,0.00009446273,0.000113403585,0.0006062879,0.0010383292,0.00006617494,0.00034962772,0.0005581399,0.000009594147],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000574125,0.00036344328,0.9890716,0.00008707849,0.00027098105,0.000019402285,0.00093314674,0.000012894808,0.00001980133,0.0038214987,0.0025668603,0.0027758537],"study_design_scores_gemma":[0.0010271383,0.00054325635,0.9750472,0.000560607,0.00043208012,0.000037781152,0.0055041895,0.00010522115,0.00092687417,0.015484697,0.00023849875,0.00009251248],"about_ca_topic_score_codex":0.00040007947,"about_ca_topic_score_gemma":0.000107511456,"teacher_disagreement_score":0.08855544,"about_ca_system_score_codex":0.00005157146,"about_ca_system_score_gemma":0.00028694858,"threshold_uncertainty_score":0.99516565},"labels":[],"label_agreement":null},{"id":"W4200316566","doi":"10.1186/s41512-021-00109-3","title":"Knowledge translation of prediction rules: methods to help health professionals understand their trade-offs","year":2021,"lang":"en","type":"letter","venue":"Diagnostic and Prognostic Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Computer science; Translation (biology); Knowledge translation; Health professionals; Knowledge management; Process management; Data science; Health care; Business; Political science; Chemistry","score_opus":0.2502209112555136,"score_gpt":0.48283624440675066,"score_spread":0.23261533315123706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200316566","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037371067,0.0232829,0.26383308,0.7073219,0.0008899783,0.003305801,0.00027313532,0.00013670069,0.0005828439],"genre_scores_gemma":[0.06520795,0.013289198,0.5478793,0.34958628,0.010833245,0.0041551054,0.005297774,0.0006626725,0.003088513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867887,0.008339201,0.0010376154,0.0013271711,0.0013672119,0.0011400827],"domain_scores_gemma":[0.9485997,0.04913355,0.0002707771,0.0009821992,0.0006064985,0.00040726428],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0075783418,0.00043903672,0.0008942259,0.00086665596,0.0005813585,0.0002549475,0.0010815497,0.00075240067,0.000046607212],"category_scores_gemma":[0.010289743,0.00037482756,0.00014047649,0.001490642,0.00023518685,0.00020575043,0.0005002693,0.0037809033,0.000017776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001678626,0.0002104544,0.0029454126,0.0056379824,0.0000954583,0.00009288838,0.020142656,0.000016712824,0.000011364358,0.002050326,0.5359483,0.43283165],"study_design_scores_gemma":[0.0012742201,0.0037268773,0.025635403,0.014407407,0.000066078785,0.00016232887,0.00296626,0.024471117,0.0002586113,0.01750159,0.9082876,0.0012425076],"about_ca_topic_score_codex":0.00019868393,"about_ca_topic_score_gemma":0.00002895956,"teacher_disagreement_score":0.43158916,"about_ca_system_score_codex":0.00023203192,"about_ca_system_score_gemma":0.0022921367,"threshold_uncertainty_score":0.99987036},"labels":[],"label_agreement":null},{"id":"W4205154061","doi":"10.1186/s41512-021-00114-6","title":"Graphical calibration curves and the integrated calibration index (ICI) for competing risk models","year":2022,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Patient-Centered Outcomes Research Institute; Heart and Stroke Foundation of Canada","keywords":"Calibration; Statistics; Hazard; Monte Carlo method; Regression analysis; Proportional hazards model; Outcome (game theory); Range (aeronautics); Computer science; Econometrics; Data mining; Mathematics; Engineering","score_opus":0.149392363648987,"score_gpt":0.38683802710269627,"score_spread":0.23744566345370927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205154061","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.939727,0.020784596,0.008529463,0.023338318,0.00012460125,0.0069379434,0.00021638258,0.00007894756,0.00026271705],"genre_scores_gemma":[0.9882761,0.0068927035,0.00020129462,0.0006836727,0.00008342843,0.003461636,0.0003360551,0.000025883088,0.000039175666],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972289,0.0009791158,0.00034011158,0.00041532016,0.0006674689,0.00036904518],"domain_scores_gemma":[0.97780204,0.021497224,0.00008490435,0.00021932134,0.00022577014,0.00017073448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028104328,0.00016320463,0.00033202034,0.00017879358,0.0010819559,0.00011525052,0.000098341494,0.00006346886,0.0000723216],"category_scores_gemma":[0.008149048,0.000104318,0.000076387885,0.00048005712,0.00046548218,0.000113680035,0.0001831277,0.00060151477,7.232647e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015314717,0.000889671,0.93244785,0.000506426,0.00032180388,0.000059305563,0.00204546,0.00051103544,0.000019935353,0.035659026,0.008733356,0.017274635],"study_design_scores_gemma":[0.010630525,0.002465094,0.18415241,0.0007674068,0.00059169205,0.000121868616,0.004092158,0.7604558,0.00011043209,0.034384202,0.0019212334,0.0003071949],"about_ca_topic_score_codex":0.0007902958,"about_ca_topic_score_gemma":0.000041490566,"teacher_disagreement_score":0.75994474,"about_ca_system_score_codex":0.000046388206,"about_ca_system_score_gemma":0.0001534428,"threshold_uncertainty_score":0.97557604},"labels":[],"label_agreement":null},{"id":"W4280518513","doi":"10.1186/s41512-022-00123-z","title":"Quality and transparency of reporting derivation and validation prognostic studies of recurrent stroke in patients with TIA and minor stroke: a systematic review","year":2022,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"University of Ottawa","keywords":"Medicine; Stroke (engine); MEDLINE; Predictive modelling; Computer science; Machine learning","score_opus":0.2699960213258003,"score_gpt":0.4699169750905324,"score_spread":0.19992095376473207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280518513","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08908644,0.8993336,0.000015579726,0.000064199565,0.000027805323,0.011255927,0.00014961236,0.000010619331,0.000056227676],"genre_scores_gemma":[0.03210441,0.96541065,0.00026396368,0.000010391245,0.000014733357,0.0018008137,0.00032713034,0.000036268422,0.000031665775],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99339694,0.0010812707,0.0031519234,0.00074193743,0.0012460157,0.0003819271],"domain_scores_gemma":[0.983774,0.012664447,0.0024077734,0.0004547964,0.00054113334,0.00015787175],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005561141,0.00040865538,0.0033283385,0.000525092,0.00010487357,0.000028116012,0.0001168285,0.00012235525,0.000012381751],"category_scores_gemma":[0.061876204,0.0002920535,0.00008829815,0.00058063096,0.00044212266,0.00009485444,0.00031503613,0.0005874246,3.3025015e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046107114,0.00019174156,0.20679721,0.7212735,0.0004633222,0.00002477262,0.00034712223,3.26761e-8,3.4702526e-7,0.000021910137,0.00004141849,0.07079254],"study_design_scores_gemma":[0.0018808574,0.0025576449,0.11091117,0.8743243,0.007551732,0.000059200684,0.0009398681,0.0000070920487,0.0000032499954,0.000024190274,0.0013277342,0.00041294808],"about_ca_topic_score_codex":0.000051947,"about_ca_topic_score_gemma":0.000008479942,"teacher_disagreement_score":0.15305084,"about_ca_system_score_codex":0.000104544146,"about_ca_system_score_gemma":0.00021642634,"threshold_uncertainty_score":0.99995315},"labels":[],"label_agreement":null},{"id":"W4282960968","doi":"10.1186/s41512-022-00125-x","title":"Bayesian latent class analysis produced diagnostic accuracy estimates that were more interpretable than composite reference standards for extrapulmonary tuberculosis tests","year":2022,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canada Excellence Research Chairs, Government of Canada; Canadian Institutes of Health Research; Deutsches Zentrum für Infektionsforschung","keywords":"Gold standard (test); Extrapulmonary tuberculosis; Latent class model; Bayesian probability; Statistics; Medicine; Tuberculosis; Mycobacterium tuberculosis; Mathematics; Pathology","score_opus":0.07682152450935713,"score_gpt":0.4131796994782631,"score_spread":0.33635817496890597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282960968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599269,0.010101722,0.0013902622,0.019695431,0.00020275121,0.00617735,0.0015712259,0.00019489038,0.00073948456],"genre_scores_gemma":[0.9871824,0.0036144115,0.0010283991,0.00051641924,0.00015558516,0.005348943,0.0017945399,0.00009370906,0.00026563328],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9918893,0.0012907109,0.0008707288,0.0016091183,0.0022976547,0.002042501],"domain_scores_gemma":[0.92059726,0.075794846,0.00020136246,0.0011391252,0.0011575319,0.0011098969],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.005771779,0.0005605622,0.0013933099,0.0012626755,0.001512001,0.00023071624,0.0006574106,0.00023368423,0.00073918607],"category_scores_gemma":[0.07405265,0.00047200036,0.00039420062,0.0018417371,0.0007463112,0.00026919783,0.0010435915,0.0018148336,0.000020970969],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013229897,0.00091022486,0.9666258,0.0007826756,0.0015958291,0.0005568111,0.0005154262,0.00052995613,0.0006900594,0.00038242375,0.013035717,0.013052057],"study_design_scores_gemma":[0.0019487549,0.003616944,0.94129443,0.00053830474,0.0018554513,0.00031658594,0.0009752569,0.03732749,0.0007334374,0.0018464468,0.008897893,0.0006489952],"about_ca_topic_score_codex":0.0012394629,"about_ca_topic_score_gemma":0.00011823896,"teacher_disagreement_score":0.07450413,"about_ca_system_score_codex":0.0005069488,"about_ca_system_score_gemma":0.0008095058,"threshold_uncertainty_score":0.99978787},"labels":[],"label_agreement":null},{"id":"W4285391305","doi":"10.1186/s41512-022-00127-9","title":"Protocol for a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence for grading of ophthalmology imaging modalities","year":2022,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Queen's University; Public Health Ontario; University of Toronto","funders":"","keywords":"Medical physics; Modalities; Grading (engineering); MEDLINE; Receiver operating characteristic; Cochrane Library; Meta-analysis; Systematic review; Medicine; Artificial intelligence; Protocol (science); Diagnostic accuracy; Computer science; Machine learning; Pathology; Radiology","score_opus":0.4799289046005643,"score_gpt":0.5549632884269203,"score_spread":0.07503438382635602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285391305","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000842079,0.8080344,0.00050136144,0.0002964491,0.0000123081245,0.1906677,0.00044096267,0.0000058256146,0.000032529173],"genre_scores_gemma":[0.00096439413,0.5709543,0.00035102695,0.000020746138,0.000021155793,0.42746556,0.00008523942,0.000044610828,0.00009292331],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99388313,0.0016690122,0.002504704,0.0006497497,0.00082181464,0.00047158392],"domain_scores_gemma":[0.8608881,0.13594773,0.001491351,0.00077266747,0.00077920826,0.0001209162],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062192613,0.00043137535,0.007868086,0.0009534189,0.00022873488,0.000040706895,0.00051134947,0.00010665262,0.0001731247],"category_scores_gemma":[0.15200123,0.0002451841,0.0025380524,0.0019132609,0.00084060454,0.000055461413,0.00035137348,0.00047591404,3.600214e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025201567,0.00020126178,0.00019827318,0.9553683,0.033170957,0.000017579589,0.00013171716,0.0000028130883,2.9992563e-7,0.0011011097,0.000054534852,0.009727954],"study_design_scores_gemma":[0.00014596918,0.00052791846,0.000020068373,0.12146979,0.872207,0.00024175344,0.00040724687,0.00070534425,0.000019328796,0.0020004187,0.0019877525,0.0002673946],"about_ca_topic_score_codex":0.00012380368,"about_ca_topic_score_gemma":0.0000013960118,"teacher_disagreement_score":0.83903605,"about_ca_system_score_codex":0.00004571992,"about_ca_system_score_gemma":0.000453506,"threshold_uncertainty_score":0.99983186},"labels":[],"label_agreement":null},{"id":"W4289687832","doi":"10.1186/s41512-022-00128-8","title":"Development and validation of prognostic models for anal cancer outcomes using distributed learning: protocol for the international multi-centre atomCAT2 study","year":2022,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Colorectal and Anal Carcinomas","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Hanarth Fonds; Yorkshire Cancer Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Academy of Medical Sciences; National Institute for Health and Care Research; Cancer Research UK","keywords":"Anal cancer; Medicine; Protocol (science); Chemoradiotherapy; Cohort; Cancer; Medical physics; Oncology; Internal medicine; Pathology; Alternative medicine","score_opus":0.26864124848753024,"score_gpt":0.46066825434162423,"score_spread":0.192027005854094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289687832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8966342,0.00011014934,0.0031832464,0.0008585232,0.00004975302,0.09903071,0.00011025603,0.000015855772,0.0000072741536],"genre_scores_gemma":[0.8248593,0.0000050306403,0.0008230872,0.00001699158,0.000043854183,0.17402765,0.000089037356,0.000016468262,0.00011857142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99822164,0.0001333923,0.00034656064,0.0003380318,0.00064527,0.0003151107],"domain_scores_gemma":[0.99337107,0.005752738,0.00010587308,0.00009891371,0.0005659456,0.00010544504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001298939,0.00014020313,0.0002539443,0.00014220165,0.0006775318,0.00005840058,0.00014043461,0.000031729294,0.00003855804],"category_scores_gemma":[0.004498575,0.0000964288,0.00005510207,0.00024112078,0.0001176721,0.00005897483,0.00029574896,0.0002691108,2.0843817e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007384362,0.0009701526,0.9867564,0.0003213453,0.00021174405,0.000010961394,0.0021228073,0.001128757,0.00007445303,0.0001621804,0.00011332496,0.0073894784],"study_design_scores_gemma":[0.010265696,0.0022709593,0.6847041,0.0002746289,0.00034515082,0.000023877301,0.012818985,0.28258133,0.0007631777,0.0003611314,0.0053207334,0.00027023384],"about_ca_topic_score_codex":0.00013893766,"about_ca_topic_score_gemma":0.0000418801,"teacher_disagreement_score":0.30205226,"about_ca_system_score_codex":0.00011433341,"about_ca_system_score_gemma":0.000384886,"threshold_uncertainty_score":0.53855395},"labels":[],"label_agreement":null},{"id":"W4320481764","doi":"10.1186/s41512-023-00140-6","title":"IMplementing Predictive Analytics towards efficient COPD Treatments (IMPACT): protocol for a stepped-wedge cluster randomized impact study","year":2023,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Paul's Hospital; Centre for Advancing Health Outcomes; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Pulmonologists; Medicine; COPD; Randomized controlled trial; Exacerbation; Clinical decision support system; Psychological intervention; Physical therapy; Medical prescription; Intensive care medicine; Decision support system; Nursing; Internal medicine; Data mining","score_opus":0.08862259929874784,"score_gpt":0.47419502302094113,"score_spread":0.3855724237221933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320481764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60876334,0.00013933486,0.0003892036,0.00036571152,0.000053363154,0.38887358,0.00054536236,0.00014244787,0.00072766596],"genre_scores_gemma":[0.6355893,0.00002969641,0.00008242018,0.000016508191,0.00023725914,0.36296245,0.0002679244,0.00008780907,0.0007266131],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9912684,0.0015572194,0.001001144,0.0012257125,0.002357195,0.0025903417],"domain_scores_gemma":[0.97521657,0.02120594,0.00018911937,0.00074869307,0.0015141658,0.0011255415],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008316698,0.0006057206,0.0013918024,0.0011857104,0.00085995725,0.0003051793,0.00034781417,0.00018187017,0.00045830454],"category_scores_gemma":[0.026957966,0.00041371677,0.0005783598,0.0019877497,0.0007891667,0.00014617559,0.00086386496,0.0007320329,0.000133478],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14632761,0.0064802556,0.7945413,0.002620121,0.0042896396,0.0012503355,0.003212405,0.0005839718,0.00003733204,0.000099963356,0.011105934,0.029451115],"study_design_scores_gemma":[0.23720138,0.0052520717,0.6622721,0.00060623727,0.000839535,0.00004393714,0.0031449418,0.0893808,0.00004308956,0.00049282686,0.00034607766,0.00037700494],"about_ca_topic_score_codex":0.0007125187,"about_ca_topic_score_gemma":0.000022723709,"teacher_disagreement_score":0.13226922,"about_ca_system_score_codex":0.001007878,"about_ca_system_score_gemma":0.0018856578,"threshold_uncertainty_score":0.99983144},"labels":[],"label_agreement":null},{"id":"W4376602191","doi":"10.1186/s41512-023-00147-z","title":"Methodological concerns about “concordance-statistic for benefit” as a measure of discrimination in predicting treatment benefit","year":2023,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Concordance; Statistic; Metric (unit); Discriminative model; Counterfactual thinking; Econometrics; Computer science; Statistics; Categorical variable; Cut-point; Machine learning; Mathematics; Psychology; Medicine; Economics; Social psychology; Operations management","score_opus":0.7855151177990123,"score_gpt":0.5831396648779538,"score_spread":0.20237545292105852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376602191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9758888,0.004892482,0.0048136427,0.008025375,0.00028666033,0.0036819207,0.0010491185,0.000058432677,0.0013036092],"genre_scores_gemma":[0.99173087,0.002084567,0.0028626623,0.00019372438,0.00022008894,0.0022602475,0.00019294416,0.00003389777,0.00042096965],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954098,0.0005999224,0.0023433804,0.0007039809,0.00023977821,0.0007031245],"domain_scores_gemma":[0.9248229,0.07383874,0.0006025193,0.0002934129,0.00024417954,0.00019821663],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024618892,0.00019798725,0.0009807898,0.00062673097,0.00025001555,0.000076302815,0.0002156378,0.00017544793,0.000103667335],"category_scores_gemma":[0.13371868,0.00020642712,0.00009007525,0.0005815709,0.00023182316,0.00019107244,0.000082450526,0.00020657587,0.00018898436],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000870861,0.00018062978,0.6755842,0.00092022,0.000069271984,0.000010407479,0.00534664,0.00043450965,0.000005112083,0.30513313,0.00091317453,0.011315583],"study_design_scores_gemma":[0.0022534488,0.0014914005,0.6960245,0.0008035965,0.000024182145,0.0000055364894,0.0045353156,0.021849476,0.000034326582,0.27006987,0.0026012596,0.00030712533],"about_ca_topic_score_codex":0.0029332459,"about_ca_topic_score_gemma":0.0006322453,"teacher_disagreement_score":0.1090998,"about_ca_system_score_codex":0.0003643316,"about_ca_system_score_gemma":0.00019165798,"threshold_uncertainty_score":0.87357837},"labels":[],"label_agreement":null},{"id":"W4385239524","doi":"10.1186/s41512-023-00151-3","title":"Field evaluations of four SARS-CoV-2 rapid antigen tests during SARS-CoV-2 Delta variant wave in South Africa","year":2023,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada","funders":"European and Developing Countries Clinical Trials Partnership; Medical Research Council; Direktion für Entwicklung und Zusammenarbeit; Department of Science and Innovation, South Africa","keywords":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Coronavirus disease 2019 (COVID-19); Antigen; Virology; Diagnostic test; 2019-20 coronavirus outbreak; Immunology; Internal medicine; Veterinary medicine","score_opus":0.24660836909298858,"score_gpt":0.4193529557768007,"score_spread":0.17274458668381212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385239524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99400693,0.00084498624,0.00017245741,0.0007375694,0.00015552937,0.0016363773,0.000031719046,0.00015567233,0.0022587725],"genre_scores_gemma":[0.9984815,0.00026247173,0.00046645908,0.00021000227,0.00016404757,0.00028635256,0.000023551445,0.000054663826,0.00005092604],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99611735,0.00043867997,0.00072226656,0.00066935504,0.0010859229,0.00096644636],"domain_scores_gemma":[0.985498,0.013137442,0.00013083727,0.0005190975,0.0006193987,0.00009521253],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027607186,0.00027605658,0.0005396021,0.0012405341,0.0003121329,0.00008647017,0.00019835077,0.0002325747,0.000025759906],"category_scores_gemma":[0.06029851,0.00025410767,0.00011091763,0.0025992407,0.0002460257,0.0001251899,0.0002822321,0.00081830006,0.00014467417],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004568584,0.0005387537,0.29042467,0.00094841036,0.000197847,0.003276941,0.009196999,0.000006134105,0.66991943,0.0002436714,0.0022672976,0.022522993],"study_design_scores_gemma":[0.003414826,0.0014314682,0.3297207,0.0020257905,0.00012121835,0.00031828714,0.0011572542,0.009266489,0.6496816,0.0017753674,0.0006735667,0.00041342253],"about_ca_topic_score_codex":0.0003772549,"about_ca_topic_score_gemma":0.000111369984,"teacher_disagreement_score":0.05753779,"about_ca_system_score_codex":0.000073447074,"about_ca_system_score_gemma":0.0003873375,"threshold_uncertainty_score":0.9999911},"labels":[],"label_agreement":null},{"id":"W4392729978","doi":"10.1186/s41512-024-00166-4","title":"Risk prediction models for lung cancer in people who have never smoked: a protocol of a systematic review","year":2024,"lang":"en","type":"review","venue":"Diagnostic and Prognostic Research","topic":"Lung Cancer Diagnosis and Treatment","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Provincial Health Services Authority; Brock University; University of British Columbia","funders":"","keywords":"Lung cancer; Checklist; Medicine; Data extraction; MEDLINE; Protocol (science); Critical appraisal; Systematic review; Population; Scopus; Predictive modelling; Lung cancer screening; Family medicine; Environmental health; Alternative medicine; Internal medicine; Pathology; Computer science; Machine learning; Psychology","score_opus":0.11762400471627132,"score_gpt":0.48730516250469363,"score_spread":0.3696811577884223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392729978","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003153713,0.68574417,0.000042749103,0.00016869867,0.000058406436,0.31290823,0.00093583524,0.00002297217,0.00011575929],"genre_scores_gemma":[0.000026448708,0.5351216,0.000030538504,0.000020547639,0.00009041427,0.46431768,0.00008979006,0.00006590086,0.0002370729],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9947517,0.0007558309,0.001798816,0.0009824537,0.0010157118,0.0006955038],"domain_scores_gemma":[0.9873974,0.010552989,0.000462556,0.00070748,0.0006050818,0.00027453972],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002925276,0.00058236654,0.004406508,0.00065983937,0.000107436594,0.0000811133,0.00023229451,0.00036869734,0.000053577736],"category_scores_gemma":[0.008195894,0.00036618824,0.00058450334,0.0009921832,0.00014373244,0.0001349506,0.00018453995,0.0009518871,0.00000790167],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041153293,0.00035297868,0.0036229328,0.95334816,0.0009579047,0.00006337694,0.00025584112,0.000004352748,3.0872604e-9,0.00019814324,0.007965857,0.033189274],"study_design_scores_gemma":[0.0011816702,0.0007578357,0.00022434491,0.9591668,0.020081215,0.00004392261,0.00003904432,0.003838339,2.6955868e-7,0.00023218518,0.014178181,0.00025618568],"about_ca_topic_score_codex":0.0008523487,"about_ca_topic_score_gemma":0.00015237564,"teacher_disagreement_score":0.15140945,"about_ca_system_score_codex":0.0008299596,"about_ca_system_score_gemma":0.0016582067,"threshold_uncertainty_score":0.999879},"labels":[],"label_agreement":null},{"id":"W4392735078","doi":"10.1186/s41512-024-00165-5","title":"A study protocol for a predictive model to assess population-based avoidable hospitalization risk: Avoidable Hospitalization Population Risk Prediction Tool (AvHPoRT)","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Bruyère; University of Ottawa; Ottawa Hospital; Statistics Canada; Public Health Ontario; Trillium Health Centre; University of Toronto","funders":"Canadian Institutes of Health Research; Institute of Population and Public Health; University of Toronto; Canada Research Chairs; UK Research and Innovation","keywords":"Medicine; Population; Concordance; Statistic; Health care; Cohort; Socioeconomic status; Environmental health; Statistics","score_opus":0.15294429867885506,"score_gpt":0.5127437944701195,"score_spread":0.35979949579126447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392735078","genre_codex":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3542819,0.00011681294,0.17292842,0.0009966417,0.0006651722,0.46856272,0.0012176504,0.00063092547,0.0005997579],"genre_scores_gemma":[0.5442077,0.00003676501,0.001168851,0.000203388,0.0003729934,0.4527104,0.00075370155,0.00008509829,0.00046111477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99298877,0.0019800237,0.001375318,0.0011576269,0.0013311963,0.0011670828],"domain_scores_gemma":[0.9827046,0.014610302,0.00033380915,0.00054057443,0.0014142164,0.0003964941],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.006728022,0.00039947827,0.0005462955,0.0008358072,0.003053951,0.0002907181,0.0002526078,0.00041511684,0.000115106326],"category_scores_gemma":[0.02426441,0.0003514281,0.00010858096,0.0014167285,0.000055578374,0.000744627,0.00019325763,0.0011339477,0.00006383521],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043886757,0.00046282483,0.95786005,0.0020584834,0.00007365784,0.000009753649,0.0026586913,0.013994659,0.0000016737844,0.0010542367,0.01799659,0.0033905045],"study_design_scores_gemma":[0.0020245716,0.002266038,0.72708607,0.00090511073,0.00017280367,6.148261e-7,0.000947697,0.257552,0.000004203092,0.0069349995,0.0018060558,0.00029982446],"about_ca_topic_score_codex":0.003839973,"about_ca_topic_score_gemma":0.0008223341,"teacher_disagreement_score":0.24355733,"about_ca_system_score_codex":0.0012224165,"about_ca_system_score_gemma":0.0021826257,"threshold_uncertainty_score":0.9998938},"labels":[],"label_agreement":null},{"id":"W4394739940","doi":"10.1186/s41512-024-00168-2","title":"Study protocol for the development and validation of a clinical prediction tool to estimate the risk of 1-year mortality among hospitalized patients with dementia","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University Health Network; University of Toronto; Bruyère; Ottawa Hospital; Sinai Health System; Sunnybrook Health Science Centre; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Dementia; Medicine; Logistic regression; Psychological intervention; Cohort; Health care; Population; Protocol (science); Cohort study; Emergency medicine; Intensive care medicine; Internal medicine; Disease; Psychiatry; Alternative medicine","score_opus":0.1927233143690585,"score_gpt":0.5147470811701601,"score_spread":0.32202376680110156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394739940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85291326,0.000063917854,0.00022806558,0.00012804483,0.000034519355,0.14656173,0.00003465717,0.000012475113,0.00002329752],"genre_scores_gemma":[0.81855744,0.000021326696,0.0006188311,0.0000049068494,0.000029165512,0.1807316,0.000017859182,0.000013273175,0.00000562505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99791783,0.00026012663,0.0005964205,0.0003376833,0.0006842751,0.00020364519],"domain_scores_gemma":[0.99040055,0.008723977,0.00010285954,0.00025897406,0.0004200674,0.00009356307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033388347,0.0001266267,0.00028357757,0.00008028785,0.00019606718,0.00006753284,0.00007766474,0.000046314137,0.000013658971],"category_scores_gemma":[0.0065232865,0.00005744915,0.000048019596,0.0002660992,0.0002307242,0.000056427834,0.000096370095,0.00016900508,0.0000015665742],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042790716,0.0013138824,0.978939,0.00033627337,0.0009496606,0.000004330996,0.0012466302,0.0000104844685,2.4579938e-7,0.000070656555,0.00023960248,0.016461326],"study_design_scores_gemma":[0.003480056,0.0045041186,0.98927,0.0006555837,0.0008287724,5.272773e-7,0.00038580963,0.00029302237,0.00019263428,0.000083984385,0.0002472208,0.000058276084],"about_ca_topic_score_codex":0.00011045633,"about_ca_topic_score_gemma":0.00003206224,"teacher_disagreement_score":0.034355868,"about_ca_system_score_codex":0.000017625875,"about_ca_system_score_gemma":0.00015477277,"threshold_uncertainty_score":0.7809454},"labels":[],"label_agreement":null},{"id":"W4400900443","doi":"10.1186/s41512-024-00176-2","title":"Evaluating diagnostic accuracy of an RT-PCR test for the detection of SARS-CoV-2 in saliva","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada","funders":"European and Developing Countries Clinical Trials Partnership; Department of Science and Innovation, South Africa","keywords":"Saliva; Medicine; Coronavirus disease 2019 (COVID-19); Logistic regression; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Internal medicine; Gastroenterology; Disease; Infectious disease (medical specialty)","score_opus":0.26334656890165264,"score_gpt":0.4953956206165163,"score_spread":0.23204905171486367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400900443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879799,0.0067474665,0.0013651467,0.00042585362,0.00022787107,0.0029364433,0.000033399854,0.00007411705,0.00020979135],"genre_scores_gemma":[0.997884,0.0003449926,0.00062866625,0.00009934496,0.0002445963,0.00072018406,0.000012253856,0.000051995154,0.000014010771],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99711746,0.0003289474,0.0007169542,0.0005205587,0.0007812251,0.00053486763],"domain_scores_gemma":[0.81544834,0.18328601,0.000121260884,0.00040985367,0.0006657274,0.00006881533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00437201,0.00021208072,0.00041136116,0.00057161535,0.00020358244,0.000098820754,0.00019526506,0.0001538224,0.000010100269],"category_scores_gemma":[0.2759849,0.0001553682,0.000105638224,0.0013172902,0.00041551466,0.0001846315,0.00011173125,0.00065388676,0.000012498357],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023402063,0.00047076846,0.051235415,0.002028172,0.0000887018,0.00010570365,0.0013246561,0.000014668263,0.5733832,0.00027786178,0.00009279777,0.370744],"study_design_scores_gemma":[0.0019624257,0.0046183597,0.101893954,0.0034522552,0.0002887103,0.00021745276,0.0010589258,0.09455162,0.7883612,0.0026618845,0.00069231854,0.00024088779],"about_ca_topic_score_codex":0.0008552893,"about_ca_topic_score_gemma":0.00021842911,"teacher_disagreement_score":0.37050313,"about_ca_system_score_codex":0.00007118508,"about_ca_system_score_gemma":0.00035884208,"threshold_uncertainty_score":0.7301138},"labels":[],"label_agreement":null},{"id":"W4404070406","doi":"10.1186/s41512-024-00179-z","title":"The relative data hungriness of unpenalized and penalized logistic regression and ensemble-based machine learning methods: the case of calibration","year":2024,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Sunnybrook Hospital; University of Toronto; Vector Institute; Sunnybrook Health Science Centre","funders":"","keywords":"Calibration; Logistic regression; Ensemble learning; Artificial intelligence; Computer science; Machine learning; Regression; Statistics; Pattern recognition (psychology); Mathematics","score_opus":0.43834432732399464,"score_gpt":0.5765325733102753,"score_spread":0.13818824598628066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404070406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025551097,0.01799535,0.9540021,0.0010363809,0.000056496952,0.0010824692,0.00012204426,0.000026069052,0.0001280126],"genre_scores_gemma":[0.79976916,0.0025216069,0.19738254,0.000009291917,0.000030779465,0.00009563758,0.000033485652,0.000030708903,0.0001267709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99524486,0.0031755543,0.00050338043,0.00044722552,0.00033584944,0.00029315066],"domain_scores_gemma":[0.79535574,0.20384143,0.00011703454,0.00037787884,0.00021450291,0.000093405346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008318507,0.00017481456,0.0003713783,0.000101493526,0.0005058996,0.0001290824,0.0002125745,0.000085896674,0.000014374254],"category_scores_gemma":[0.11619404,0.000086489235,0.000027941134,0.0003444967,0.0011704422,0.00015181335,0.00045696873,0.00058935565,3.3320913e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038490593,0.000082932704,0.0009690537,0.0020172165,0.00013649765,0.00049787364,0.0012250757,0.000030368597,0.0005797398,0.7499175,0.00021484087,0.24394402],"study_design_scores_gemma":[0.00059028127,0.0002902942,0.00021742331,0.0009774286,0.00020837976,0.00016708438,0.0004839211,0.3689601,0.00052154926,0.6269324,0.00053006294,0.000121085825],"about_ca_topic_score_codex":0.00024662935,"about_ca_topic_score_gemma":0.00005414904,"teacher_disagreement_score":0.7742181,"about_ca_system_score_codex":0.000010966035,"about_ca_system_score_gemma":0.00011320558,"threshold_uncertainty_score":0.8912506},"labels":[],"label_agreement":null},{"id":"W4408093082","doi":"10.1186/s41512-025-00185-9","title":"Development and internal validation of a new life expectancy estimator for multimorbid older adults","year":2025,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Horizon 2020; Staatssekretariat für Bildung, Forschung und Innovation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Medicine; Life expectancy; Body mass index; Polypharmacy; Activities of daily living; Gerontology; Geriatrics; Internal medicine; Physical therapy; Population","score_opus":0.08580600016621509,"score_gpt":0.42078043171093243,"score_spread":0.33497443154471734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408093082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98425496,0.003990727,0.0058249813,0.0012225219,0.00009254131,0.0025332305,0.000008165654,0.000031969506,0.002040906],"genre_scores_gemma":[0.9912904,0.0002702033,0.0069854576,0.000053644504,0.00006588769,0.0003880752,0.000051154224,0.000013237784,0.00088195567],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986839,0.000038166338,0.00031745873,0.00033060028,0.00033573052,0.00029413318],"domain_scores_gemma":[0.99697447,0.0023531136,0.000047796475,0.00016287137,0.0002365494,0.00022517759],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004240519,0.00012659683,0.00024207005,0.00026503875,0.00010919115,0.00006054133,0.0000825419,0.00005465598,0.00008125389],"category_scores_gemma":[0.009294309,0.00011034636,0.00003106805,0.00021924586,0.00014707861,0.00006887977,0.00014500847,0.00012613091,0.000004764458],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001971436,0.0013009332,0.4802188,0.013604269,0.0007696453,0.00011727288,0.0074710175,0.000008737286,0.00014665563,0.019759491,0.046637747,0.42799398],"study_design_scores_gemma":[0.011750763,0.00067424495,0.9548724,0.009241422,0.0003139895,0.000009858846,0.006357444,0.003277731,0.004960069,0.0022441826,0.0060044937,0.0002933813],"about_ca_topic_score_codex":0.000095739364,"about_ca_topic_score_gemma":0.0000070215774,"teacher_disagreement_score":0.4746536,"about_ca_system_score_codex":0.000041489453,"about_ca_system_score_gemma":0.0007104799,"threshold_uncertainty_score":0.99905086},"labels":[],"label_agreement":null},{"id":"W4416142124","doi":"10.1186/s41512-025-00208-5","title":"Performance of clinical prediction models for chronic kidney disease among people with diabetes: external validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN)","year":2025,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Chronic Kidney Disease and Diabetes","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Alberta Innovates; Alberta Innovates - Health Solutions","keywords":"Kidney disease; Primary care; Predictive modelling; Risk assessment; Disease; MEDLINE","score_opus":0.04343195241264646,"score_gpt":0.3448820834389103,"score_spread":0.30145013102626383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416142124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99063385,0.0048152898,0.0004918184,0.0005786093,0.00016385365,0.0025387951,0.00021838628,0.000023889446,0.00053553336],"genre_scores_gemma":[0.9973004,0.0006602721,0.00015891409,0.00024565164,0.00048506787,0.00043784003,0.0006167136,0.000025776297,0.00006937989],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975477,0.0002574439,0.0004970829,0.0004471777,0.0005439048,0.0007067204],"domain_scores_gemma":[0.99382603,0.004055875,0.000108457156,0.0004102209,0.0008099224,0.0007894996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015814825,0.0001833461,0.0004114987,0.00016630413,0.00058741646,0.00008318082,0.00015982088,0.00011716227,0.000016697895],"category_scores_gemma":[0.004292352,0.00012979996,0.000102650236,0.0005404438,0.00049747375,0.00016372709,0.000087874745,0.0003630556,0.0000012204998],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029830929,0.000097325115,0.9896232,0.0027912077,0.0001057725,0.0000052771375,0.00009715362,0.0030360464,0.000005372278,0.0001212568,0.0014093965,0.0024096898],"study_design_scores_gemma":[0.0016661127,0.00038448244,0.7879158,0.00290048,0.00026398172,7.198403e-7,0.000057648103,0.2063202,0.000025023066,0.00020537208,0.00016243121,0.00009774164],"about_ca_topic_score_codex":0.0019175188,"about_ca_topic_score_gemma":0.0017670959,"teacher_disagreement_score":0.20328416,"about_ca_system_score_codex":0.00027684896,"about_ca_system_score_gemma":0.0071643814,"threshold_uncertainty_score":0.99846405},"labels":[],"label_agreement":null},{"id":"W4417399303","doi":"10.1186/s41512-025-00204-9","title":"A decomposition of Fisher’s information to inform sample size for developing or updating fair and precise clinical prediction models — part 2: time-to-event outcomes","year":2025,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Birmingham Biomedical Research Centre; Engineering and Physical Sciences Research Council; Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Reliability (semiconductor); Sample size determination; Predictive modelling; Sample (material); Decomposition; Data modeling","score_opus":0.10097981148333827,"score_gpt":0.4622922384802612,"score_spread":0.3613124269969229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417399303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16465135,0.000049104958,0.8192871,0.011665204,0.00021441605,0.0036112634,0.000086041815,0.0000944493,0.00034102326],"genre_scores_gemma":[0.7722178,0.000106748994,0.22516854,0.0010519793,0.00006000304,0.001142209,0.000062516585,0.000011804883,0.00017835721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99772006,0.00025431177,0.00083125435,0.00034068245,0.0004573088,0.00039635156],"domain_scores_gemma":[0.95422477,0.044480346,0.000116113566,0.00028704092,0.0006908431,0.00020089517],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033032317,0.00013635155,0.00029675465,0.000310984,0.00036717384,0.00023718395,0.00034240293,0.00010931311,0.000012004488],"category_scores_gemma":[0.07388275,0.00011374338,0.000038088994,0.0007253413,0.00005648577,0.00067052996,0.0005718916,0.00026242292,0.000011963725],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002267998,0.0000827577,0.31540388,0.0010636672,0.0000522538,0.000001655944,0.002430086,0.0019555325,0.0000023159016,0.013335322,0.0053405934,0.6601051],"study_design_scores_gemma":[0.0011030391,0.0016618544,0.52509797,0.0016096953,0.000022466927,0.000005278265,0.00021935548,0.44625464,0.000052059284,0.01475611,0.00897053,0.00024701827],"about_ca_topic_score_codex":0.00013739971,"about_ca_topic_score_gemma":0.000025643381,"teacher_disagreement_score":0.6598581,"about_ca_system_score_codex":0.00006868835,"about_ca_system_score_gemma":0.0004047374,"threshold_uncertainty_score":0.9339183},"labels":[],"label_agreement":null}]}