{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1016,"total_is_capped":false,"direct_labels_cover":5,"predictions_cover":1016,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2917548772c0","filters":{"topic":"COVID-19 diagnosis using AI"}},"results":[{"id":"W3105081694","doi":"10.1038/s41598-020-76550-z","title":"COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":3156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Coronavirus disease 2019 (COVID-19); Convolutional neural network; Computer science; Benchmark (surveying); Radiography; Audit; Pandemic; Artificial intelligence; Medicine; Radiology; Medical physics; Data mining; Pathology; Disease; Cartography; Business; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06991285969034737,"gpt":0.317833855583925,"spread":0.2479209958935776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001432576,0.0002533405,0.0005194636,0.0001599143,0.0004744568,0.0001297626,0.0001394491,0.0001341957,0.000333701],"category_scores_gemma":[0.01221177,0.0002448673,0.0002597516,0.0008283771,0.0005892143,0.0001673371,0.00008276131,0.0001629881,0.00001067811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003120662,"about_ca_system_score_gemma":0.001869411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004995331,"about_ca_topic_score_gemma":0.00009207246,"domain_scores_codex":[0.9966691,0.0001493431,0.0008546476,0.001160067,0.00071647,0.000450385],"domain_scores_gemma":[0.9958978,0.001492736,0.0006531684,0.0006780568,0.0004186394,0.0008596107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001555857,0.0003935799,0.01347527,0.0008496905,0.0002359941,0.002724016,0.001751173,0.2323333,0.3462557,0.00001327171,0.3981893,0.002222871],"study_design_scores_gemma":[0.005302519,0.001832606,0.01127677,0.0002952041,0.001384267,0.001265588,0.000759846,0.2145535,0.1715282,0.005896616,0.5847252,0.001179716],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2954336,0.002683031,0.6344771,0.05130516,0.01040938,0.00484457,0.0001487975,0.0006767882,0.00002148012],"genre_scores_gemma":[0.980938,0.00000656072,0.008958947,0.008787901,0.0006397071,0.0001681224,0.0003252874,0.00004125819,0.0001342255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6855044,"threshold_uncertainty_score":0.9985398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014561994","doi":"10.1016/j.chest.2020.04.003","title":"The Role of Chest Imaging in Patient Management During the COVID-19 Pandemic","year":2020,"lang":"en","type":"article","venue":"CHEST Journal","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1304,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Centers for Disease Control and Prevention; FibroGen; Roche; Agency for Healthcare Research and Quality; Boehringer Ingelheim","keywords":"Medicine; Context (archaeology); Pandemic; Intensive care medicine; Disease; Health care; Pulmonologists; Personal protective equipment; Chest radiograph; Disease management; Coronavirus disease 2019 (COVID-19); Emergency medicine; Medical emergency; Internal medicine; Lung; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.03023804280087848,"gpt":0.2995219860677469,"spread":0.2692839432668684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005809317,0.0001222978,0.0001817252,0.00007412109,0.0002600005,0.00005703031,0.000247581,0.00002704664,0.00004371932],"category_scores_gemma":[0.0005573659,0.00007239873,0.0001029982,0.0002548966,0.0001134794,0.00005702416,0.0001438678,0.000487052,0.00001018423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004441019,"about_ca_system_score_gemma":0.0001695373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003804821,"about_ca_topic_score_gemma":0.00001536556,"domain_scores_codex":[0.9986853,0.00009068578,0.0004175401,0.0001646092,0.0003684322,0.0002734214],"domain_scores_gemma":[0.9989627,0.0002973409,0.0002127828,0.0002318634,0.00004711523,0.0002481984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003219745,0.000171265,0.9235022,0.0005247328,0.0001044186,0.0006536354,0.00978898,0.0009943722,0.008764718,0.00008637279,0.003540201,0.05154715],"study_design_scores_gemma":[0.002590487,0.0001022822,0.3061425,0.0002925703,0.0001215586,0.0007450263,0.006723317,0.001112615,0.002962752,0.0004215126,0.6786206,0.0001647845],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8295884,0.002805211,0.0001284665,0.1665797,0.0001368164,0.0003522797,0.000001867796,0.00003621318,0.000370996],"genre_scores_gemma":[0.9812474,0.0008571649,0.0001344976,0.0174959,0.0002085247,0.00001446802,7.094045e-7,0.00001936258,0.00002197183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6750804,"threshold_uncertainty_score":0.2952335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4230649743","doi":"10.1148/radiol.2020201365","title":"The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society","year":2020,"lang":"en","type":"article","venue":"Radiology","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Context (archaeology); Intensive care medicine; Pandemic; Health care; Disease; Personal protective equipment; Disease management; Coronavirus disease 2019 (COVID-19); Emergency medicine; Internal medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.02903078362873905,"gpt":0.3078824804033156,"spread":0.2788516967745765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005585651,0.0001250056,0.0001996692,0.00001902585,0.000209285,0.00001222893,0.0002047777,0.00004029889,0.00004049107],"category_scores_gemma":[0.0005086796,0.00006520278,0.000104008,0.0001409408,0.0003304568,0.00001289053,0.0001916134,0.000243733,0.000006150657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003631159,"about_ca_system_score_gemma":0.0001518494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005406921,"about_ca_topic_score_gemma":0.00008986122,"domain_scores_codex":[0.9985837,0.0002631214,0.0004120602,0.0002747206,0.0002189597,0.0002473828],"domain_scores_gemma":[0.9972568,0.002159518,0.0001750724,0.0002875547,0.00004354368,0.00007753225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004458122,0.000160985,0.924082,0.0001145106,0.0003765398,0.00008527515,0.01890269,0.003934676,0.008524414,0.000904161,0.02848558,0.01398339],"study_design_scores_gemma":[0.003310334,0.00007790919,0.3239527,0.0000453906,0.0001105899,0.00005793171,0.009316278,0.01533785,0.0005231817,0.0004893101,0.6466386,0.000139928],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7306768,0.001418716,0.0001185095,0.2669386,0.00008071577,0.0006496935,0.00003476952,0.00003454632,0.00004769233],"genre_scores_gemma":[0.9526548,0.0003036232,0.00038798,0.04639516,0.0001040908,0.0001059804,0.00002046035,0.0000132134,0.00001471531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.618153,"threshold_uncertainty_score":0.2658892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3024801014","doi":"10.1109/access.2020.2994762","title":"CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":770,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Convolutional neural network; Deep learning; Computer science; Artificial intelligence; Classifier (UML); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Pattern recognition (psychology); Radiography; Machine learning; Outbreak; Medicine; Radiology; Virology; Infectious disease (medical specialty); Disease; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.3634355217624528,"gpt":0.4781321216466249,"spread":0.1146965998841722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003479347,0.0002189913,0.0003343615,0.0001389274,0.0002479909,0.0001749937,0.0005216,0.000153526,0.00008408848],"category_scores_gemma":[0.001670537,0.0002239935,0.00008755999,0.0004776267,0.00007219801,0.0008264801,0.0001555177,0.0002056937,0.00001470302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005196615,"about_ca_system_score_gemma":0.0007977444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007985839,"about_ca_topic_score_gemma":0.0002119141,"domain_scores_codex":[0.9981791,0.00006592155,0.0004005752,0.000779036,0.0002580233,0.0003173632],"domain_scores_gemma":[0.9979922,0.0004505415,0.0002174218,0.000735259,0.0001378007,0.0004667427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002635358,0.0003644962,0.005657532,0.002432925,0.0002990568,0.00005783694,0.000995282,0.003645463,0.8379881,0.000009993832,0.1146032,0.03131077],"study_design_scores_gemma":[0.006680924,0.0004118777,0.001791896,0.0001023616,0.0007375608,0.00002977022,0.0001668781,0.6567687,0.1330918,0.0001319906,0.1996171,0.0004691653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2314605,0.0001342349,0.6436582,0.1188483,0.001790628,0.003089283,0.0003953897,0.000584298,0.00003918534],"genre_scores_gemma":[0.8494298,0.00002753605,0.001648017,0.1472117,0.001120756,0.00008338396,0.0003733813,0.0000683852,0.00003701508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7048963,"threshold_uncertainty_score":0.9134191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3020511645","doi":"10.1016/j.scitotenv.2020.138996","title":"Evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) as coronavirus disease 2019 (COVID-19) pandemic: A global health emergency","year":2020,"lang":"en","type":"review","venue":"The Science of The Total Environment","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":592,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ministry of Education, Government of the People's Republic of Bangladesh; National Research Foundation of Korea","keywords":"Pandemic; Outbreak; Coronavirus; Disease; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Virology; Infectious disease (medical specialty); China; Medicine; Geography; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1233438058078482,"gpt":0.4246663780177223,"spread":0.3013225722098741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001802071,0.0006433419,0.001789112,0.0001371043,0.0004658416,0.00001758512,0.001864406,0.0001749709,0.0001866586],"category_scores_gemma":[0.0006254006,0.0003960925,0.0009561538,0.001176141,0.002370098,0.0001617307,0.001583017,0.0005777896,0.000299347],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.008584381,"about_ca_system_score_gemma":0.008964265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001331435,"about_ca_topic_score_gemma":0.000006297441,"domain_scores_codex":[0.9939942,0.000568085,0.001379953,0.00110025,0.002242195,0.0007152794],"domain_scores_gemma":[0.9952457,0.0001658222,0.001696794,0.002157862,0.00003572398,0.000698116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001684863,0.004172821,0.001440562,0.04506738,0.00267412,0.0006130835,0.001637088,0.009912338,0.003931683,0.002064855,0.01688904,0.9099122],"study_design_scores_gemma":[0.001275643,0.001347631,0.01125331,0.007096787,0.004546763,0.001324602,0.00006183445,0.0001580416,0.00003893562,0.0008585887,0.9711202,0.0009176017],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01567946,0.9734579,0.00002951544,0.005432968,0.0007784892,0.003286941,0.001231116,0.00006284179,0.00004080135],"genre_scores_gemma":[0.01152917,0.9853613,0.00005791168,0.002439466,0.00009956973,0.0001276714,0.00002118643,0.00006240694,0.0003012592],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9542312,"threshold_uncertainty_score":0.9998491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034560014","doi":"10.1109/access.2020.3001973","title":"Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":554,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ministerstvo Školství, Mládeže a Tělovýchovy","keywords":"Computer science; Artificial intelligence; Coronavirus disease 2019 (COVID-19); Adversarial system; Deep learning; Artificial neural network; Machine learning; Process (computing); Data science; Generative grammar; Infectious disease (medical specialty); Disease; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.3188385306203328,"gpt":0.4076785830440597,"spread":0.08884005242372689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000139073,0.0001817125,0.0003156569,0.00007799138,0.0001902369,0.0001445338,0.00009901343,0.00008096892,0.0000374736],"category_scores_gemma":[0.00124386,0.0001591457,0.00005871054,0.0001902102,0.0001220378,0.0001433475,0.00006335121,0.0001093106,0.000005003271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001245488,"about_ca_system_score_gemma":0.0001127928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002112607,"about_ca_topic_score_gemma":0.0001049214,"domain_scores_codex":[0.9988801,0.00004297932,0.0002307164,0.0004908366,0.0001302506,0.0002250846],"domain_scores_gemma":[0.9982617,0.001033553,0.00007780972,0.0001336167,0.0000334389,0.000459809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006115325,0.0004278333,0.1541115,0.000899213,0.0001841322,0.0000720778,0.00682386,0.008270547,0.0001748311,0.0004149786,0.001890453,0.8261191],"study_design_scores_gemma":[0.003875429,0.007231236,0.01985391,0.0003836493,0.002078161,0.00008891008,0.003503507,0.4887874,0.1144298,0.005335863,0.3527179,0.001714125],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6815484,0.002086153,0.1327115,0.1809277,0.0001817959,0.002167649,0.00002221681,0.0002956517,0.00005898775],"genre_scores_gemma":[0.9804945,0.0008259517,0.0007099007,0.01708533,0.0003587144,0.0004664247,0.00001330241,0.00002973257,0.00001614498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8244049,"threshold_uncertainty_score":0.6489775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3168156287","doi":"10.1016/j.bbe.2021.05.013","title":"Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning Based Approach","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Biomedicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":375,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Feature extraction; Machine learning; Feature (linguistics); Deep learning; Coronavirus disease 2019 (COVID-19); Classifier (UML); Acute respiratory distress; Pneumonia; Medicine; Pattern recognition (psychology); Disease; Infectious disease (medical specialty); Pathology; Lung; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0427837220591765,"gpt":0.3334961717697731,"spread":0.2907124497105966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157257,0.0002098628,0.0007734068,0.0007874275,0.00005961555,0.00001500329,0.00009030439,0.00005949365,0.0001081696],"category_scores_gemma":[0.001361984,0.0001661448,0.0001152996,0.0009003752,0.0002152808,0.00005988591,0.00004840153,0.0005218218,0.000001444392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003736221,"about_ca_system_score_gemma":0.0009304011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009113103,"about_ca_topic_score_gemma":0.00001006091,"domain_scores_codex":[0.9978697,0.00009971749,0.0008931005,0.0002749563,0.0006355264,0.0002270158],"domain_scores_gemma":[0.9979262,0.0005120224,0.000593903,0.0002369142,0.0001526658,0.0005782694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.005475699,0.00428386,0.048468,0.009745756,0.0004772241,0.006081969,0.001622302,0.008252601,0.7469079,0.0000436437,0.0006718393,0.1679692],"study_design_scores_gemma":[0.07900819,0.004531766,0.4013025,0.005404552,0.003848224,0.002690932,0.003778427,0.3352159,0.07928035,0.0005564403,0.08316582,0.001216978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9617421,0.005005646,0.01635616,0.01600438,0.0001787679,0.0005527305,0.00001448494,0.00006380206,0.00008192152],"genre_scores_gemma":[0.990207,0.0002490318,0.003372301,0.005924008,0.0001602934,0.00001193443,0.00002526598,0.00003055313,0.00001957575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6676275,"threshold_uncertainty_score":0.6775188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021613067","doi":"10.3390/ijerph17093176","title":"How Big Data and Artificial Intelligence Can Help Better Manage the COVID-19 Pandemic","year":2020,"lang":"en","type":"review","venue":"International Journal of Environmental Research and Public Health","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":375,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Big data; Pandemic; Coronavirus disease 2019 (COVID-19); Data science; Field (mathematics); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Public health; 2019-20 coronavirus outbreak; Computer science; Outbreak; Business; Data mining; Virology; Medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.5235989194540144,"gpt":0.5134173160312675,"spread":0.01018160342274688,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004480334,0.0002434406,0.0007977328,0.0006088607,0.0002258867,0.0004991171,0.001187024,0.0001317656,0.00008421235],"category_scores_gemma":[0.002684313,0.0001590615,0.0001224149,0.0002358953,0.0006852057,0.0001973853,0.001205009,0.001734121,0.00000966278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001856747,"about_ca_system_score_gemma":0.002861697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001961348,"about_ca_topic_score_gemma":0.0001271548,"domain_scores_codex":[0.9956489,0.0007558168,0.0007946571,0.000488353,0.001837618,0.0004746216],"domain_scores_gemma":[0.9957043,0.001885252,0.0005281933,0.0004409634,0.00006632914,0.001374971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003681898,0.0001851421,0.0004838212,0.001156259,0.0002889016,0.0003325987,0.0002165736,6.364476e-8,0.000001229022,0.00006950307,0.006893175,0.9903359],"study_design_scores_gemma":[0.0001738199,0.0004259698,0.0001189811,0.001042942,0.00005222302,0.00193962,0.0004702907,0.00002771548,2.11936e-7,0.0004251364,0.9952188,0.0001043464],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001260523,0.5833008,0.0005247797,0.4149496,0.0002241848,0.0004108117,0.0004531217,0.000005235586,0.000005346317],"genre_scores_gemma":[0.003878434,0.9712966,0.0001079112,0.02256634,0.001796076,0.00001307843,0.0002326047,0.00003283764,0.00007611988],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9902316,"threshold_uncertainty_score":0.7533988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3114166611","doi":"10.3389/fmed.2020.608525","title":"COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest CT Images","year":2020,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":347,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Convolutional neural network; Leverage (statistics); Coronavirus disease 2019 (COVID-19); Medicine; Radiology; Artificial intelligence; Disease; Computer science; Pathology; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.05675796477487922,"gpt":0.3146544662007718,"spread":0.2578965014258925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006794575,0.0003282978,0.001098774,0.0002462116,0.0001279462,0.00001027234,0.0002158129,0.00008509894,0.0001242022],"category_scores_gemma":[0.009296934,0.0003012304,0.0001468083,0.0007150875,0.0005713367,0.0001013217,0.00005380153,0.0003430287,0.000003456957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005319579,"about_ca_system_score_gemma":0.0005236067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001409906,"about_ca_topic_score_gemma":0.00007824809,"domain_scores_codex":[0.9973922,0.0002243369,0.0007513412,0.000634642,0.0005215679,0.0004759515],"domain_scores_gemma":[0.9965723,0.002027489,0.0003162936,0.0003304634,0.0001509377,0.0006025049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006324455,0.0002581235,0.07534088,0.00111817,0.0004069126,0.001086939,0.001811,0.03199076,0.01217332,0.00001851493,0.8590289,0.01044201],"study_design_scores_gemma":[0.03917081,0.006764266,0.03913897,0.001320703,0.002409467,0.0003612176,0.003943992,0.6001306,0.01245714,0.002926437,0.2902386,0.001137851],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03408023,0.009486447,0.8381959,0.1138738,0.00196697,0.002097356,0.00009490949,0.000193081,0.00001132388],"genre_scores_gemma":[0.9090143,0.0002650431,0.03723236,0.05095182,0.001923975,0.0002123491,0.0002998499,0.00006621444,0.00003411404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.874934,"threshold_uncertainty_score":0.999944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013772641","doi":"10.1613/jair.1.12162","title":"Mapping the landscape of Artificial Intelligence applications against COVID-19","year":2020,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":338,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Science and Technology Facilities Council; Institut de Valorisation des Données; William and Flora Hewlett Foundation","keywords":"Multidisciplinary approach; Coronavirus disease 2019 (COVID-19); Applications of artificial intelligence; Pandemic; 2019-20 coronavirus outbreak","retraction":null,"screen_n_in":null,"score":{"opus":0.3617784450179333,"gpt":0.4770410701565926,"spread":0.1152626251386594,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005337292,0.0002162117,0.0005938638,0.0007693036,0.000450004,0.0001448822,0.001023324,0.0001643882,0.0004931418],"category_scores_gemma":[0.009598647,0.0001590999,0.0003525989,0.003235199,0.0008610089,0.0001681343,0.0002598646,0.001617991,0.0002227525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003103053,"about_ca_system_score_gemma":0.002352409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008858205,"about_ca_topic_score_gemma":0.00003718227,"domain_scores_codex":[0.9948307,0.0004777758,0.001775026,0.0004119613,0.001893523,0.0006109605],"domain_scores_gemma":[0.9926332,0.003395257,0.0005929131,0.0005761737,0.001932229,0.0008702387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002040974,0.001610888,0.001481612,0.001095151,0.000361477,0.0003838924,0.01884163,0.01936964,0.105897,0.01972396,0.01689786,0.8122959],"study_design_scores_gemma":[0.0002912793,0.004888791,0.0004717327,0.001275314,0.0002768728,0.0003385412,0.09337025,0.1313596,0.4370712,0.06382374,0.265926,0.0009066008],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07475907,0.00153955,0.5484348,0.3726371,0.0003225185,0.00175391,0.00002655255,0.00006491874,0.0004615821],"genre_scores_gemma":[0.9870201,0.00100988,0.002115224,0.008074558,0.001667717,0.0000435523,0.00000526927,0.00003890284,0.00002478177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9122611,"threshold_uncertainty_score":0.998744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3048416409","doi":"10.1016/j.bspc.2020.102149","title":"An IoT-based framework for early identification and monitoring of COVID-19 cases","year":2020,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":297,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Health Science Centre; St Joseph's Health Centre; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Computer science; Machine learning; Identification (biology); Support vector machine; Artificial intelligence; Naive Bayes classifier; Coronavirus disease 2019 (COVID-19); Cloud computing; Upload; Data mining; Table (database); Decision stump; Isolation (microbiology); Decision tree; World Wide Web; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04656151471364115,"gpt":0.3584960391439156,"spread":0.3119345244302745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003234141,0.0001296088,0.0003178397,0.00008317857,0.0001612431,0.00007317141,0.00007036151,0.0001542223,0.00001162235],"category_scores_gemma":[0.001615229,0.0001117277,0.00004515215,0.0002049161,0.0002757892,0.00006088322,0.000009918042,0.000139335,5.655706e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003584133,"about_ca_system_score_gemma":0.0004048295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006116288,"about_ca_topic_score_gemma":3.414977e-7,"domain_scores_codex":[0.9987838,0.0000465639,0.0003210435,0.0003552616,0.0003072465,0.0001860807],"domain_scores_gemma":[0.9980344,0.0009038744,0.0001538263,0.00009567274,0.000117148,0.0006951194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004982398,0.001017125,0.1157897,0.009352678,0.0001661294,0.0001259553,0.003190616,0.00006553724,0.3066136,0.0001816004,0.0006656929,0.557849],"study_design_scores_gemma":[0.05963743,0.02144982,0.1694559,0.007303831,0.00412886,0.0001540877,0.003539959,0.5955602,0.07650489,0.006486431,0.05348227,0.002296354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3711109,0.001768293,0.5721843,0.05432247,0.00004565324,0.0004261606,0.00003838927,0.0001034173,4.809722e-7],"genre_scores_gemma":[0.9859468,0.000009383175,0.003867392,0.0096139,0.0004719304,0.00005782161,0.00001194114,0.00001832457,0.000002528601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6148359,"threshold_uncertainty_score":0.4556122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3131326546","doi":"10.1109/access.2021.3058537","title":"A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)","year":2021,"lang":"en","type":"review","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":292,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deep learning; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Computer science; Pandemic; Modalities; Data science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Categorization; Machine learning; Field (mathematics); 2019-20 coronavirus outbreak; Globe; Infectious disease (medical specialty); Medicine; Outbreak; Disease; Pathology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.368597281056471,"gpt":0.5310062315117523,"spread":0.1624089504552813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001359941,0.0006592483,0.003513143,0.0002969378,0.0002183285,0.00009175905,0.00110685,0.0004142931,0.0002325042],"category_scores_gemma":[0.008874502,0.0004350695,0.00151004,0.00104348,0.0001540091,0.0001062298,0.000255312,0.0009434627,0.00001225243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006626156,"about_ca_system_score_gemma":0.001496464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004029272,"about_ca_topic_score_gemma":0.00005370706,"domain_scores_codex":[0.9966549,0.0002785999,0.001221619,0.0008781403,0.0005368444,0.0004298878],"domain_scores_gemma":[0.9861917,0.01069441,0.001186025,0.001327375,0.0003582712,0.000242188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001227395,0.0003202175,0.00002473254,0.1968363,0.0003238755,0.00002220072,0.00001927662,0.000008018046,6.314818e-7,0.00002855565,0.03046931,0.7719346],"study_design_scores_gemma":[0.0003138502,0.0001775836,0.000002543107,0.2279406,0.004649935,0.00004541112,0.0000035126,0.000009319267,0.00007471188,0.000004397096,0.7664757,0.0003024254],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.940362e-7,0.9835308,0.00376065,0.00623646,0.0004219704,0.00570633,0.0001052419,0.0001937388,0.00004433111],"genre_scores_gemma":[0.000002547707,0.9362838,0.0005780216,0.05448911,0.0005099689,0.007722329,0.0001453695,0.0001657835,0.0001030604],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7716322,"threshold_uncertainty_score":0.9998101,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2980965120","doi":"10.1038/s41598-019-51503-3","title":"Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Government of Canada; National Philanthropic Trust; Bill and Melinda Gates Foundation; United States Agency for International Development","keywords":"Triage; Medicine; Tuberculosis; Radiography; Artificial intelligence; Pulmonary tuberculosis; Diagnostic accuracy; Convolutional neural network; Artificial neural network; Machine learning; Radiology; Pathology; Computer science; Medical emergency","retraction":null,"screen_n_in":null,"score":{"opus":0.1088325756948852,"gpt":0.3711691323453224,"spread":0.2623365566504371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005484954,0.0001653334,0.0003925255,0.000451877,0.0002477283,0.00009825316,0.0001352308,0.00009723753,0.000039996],"category_scores_gemma":[0.01547418,0.0001328033,0.0002697771,0.001686996,0.0002310258,0.000137284,0.00008791844,0.0001477854,0.000007442937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002546481,"about_ca_system_score_gemma":0.0003575773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007910319,"about_ca_topic_score_gemma":0.0005314586,"domain_scores_codex":[0.996685,0.0001580416,0.0009784343,0.0007093014,0.001197092,0.0002721655],"domain_scores_gemma":[0.9953026,0.001113235,0.0008787893,0.001092231,0.001511575,0.0001016102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001080513,0.0004953727,0.1995973,0.001334951,0.0001712814,0.00001483731,0.00245768,0.3157167,0.3870991,0.00006351925,0.00007762032,0.09286354],"study_design_scores_gemma":[0.0003177295,0.0002789175,0.0477028,0.00243991,0.0012537,0.0002067023,0.000953802,0.6290548,0.3150242,0.000958498,0.001488975,0.0003200076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9529296,0.0004038815,0.03669906,0.000337674,0.005951777,0.003628366,0.000003160289,0.0000356988,0.0000107584],"genre_scores_gemma":[0.9981217,0.00000380635,0.001538715,0.00004138605,0.00008344874,0.0001455929,0.0000107563,0.00002601955,0.00002855042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.313338,"threshold_uncertainty_score":0.9928189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194687576","doi":"10.1016/s2589-7500(21)00116-3","title":"Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms","year":2021,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Triage; Algorithm; Medicine; Tuberculosis; Receiver operating characteristic; Machine learning; Artificial intelligence; Test (biology); Diagnostic accuracy; Abnormality; Radiology; Medical physics; Computer science; Pathology; Medical emergency; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09890904320150842,"gpt":0.3931391453166914,"spread":0.294230102115183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238943,0.0001791014,0.0006082292,0.0001274544,0.0001162577,0.00008888236,0.0001469339,0.00009036931,0.00002119874],"category_scores_gemma":[0.001855395,0.000153843,0.0001090675,0.0005395101,0.00006324149,0.0002610766,0.00005498807,0.0002513335,0.000007091593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000607327,"about_ca_system_score_gemma":0.0007751643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003259105,"about_ca_topic_score_gemma":0.001380919,"domain_scores_codex":[0.9975787,0.0002848408,0.0006632717,0.0004786023,0.0005865308,0.000408088],"domain_scores_gemma":[0.9975343,0.001157283,0.0002377522,0.0005518256,0.0003967462,0.0001220743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005059911,0.0004866858,0.001611272,0.0003513285,0.00008694827,0.000005647677,0.005292148,0.003877709,0.001406012,0.0001126589,0.000161146,0.9861025],"study_design_scores_gemma":[0.005800106,0.001731054,0.1131017,0.002685565,0.0006561824,0.000041695,0.009885723,0.7154375,0.09320118,0.05519983,0.001533533,0.0007258845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390665,0.0004435516,0.003258799,0.0553626,0.0002761291,0.001231597,0.0002562545,0.00007072881,0.00003380877],"genre_scores_gemma":[0.9938511,0.00008747428,0.001453273,0.003078076,0.000982276,0.0001578806,0.0003502108,0.00003257101,0.000007141259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9853766,"threshold_uncertainty_score":0.6273535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3012582186","doi":"10.48550/arxiv.2003.09871","title":"COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":267,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Convolutional neural network; Computer science; Benchmark (surveying); Audit; Pandemic; Artificial intelligence; Medicine; Medical physics; Business; Cartography; Pathology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1490005189618571,"gpt":0.2577539400726493,"spread":0.1087534211107921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003774478,0.0005444698,0.0009793383,0.0003080903,0.0002833365,0.00004275801,0.0004816449,0.0005343707,0.000229192],"category_scores_gemma":[0.003150114,0.0006549045,0.0005653111,0.0006329122,0.0004482154,0.0001350437,0.0005038318,0.0006619856,0.0000199759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262531,"about_ca_system_score_gemma":0.002261088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002922845,"about_ca_topic_score_gemma":0.0003226171,"domain_scores_codex":[0.9969829,0.0003610637,0.0004885945,0.001457701,0.0002066682,0.0005030662],"domain_scores_gemma":[0.9937968,0.003498413,0.0006538297,0.0007949195,0.0003835544,0.0008725086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003900337,0.0002571587,0.005267841,0.001080644,0.0006035669,0.0009417582,0.0002729217,0.9748983,0.003014543,0.0002908055,0.009311239,0.0001609318],"study_design_scores_gemma":[0.008240177,0.001283641,0.008206411,0.0004457325,0.003620724,0.00003965385,0.0004761697,0.9462919,0.002975757,0.01318042,0.01403351,0.00120591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.106893,0.0005705903,0.8827964,0.005815187,0.0007527847,0.002273418,0.0005027166,0.0003819425,0.00001394278],"genre_scores_gemma":[0.9875003,0.0001989247,0.004110056,0.006793427,0.0006772362,0.00002396039,0.0005069032,0.00007810728,0.0001111502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8806072,"threshold_uncertainty_score":0.9995902,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2559794190","doi":"10.1097/rli.0000000000000341","title":"Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs","year":2016,"lang":"en","type":"article","venue":"Investigative Radiology","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":253,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Michael's Hospital","funders":"Siemens Medical Solutions USA; Nvidia; Google","keywords":"Medicine; Receiver operating characteristic; Radiography; Convolutional neural network; Radiology; Pleural effusion; Pneumothorax; Credentialing; Artificial intelligence; Computer science; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.08313131128224248,"gpt":0.3036097608725078,"spread":0.2204784495902653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003645533,0.0001469539,0.000365703,0.0001405428,0.0001220857,0.000008034744,0.00003777246,0.0001162158,0.000003792132],"category_scores_gemma":[0.0005125285,0.0001156245,0.00005641883,0.0001077386,0.001215651,0.00008676329,0.00001921469,0.0001006587,4.156593e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008409745,"about_ca_system_score_gemma":0.00006740295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002950267,"about_ca_topic_score_gemma":0.00003082166,"domain_scores_codex":[0.9988811,0.0001902715,0.0003039865,0.0003147413,0.0000836625,0.0002262639],"domain_scores_gemma":[0.9974443,0.00202949,0.0002124723,0.0001045679,0.00009475197,0.0001143732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001270705,0.0001607481,0.3444645,0.0006061185,0.0007156746,0.00001450295,0.01056593,0.001096927,0.4348637,0.02390306,0.001567758,0.1807704],"study_design_scores_gemma":[0.003749245,0.002431043,0.9328172,0.0004440426,0.0001387672,0.0002709928,0.0003812136,0.0427927,0.008021059,0.007833648,0.0008832846,0.0002368388],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9759784,0.0002625753,0.01852972,0.0045357,0.0001949821,0.0004124799,0.00002426379,0.00004638592,0.00001548476],"genre_scores_gemma":[0.9856434,0.00002941074,0.01210509,0.001715647,0.0003815638,0.00007985082,0.00002207191,0.00001542697,0.000007557331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5883526,"threshold_uncertainty_score":0.4715031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108591672","doi":"10.1002/mp.14676","title":"Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":251,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Segmentation; Medical imaging; Image segmentation; Deep learning; Computed tomography; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.08268855983109663,"gpt":0.3785273690815479,"spread":0.2958388092504513,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003746541,0.0001216869,0.0002285425,0.00002625313,0.0001135495,0.00002644005,0.00008759111,0.00005126072,0.0001102154],"category_scores_gemma":[0.004221368,0.0001120019,0.0000481,0.0002151106,0.00009459283,0.00006708065,0.00014596,0.000271797,0.00001029899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331872,"about_ca_system_score_gemma":0.0003973041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072841,"about_ca_topic_score_gemma":0.000002637617,"domain_scores_codex":[0.9986348,0.00004955274,0.0002034774,0.0004072296,0.0005219377,0.0001829774],"domain_scores_gemma":[0.9986185,0.0004870941,0.00007778953,0.00018453,0.00004871019,0.0005834205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008672624,0.001889387,0.1217452,0.008906915,0.0005148743,0.0002592242,0.01268009,0.00590551,0.002460168,0.0008820559,0.4665262,0.3773631],"study_design_scores_gemma":[0.006319785,0.000852994,0.004448629,0.0002667221,0.0005737735,0.00003597327,0.000192887,0.6482871,0.002321129,0.0002794923,0.336069,0.0003525389],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2119178,0.0002392353,0.6224907,0.1634466,0.0003254981,0.001175903,0.00003737303,0.0002802293,0.00008662452],"genre_scores_gemma":[0.9576906,0.00009863098,0.0004103138,0.04019534,0.0008393761,0.00004857625,0.0006742308,0.0000241531,0.00001877751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7457728,"threshold_uncertainty_score":0.5053676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127253295","doi":"10.1016/j.cosrev.2021.100370","title":"Role of machine learning in medical research: A survey","year":2021,"lang":"en","type":"article","venue":"Computer Science Review","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":242,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Lakehead University; Northern Ontario Academic Medicine Association","keywords":"Computer science; Artificial intelligence; Machine learning; Deep learning; Data science; Domain (mathematical analysis); Health care; Medical research; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.181429216282171,"gpt":0.4654740088941582,"spread":0.2840447926119872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01319328,0.00007634512,0.0004498338,0.0002323434,0.00006802728,0.0000225978,0.0003937404,0.00003606828,0.0002254276],"category_scores_gemma":[0.009402912,0.00006288239,0.00005883369,0.003745384,0.000419745,0.00007929164,0.0005572532,0.0004798875,0.00003759245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156647,"about_ca_system_score_gemma":0.002393514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003301699,"about_ca_topic_score_gemma":0.000173723,"domain_scores_codex":[0.9967226,0.0007275451,0.0003720162,0.0004179343,0.001430834,0.0003290772],"domain_scores_gemma":[0.9976125,0.001029941,0.00005885631,0.0004501512,0.0006114398,0.0002371117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000005069218,0.0003082301,0.07588769,0.002793703,0.000006338127,0.0002351698,0.0001711356,0.00001747595,0.0007133249,0.0001455536,0.002187596,0.9175287],"study_design_scores_gemma":[0.000966969,0.0003694131,0.4708547,0.06378426,0.00002741329,0.0003543601,0.00001045679,0.09867367,0.001838455,0.0001455266,0.3627146,0.000260166],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1178578,0.7392309,0.002935898,0.1377468,0.0004258031,0.001112817,0.000004512735,0.0001138687,0.0005716299],"genre_scores_gemma":[0.6636702,0.2861327,0.009724565,0.0400263,0.0002205306,0.00003586882,0.000029323,0.0000322714,0.0001282363],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9172686,"threshold_uncertainty_score":0.9989413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093982442","doi":"10.1109/access.2020.3030194","title":"COVID-SAFE: An IoT-Based System for Automated Health Monitoring and Surveillance in Post-Pandemic Life","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":230,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Saskatchewan Health Authority; Saskatchewan Health; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pandemic; Internet of Things; Isolation (microbiology); Node (physics); Computer security; Cyber-physical system; Cloud computing; Coronavirus disease 2019 (COVID-19); Real-time computing; Engineering; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.09589681227167375,"gpt":0.4172665385088837,"spread":0.3213697262372099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005467008,0.0001927964,0.0005439711,0.0001522137,0.0001046636,0.00008986116,0.0002203075,0.0001099189,0.000004643973],"category_scores_gemma":[0.001037886,0.0001913985,0.00004602036,0.0004176626,0.00003748045,0.0001408386,0.00003633717,0.0001775934,0.00000374888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004616549,"about_ca_system_score_gemma":0.00150886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001726903,"about_ca_topic_score_gemma":0.0002310161,"domain_scores_codex":[0.9983179,0.0001376796,0.0004384412,0.0005002636,0.0002342296,0.0003714799],"domain_scores_gemma":[0.9980999,0.000595632,0.0001754854,0.0002818818,0.0001419722,0.0007050871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009214419,0.0001629142,0.9729532,0.006084313,0.00004709195,0.00006026843,0.0008332109,0.005890602,0.005795445,0.000004568531,0.004573068,0.002673858],"study_design_scores_gemma":[0.01099328,0.001274187,0.7183122,0.001381988,0.00004853242,0.00002026489,0.0004117606,0.258304,0.00519172,0.000003191644,0.003501459,0.0005574171],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9576905,0.0005089734,0.0006650283,0.03859631,0.0004766645,0.0010657,0.00006809954,0.0009254665,0.000003283006],"genre_scores_gemma":[0.9678362,0.00002713014,0.0003926816,0.0311488,0.0004123478,0.0001011964,0.00003241577,0.00004688582,0.000002356119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2546411,"threshold_uncertainty_score":0.7805002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3159019058","doi":"10.1038/s41597-021-00900-3","title":"COVID-CT-MD, COVID-19 computed tomography scan dataset applicable in machine learning and deep learning","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; McGill University Health Centre; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Coronavirus disease 2019 (COVID-19); Computed tomography; Artificial intelligence; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Chest radiograph; Computer science; Pneumonia; Medicine; Tomography; Radiology; Machine learning; Medical physics; Radiography; Infectious disease (medical specialty); Pathology; Disease; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05262219948600481,"gpt":0.3532226569827437,"spread":0.3006004574967389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002964787,0.0002809815,0.0004998153,0.0006667773,0.0007570706,0.0005829641,0.0007464954,0.00007553247,0.000879719],"category_scores_gemma":[0.004979244,0.0002948231,0.000052214,0.002691974,0.0005575811,0.0003667702,0.002231657,0.0007769881,0.00009156294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002384816,"about_ca_system_score_gemma":0.001129469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001627985,"about_ca_topic_score_gemma":0.003229416,"domain_scores_codex":[0.9958919,0.0003430308,0.0004773385,0.001983162,0.0006819453,0.0006226687],"domain_scores_gemma":[0.9959301,0.0007690183,0.0001670667,0.002126795,0.00009861995,0.000908338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001359589,0.0008058072,0.2259323,0.001396443,0.0001217777,0.002042016,0.0007568129,0.003468555,0.008265587,0.0001065272,0.7329492,0.02401906],"study_design_scores_gemma":[0.001933109,0.00004667562,0.001517817,0.0001169106,0.00009777024,0.0001981226,0.0003033114,0.04822017,0.0004129327,0.00005483657,0.9468126,0.0002857583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.3245797,0.124897,0.07820524,0.2674153,0.01021564,0.0120296,0.1745121,0.005858352,0.002287145],"genre_scores_gemma":[0.4008922,0.0008687943,0.01085137,0.03487949,0.0002837188,0.00008073311,0.5497575,0.000154884,0.002231355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3752454,"threshold_uncertainty_score":0.9999504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035916362","doi":"10.2196/19866","title":"The Role of Health Technology and Informatics in a Global Public Health Emergency: Practices and Implications From the COVID-19 Pandemic","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":198,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Pandemic; Telemedicine; Health care; Medicine; Public health; Telehealth; Coronavirus disease 2019 (COVID-19); Middle East respiratory syndrome; Digital health; Global health; Health informatics; Medical emergency; Business; Disease; Economic growth; Nursing; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.089719897220137,"gpt":0.4288465134815742,"spread":0.3391266162614371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001838328,0.0001517304,0.0004272735,0.00009431294,0.0002865068,0.00004251957,0.0003518937,0.0001871089,0.0000249904],"category_scores_gemma":[0.008788922,0.00009209327,0.00003470657,0.001069298,0.0004832593,0.0002387505,0.0003274899,0.0005817592,0.000005394623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002454252,"about_ca_system_score_gemma":0.003172158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005980206,"about_ca_topic_score_gemma":0.0006703217,"domain_scores_codex":[0.9972723,0.0001340829,0.001548434,0.0001069739,0.0005500778,0.0003881128],"domain_scores_gemma":[0.9962587,0.001146427,0.00136187,0.0003968429,0.00008680202,0.0007493488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003739995,0.0001374928,0.6700038,0.000826003,0.00007962176,7.882616e-7,0.04921738,0.00000289233,0.000002305155,0.007073464,0.02452814,0.2480908],"study_design_scores_gemma":[0.001604374,0.0003974222,0.06065296,0.0001495914,0.00002563128,0.0001028102,0.04354992,0.01338143,0.000001110269,0.003318487,0.876684,0.0001323063],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2392131,0.00384897,0.001112542,0.7546793,0.00003828499,0.000878224,0.00005905716,0.0000939172,0.00007652809],"genre_scores_gemma":[0.7693472,0.01238645,0.001490709,0.2164979,0.00006505313,0.0001449622,0.0000545203,0.00001110422,0.000002074538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8521558,"threshold_uncertainty_score":0.9995605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3161970434","doi":"10.1016/j.imu.2021.100588","title":"IoT based wearable device to monitor the signs of quarantined remote patients of COVID-19","year":2021,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Humber Polytechnic","funders":"","keywords":"Wearable computer; Computer science; Android (operating system); Cloud computing; Global Positioning System; Mobile device; Wearable technology; Embedded system; Application layer; Real-time computing; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.043609492800243,"gpt":0.3571376062982099,"spread":0.3135281134979669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001353277,0.0002347872,0.0008292561,0.0004732028,0.00006894304,0.000007851984,0.0003192043,0.0001322614,0.0001889924],"category_scores_gemma":[0.01304108,0.0001668146,0.0001011006,0.001643588,0.0002409863,0.00005660542,0.0001094398,0.0003361734,0.00001780818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002493305,"about_ca_system_score_gemma":0.0009965223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001006455,"about_ca_topic_score_gemma":0.0001019546,"domain_scores_codex":[0.9966843,0.0001413242,0.001610379,0.0001738634,0.001045771,0.0003443493],"domain_scores_gemma":[0.9954976,0.002011743,0.0005118938,0.0009004973,0.0007813064,0.0002970042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.006131934,0.006098051,0.2463674,0.04622284,0.001099781,0.0003803101,0.2314655,0.07781653,0.05911989,0.0007763552,0.2468292,0.07769216],"study_design_scores_gemma":[0.07442041,0.008481009,0.07513196,0.02959783,0.001738912,0.00006579883,0.03790549,0.2249215,0.2289516,0.0007360139,0.3162948,0.001754636],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9383076,0.0001970756,0.005517391,0.05349815,0.0004078724,0.001243028,0.00002368855,0.00005575742,0.00074942],"genre_scores_gemma":[0.9321609,0.00004736849,0.01033432,0.05715819,0.00009618258,0.00001567514,0.00004853133,0.00002825327,0.0001106104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1935601,"threshold_uncertainty_score":0.9952725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3032017599","doi":"10.1007/s00264-020-04609-7","title":"Deep learning COVID-19 detection bias: accuracy through artificial intelligence","year":2020,"lang":"en","type":"article","venue":"International Orthopaedics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":192,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Medicine; Artificial intelligence; Coronavirus Infections; Deep learning; Orthopedic surgery; Machine learning; Virology; Surgery; Computer science; Internal medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.1324240516387547,"gpt":0.3865001703369287,"spread":0.254076118698174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003304338,0.0002169878,0.0002560378,0.0001517812,0.0001733024,0.00009788409,0.0002579174,0.0001402206,0.0009311431],"category_scores_gemma":[0.02028278,0.0002223159,0.0002256835,0.0004935208,0.0001178973,0.0002933762,0.0001473732,0.0006307688,0.000432553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004462605,"about_ca_system_score_gemma":0.0003571563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000183331,"about_ca_topic_score_gemma":0.00008094868,"domain_scores_codex":[0.9977449,0.00009234752,0.0005723265,0.000512566,0.0008179963,0.0002598651],"domain_scores_gemma":[0.9979349,0.0009053466,0.0002630898,0.0001876538,0.0003075711,0.0004014428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00231628,0.000851388,0.06163776,0.0005196165,0.0006937071,0.001421845,0.01276135,0.07670301,0.01346916,0.0107715,0.006389983,0.8124644],"study_design_scores_gemma":[0.0006079637,0.0004445706,0.002698113,0.0001015692,0.0001389433,0.0001504121,0.000854691,0.1710996,0.007178393,0.00235078,0.8140022,0.0003728482],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07495484,0.0002473049,0.6643472,0.2565784,0.001742904,0.0004967771,0.00001337286,0.0007036132,0.0009156229],"genre_scores_gemma":[0.905555,0.0002835145,0.002102961,0.09025189,0.001588352,0.0000318107,0.00007459916,0.00004119363,0.00007068305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8306001,"threshold_uncertainty_score":0.9999821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385652445","doi":"10.1016/j.cmpb.2023.107745","title":"The applications of machine learning techniques in medical data processing based on distributed computing and the Internet of Things","year":2023,"lang":"en","type":"review","venue":"Computer Methods and Programs in Biomedicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":187,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Cloud computing; Data science; Edge computing; Big data; Data processing; Artificial intelligence; The Internet; Machine learning; Enhanced Data Rates for GSM Evolution; World Wide Web; Data mining; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1342396236307867,"gpt":0.4908524473664609,"spread":0.3566128237356743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01247532,0.000313115,0.0018122,0.000452028,0.00007946278,0.00004208175,0.0006705782,0.0002551469,0.000001475701],"category_scores_gemma":[0.001262994,0.000156522,0.00008941961,0.001657848,0.001238306,0.00003045383,0.0008848098,0.001099899,1.214361e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005374562,"about_ca_system_score_gemma":0.0002369388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003359446,"about_ca_topic_score_gemma":0.00001203621,"domain_scores_codex":[0.9962103,0.001192746,0.001310734,0.0005812426,0.0004505393,0.0002544759],"domain_scores_gemma":[0.9904259,0.008028691,0.0006879229,0.0006750803,0.00008688943,0.00009549176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004252194,0.0001185549,0.0002176763,0.01537648,0.00005278112,0.00001093384,0.0002556523,3.906037e-7,2.58984e-7,0.00005595602,0.00004551391,0.9838233],"study_design_scores_gemma":[0.001270652,0.000329837,0.00005240686,0.07575163,0.0003289245,0.00004060012,0.00003308965,0.2828472,0.000002261928,0.0001029115,0.6391046,0.0001358733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004046954,0.6571583,0.3368282,0.003931536,0.00006074834,0.001925857,0.00001016038,0.00007670867,0.000004438624],"genre_scores_gemma":[0.0001062537,0.8211462,0.1768362,0.0007129041,0.0001829851,0.0001944785,0.000763889,0.0000513822,0.000005664464],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9836874,"threshold_uncertainty_score":0.6382782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2972112160","doi":"10.1371/journal.pone.0221339","title":"A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis","year":2019,"lang":"en","type":"review","venue":"PLoS ONE","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; St. Michael's Hospital; McGill University Health Centre","funders":"National Institute of Allergy and Infectious Diseases; McGill University; World Health Organization","keywords":"CAD; Receiver operating characteristic; Medicine; Pulmonary tuberculosis; Medical physics; Diagnostic accuracy; Artificial intelligence; MEDLINE; Tuberculosis; Machine learning; Radiology; Internal medicine; Computer science; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1562271622486037,"gpt":0.3627522615328458,"spread":0.2065250992842421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001206853,0.0005840964,0.006559812,0.0003348721,0.00004756143,0.00002694335,0.0007589951,0.0002620412,0.00003929428],"category_scores_gemma":[0.01448136,0.0003710853,0.001729397,0.001457918,0.0001127864,0.00004018565,0.0001981541,0.0003581783,0.00008089242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003133995,"about_ca_system_score_gemma":0.0009097878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003492464,"about_ca_topic_score_gemma":0.000005732664,"domain_scores_codex":[0.9948097,0.0004438169,0.00270801,0.000658388,0.0009951501,0.00038488],"domain_scores_gemma":[0.9848279,0.01056604,0.001775089,0.001912735,0.0007471798,0.0001710961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0000124108,0.003684434,0.00001912535,0.871728,0.001472579,0.000004860708,0.00003031039,0.000003737959,0.000004200912,0.00001742591,0.0001705817,0.1228523],"study_design_scores_gemma":[0.00006738904,0.0004818505,0.0000066885,0.9472145,0.04442985,0.000006198724,0.000004894868,0.0007205654,0.00009715838,0.000009190619,0.006656735,0.0003049097],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002697874,0.9659835,0.0007952111,0.002857759,0.0001314894,0.03001063,0.0001407317,0.00004843986,0.000005272268],"genre_scores_gemma":[0.00008414556,0.9878003,0.003830014,0.002928257,0.0002433981,0.00474339,0.0002307684,0.0001185855,0.00002114984],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.1225474,"threshold_uncertainty_score":0.9998741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3215969524","doi":"10.1016/j.imu.2021.100779","title":"Data augmentation using Generative Adversarial Networks (GANs) for GAN-based detection of Pneumonia and COVID-19 in chest X-ray images","year":2021,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Hospital for Sick Children; University of Toronto","funders":"Hospital for Sick Children; University of Toronto","keywords":"Generalizability theory; Computer science; Convolutional neural network; Artificial intelligence; Generative adversarial network; Training set; Deep learning; Pattern recognition (psychology); Artificial neural network; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08779487392792919,"gpt":0.3909398416086901,"spread":0.3031449676807609,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001278922,0.0002001312,0.0005585298,0.0004405658,0.00007593825,0.00001790384,0.000135454,0.0001520964,0.00002179813],"category_scores_gemma":[0.004495181,0.0001894055,0.00003251733,0.0006693467,0.0002260256,0.0002658133,0.00005761316,0.0002668643,3.446613e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004645794,"about_ca_system_score_gemma":0.0009029891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005030117,"about_ca_topic_score_gemma":0.0007139394,"domain_scores_codex":[0.9980066,0.00009836954,0.001044317,0.0002404334,0.0003578641,0.0002523946],"domain_scores_gemma":[0.9974948,0.001277937,0.0003723238,0.0004930962,0.0002108582,0.0001509575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002320065,0.000740111,0.02895149,0.007202922,0.0002481314,0.0001693133,0.02611588,0.7341465,0.173011,0.00006097543,0.004554366,0.0224793],"study_design_scores_gemma":[0.0118464,0.0003015851,0.004181969,0.0008734148,0.0002194532,0.00001998641,0.004369391,0.9609674,0.01443394,0.00004872452,0.002565453,0.0001722942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4574521,0.0004042199,0.5294788,0.01031134,0.000551873,0.001596884,0.0001022935,0.00005255833,0.00004991131],"genre_scores_gemma":[0.9714712,0.0001408431,0.01706261,0.01031072,0.0002496895,0.00003817841,0.0006942493,0.00002378249,0.000008746661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5140191,"threshold_uncertainty_score":0.7723731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319940243","doi":"10.1016/j.compbiomed.2023.106646","title":"High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Confusion matrix; Atelectasis; Artificial intelligence; Medicine; Computer science; Pattern recognition (psychology); Radiology; Lung","retraction":null,"screen_n_in":null,"score":{"opus":0.03635788074846163,"gpt":0.3711530190827284,"spread":0.3347951383342668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003844048,0.00016878,0.0005819501,0.000247114,0.00004568738,0.000002983862,0.0001226304,0.0001487558,0.00004114169],"category_scores_gemma":[0.0007355656,0.0001267079,0.00004413969,0.0003720836,0.0005246949,0.00004717058,0.0001072849,0.0001830001,0.000009178663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006345555,"about_ca_system_score_gemma":0.00006281315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003716765,"about_ca_topic_score_gemma":0.000007563982,"domain_scores_codex":[0.9986295,0.0001516608,0.0004334586,0.0004508026,0.0001242575,0.000210324],"domain_scores_gemma":[0.9973866,0.001903889,0.0001355784,0.0003708261,0.00007247279,0.000130571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004009733,0.00112064,0.4945881,0.0008751021,0.0003341985,0.000271755,0.003645897,0.0006111365,0.1973474,0.0014706,0.1278201,0.1679053],"study_design_scores_gemma":[0.008377098,0.0002718324,0.946035,0.001120219,0.0001637513,0.000001524653,0.0001253046,0.03573633,0.0006792114,0.001718822,0.00563718,0.0001336735],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9561983,0.001582935,0.004709693,0.03559595,0.00105927,0.0006409387,0.00002977162,0.0001588614,0.00002426005],"genre_scores_gemma":[0.9891439,0.002249689,0.004795687,0.002983902,0.0003225849,0.00005697368,0.0004048416,0.00001572412,0.0000267164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.451447,"threshold_uncertainty_score":0.5166997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3019586571","doi":"10.3390/ijerph17082906","title":"The Use of Digital Health in the Detection and Management of COVID-19","year":2020,"lang":"en","type":"article","venue":"International Journal of Environmental Research and Public Health","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; Memorial University of Newfoundland","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Triage; Outbreak; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Health care; Digital health; Infectious disease (medical specialty); Medical emergency; Computer science; Telemedicine; Business; Data science; Medicine; Internet privacy; Computer security; Environmental health; Disease; Virology; Pathology; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.2068774349000299,"gpt":0.4450256862976553,"spread":0.2381482513976254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002092122,0.00005156197,0.0001423902,0.0001662276,0.00008881466,0.00007994111,0.0001719356,0.00001781452,0.00001307563],"category_scores_gemma":[0.0006423212,0.00003190299,0.00003284265,0.0001382931,0.0002750468,0.0001907338,0.0001172835,0.0002789166,5.523289e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004369124,"about_ca_system_score_gemma":0.0003924445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001999417,"about_ca_topic_score_gemma":0.00004181795,"domain_scores_codex":[0.9981079,0.0002306561,0.0004408591,0.0001001023,0.0009354036,0.0001851485],"domain_scores_gemma":[0.9984133,0.000854845,0.000232083,0.00008040617,0.00004371709,0.0003756565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001719056,0.001816245,0.08481432,0.0007075294,0.0003724976,0.0001403214,0.006456276,0.0000474408,0.0004044901,0.001393489,0.009080542,0.8930478],"study_design_scores_gemma":[0.002849053,0.003865158,0.2975218,0.0002213306,0.000005488659,0.0002407133,0.006003916,0.0004771843,0.00004105775,0.0005119197,0.6882056,0.00005677308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3639664,0.001398644,0.0004798241,0.6337767,0.00003635677,0.0002891217,0.00003973869,0.000001369217,0.00001175457],"genre_scores_gemma":[0.9682548,0.0197476,0.0000913448,0.01183096,0.00005228349,0.000003153391,0.000004417968,0.000004690539,0.00001072993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.892991,"threshold_uncertainty_score":0.1300966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037666819","doi":"10.1007/s11042-022-12156-z","title":"COVID-CXNet: Detecting COVID-19 in frontal chest X-ray images using deep learning","year":2022,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":170,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; Convolutional neural network; Deep learning; Transfer of learning; Artificial intelligence; Pneumonia; Focus (optics); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus; 2019-20 coronavirus outbreak; Pattern recognition (psychology); Artificial neural network; Medicine; Virology; Pathology; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.05061380022961219,"gpt":0.3410276920780757,"spread":0.2904138918484635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005357917,0.0002001916,0.0003345933,0.0002461584,0.0008715845,0.00007249922,0.0001442221,0.00007434769,0.0004953145],"category_scores_gemma":[0.001346056,0.0002244949,0.00007318473,0.0005398002,0.0001302528,0.0001126493,0.0002307536,0.0006200248,0.00001544466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008066511,"about_ca_system_score_gemma":0.0004683303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001355786,"about_ca_topic_score_gemma":0.0001626133,"domain_scores_codex":[0.9983059,0.0001188137,0.0003719914,0.0005578356,0.0002878636,0.0003576387],"domain_scores_gemma":[0.9979141,0.001136071,0.0001560502,0.0003046441,0.00003887487,0.0004502234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002763986,0.00160218,0.2899707,0.0009433519,0.0001477102,0.0002318852,0.01237035,0.1043838,0.1799112,0.000133281,0.001938408,0.4080907],"study_design_scores_gemma":[0.006588677,0.000264377,0.07828788,0.00008108591,0.0002693065,0.0002179245,0.007756516,0.256716,0.001988755,0.0002327119,0.6467025,0.0008942581],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8082936,0.003973157,0.1429904,0.0360291,0.0003001755,0.006460576,0.0004371433,0.0009965446,0.000519332],"genre_scores_gemma":[0.9712482,0.00009063721,0.01739799,0.008996226,0.0002548565,0.001589992,0.0001880353,0.00005747237,0.0001765938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6447641,"threshold_uncertainty_score":0.9154636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380536977","doi":"10.1109/access.2023.3285596","title":"Artificial Intelligence and Biosensors in Healthcare and Its Clinical Relevance: A Review","year":2023,"lang":"en","type":"review","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Innovation and Technology Commission; Research Grants Council, University Grants Committee; Hamad Bin Khalifa University; Qatar National Library; Khalifa University of Science, Technology and Research; Qatar Foundation","keywords":"Computer science; Wearable computer; Health care; Big data; Cloud computing; Data science; Modalities; Artificial intelligence; Relevance (law); Wearable technology; Precision medicine; Data mining; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5076975144256946,"gpt":0.5825827555928399,"spread":0.07488524116714534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001671931,0.0004164856,0.002998237,0.000366404,0.00005481757,0.00006749773,0.0003039243,0.000463459,0.00001383278],"category_scores_gemma":[0.004508415,0.0003443586,0.0002449084,0.001281433,0.000130155,0.0001145462,0.0002229884,0.001102234,0.0001177983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452168,"about_ca_system_score_gemma":0.0006350052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001722182,"about_ca_topic_score_gemma":0.0002222003,"domain_scores_codex":[0.9960085,0.0004531886,0.001852668,0.0009852957,0.0003153081,0.0003850805],"domain_scores_gemma":[0.9957232,0.002845987,0.0004813406,0.000530451,0.0001283463,0.0002906268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009099903,0.00005036028,0.00008015439,0.2131365,0.00003452983,0.0002090859,0.00001113162,1.246734e-7,3.233172e-8,0.00003033909,0.003200925,0.7832377],"study_design_scores_gemma":[0.00005647145,0.00009438452,0.00007586191,0.3010028,0.0005808923,0.00006618806,0.000002281983,0.00002190052,0.000001838826,0.0001388418,0.6976913,0.0002672735],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001288744,0.9792056,0.000004064579,0.01750749,0.0007195913,0.002294724,0.00003707092,0.00009778201,0.000004774354],"genre_scores_gemma":[0.00004753016,0.9885846,0.0000302368,0.01047378,0.0004992204,0.0001975594,0.00002465305,0.00008609896,0.00005630597],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7829704,"threshold_uncertainty_score":0.9999008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3198576039","doi":"10.1148/rg.2021200210","title":"Deep Learning: An Update for Radiologists","year":2021,"lang":"en","type":"article","venue":"Radiographics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Convolutional neural network; Machine learning; Computer science; Segmentation; Terminology; Medical imaging; License; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0350929498110147,"gpt":0.332861459712141,"spread":0.2977685099011263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003520334,0.0001739116,0.0003561844,0.0002622889,0.0001650487,0.00004647522,0.0001158775,0.0001837093,0.00006317841],"category_scores_gemma":[0.0008298449,0.0001734783,0.0002986002,0.0008039424,0.0001387943,0.00008142302,0.00003109348,0.0003181081,0.000009819271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005822482,"about_ca_system_score_gemma":0.0001610259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001629579,"about_ca_topic_score_gemma":0.00004329445,"domain_scores_codex":[0.9986136,0.000108006,0.0002372584,0.0004710083,0.0002045152,0.0003656005],"domain_scores_gemma":[0.9985479,0.0003728005,0.0000763733,0.0005046806,0.0002558746,0.0002424117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001073492,0.004035776,0.7059419,0.001720077,0.001787888,0.002215848,0.002305748,0.005230278,0.01915727,0.02938748,0.09917745,0.1279668],"study_design_scores_gemma":[0.002517927,0.0008314497,0.0330133,0.00008997245,0.0003751257,0.00029012,0.0001382522,0.01309923,0.00226391,0.00119129,0.9458328,0.0003565541],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8319609,0.01380966,0.05885584,0.08985209,0.00173362,0.001621404,0.00003452822,0.001504879,0.0006271381],"genre_scores_gemma":[0.9500512,0.003635799,0.01982645,0.02464692,0.0007201584,0.000106832,0.000566321,0.00009717958,0.000349121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8466554,"threshold_uncertainty_score":0.7074241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3098474649","doi":"10.2196/23811","title":"Role of Machine Learning Techniques to Tackle the COVID-19 Crisis: Systematic Review","year":2020,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Systematic review; CINAHL; MEDLINE; Pandemic; Coronavirus disease 2019 (COVID-19); Epidemiology; Data science; Grey literature; Medicine; Computer science; Disease; Political science; Pathology; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.04515323600969522,"gpt":0.4093970256434307,"spread":0.3642437896337354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003003846,0.0006574682,0.005785959,0.0003419365,0.0001270629,0.00004797324,0.001155856,0.0005745498,0.0004015426],"category_scores_gemma":[0.02016778,0.0003659282,0.0009618834,0.001431889,0.0001507074,0.0000942179,0.0006244981,0.002011144,0.0004108157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005324655,"about_ca_system_score_gemma":0.002653472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004662796,"about_ca_topic_score_gemma":0.000004186799,"domain_scores_codex":[0.9925624,0.0005839542,0.003923102,0.0002702769,0.002225333,0.000434967],"domain_scores_gemma":[0.9932661,0.002095072,0.001861962,0.00121446,0.0002125314,0.001349898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003912737,0.0000637599,3.229499e-7,0.826791,0.0002343737,0.00002436083,0.001244702,1.713869e-7,4.518519e-8,0.00005635331,0.1181325,0.05344849],"study_design_scores_gemma":[0.00009741747,0.0001583322,1.350464e-8,0.406953,0.002596149,0.00024982,0.0002134902,0.00008762888,0.000001130259,0.000006379854,0.5894492,0.0001874169],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[6.214498e-8,0.9500129,0.0004242026,0.04011267,0.00005936526,0.008708255,0.00004612628,0.0003653799,0.0002711007],"genre_scores_gemma":[5.242805e-7,0.7927501,0.0009041004,0.2038846,0.0001389995,0.002054235,0.0001401276,0.00006696459,0.00006030874],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4713167,"threshold_uncertainty_score":0.9998792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035151116","doi":"10.1148/ryai.2020200048","title":"Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT","year":2020,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Vancouver General Hospital","funders":"AstraZeneca; Universidad de Navarra; National Heart, Lung, and Blood Institute; Sunovion; Houston Methodist Research Institute; GlaxoSmithKline; COPD Foundation","keywords":"Ground-glass opacity; Coronavirus disease 2019 (COVID-19); Ground truth; Medicine; Lung; Opacity; Correlation; Radiology; Pearson product-moment correlation coefficient; Nuclear medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Lobe; Artificial intelligence; Pathology; Internal medicine; Mathematics; Computer science; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1252018780608826,"gpt":0.3694180696864446,"spread":0.2442161916255619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003932781,0.0002459988,0.0006405274,0.0001267964,0.0001112055,0.0000183906,0.0002641112,0.0001063526,0.0006470608],"category_scores_gemma":[0.005297588,0.0002222114,0.0001084577,0.0006082815,0.0004092371,0.00007073356,0.00004563316,0.0003245035,0.0001817925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002478515,"about_ca_system_score_gemma":0.0005162909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00137979,"about_ca_topic_score_gemma":0.0003575893,"domain_scores_codex":[0.9977427,0.0002861207,0.0007173399,0.0006544324,0.0002642061,0.0003352542],"domain_scores_gemma":[0.9969822,0.001642231,0.0004059649,0.0004353372,0.000174129,0.0003601634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003968416,0.003298247,0.5986876,0.0009416688,0.00223849,0.003078683,0.0124924,0.04112121,0.269974,0.006739624,0.0278849,0.02957471],"study_design_scores_gemma":[0.0008465612,0.002337593,0.1544007,0.0005678327,0.0009178995,0.0001925069,0.001480437,0.3053983,0.5231131,0.001398706,0.00834401,0.001002297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8826895,0.0001319709,0.06686831,0.04865749,0.0002057444,0.0005421126,0.0001631622,0.0007182546,0.00002341408],"genre_scores_gemma":[0.9834276,0.00004963193,0.0004323849,0.01555655,0.000142771,0.00003237908,0.0003121415,0.00003519435,0.00001132229],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4442869,"threshold_uncertainty_score":0.9061517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091282141","doi":"10.1109/access.2020.3025010","title":"DL-CRC: Deep Learning-Based Chest Radiograph Classification for COVID-19 Detection: A Novel Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Thunder Bay Regional Research Institute; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Chest radiograph; Convolutional neural network; Coronavirus disease 2019 (COVID-19); Radiography; Artificial intelligence; Computer science; Deep learning; Pneumonia; Medicine; Radiology; Pattern recognition (psychology); Pathology; Disease; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.155369235923019,"gpt":0.3796503785839573,"spread":0.2242811426609383,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003421403,0.0002523641,0.0003880902,0.0002842927,0.0002888062,0.0001527194,0.0003570619,0.0001995493,0.0000442429],"category_scores_gemma":[0.001648381,0.0002546857,0.0002532432,0.00119641,0.000116632,0.0002110542,0.00003233924,0.0003667187,0.00001772793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002962289,"about_ca_system_score_gemma":0.0003811848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001439664,"about_ca_topic_score_gemma":0.00003319235,"domain_scores_codex":[0.9981327,0.00006425948,0.000372114,0.0007221473,0.0003674992,0.0003412948],"domain_scores_gemma":[0.998066,0.000570939,0.0002329056,0.000393887,0.0002000686,0.0005362074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01010047,0.007071792,0.1526466,0.01968802,0.001390263,0.000107268,0.007152328,0.2695399,0.3157692,0.0004051536,0.0834965,0.1326325],"study_design_scores_gemma":[0.008035302,0.0006711173,0.03136737,0.00006426098,0.0004658274,0.00002346422,0.0001878333,0.52484,0.01985076,0.00002792598,0.4139426,0.000523549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02245635,0.000148264,0.9157695,0.05908207,0.000297842,0.001530459,0.00001469606,0.0005901992,0.0001105833],"genre_scores_gemma":[0.9356246,0.0000195428,0.00292333,0.05982741,0.0007273004,0.0006713909,0.0001005782,0.00007012868,0.00003571475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9131683,"threshold_uncertainty_score":0.9999905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3028083463","doi":"10.1093/bib/bbaa232","title":"Computational strategies to combat COVID-19: useful tools to accelerate SARS-CoV-2 and coronavirus research","year":2020,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Wellcome Trust; Biotechnology and Biological Sciences Research Council; Intramural Research Program; Agence Nationale de la Recherche; National Institute of Allergy and Infectious Diseases; Medical Research Council; National Institutes of Health; Fondation Innovations en Infectiologie; Max-Planck-Gesellschaft; U.S. National Library of Medicine; Consejo Nacional de Investigaciones Científicas y Técnicas; National Institute of General Medical Sciences; Bundesministerium für Bildung und Forschung; National Human Genome Research Institute; Horizon 2020 Framework Programme; Agencia Nacional de Promoción Científica y Tecnológica; Staatssekretariat für Bildung, Forschung und Innovation; Deutsche Forschungsgemeinschaft; European Commission; European Bioinformatics Institute; Joachim Herz Stiftung; European Molecular Biology Laboratory; Velux Fonden; Carl-Zeiss-Stiftung","keywords":"Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Coronavirus; Betacoronavirus; Pandemic; Virology; Coronavirus Infections; Sars virus; Computer science; Medicine; Infectious disease (medical specialty); Disease; Outbreak","retraction":null,"screen_n_in":null,"score":{"opus":0.4185659936969426,"gpt":0.5144904201730778,"spread":0.09592442647613514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001512667,0.0006795357,0.002340708,0.001284272,0.0002619739,0.001018194,0.0005848019,0.0004636917,0.00003253021],"category_scores_gemma":[0.004428005,0.0006425817,0.0002144025,0.0022193,0.000262076,0.0004838261,0.0009040785,0.001314931,0.0005350658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00143568,"about_ca_system_score_gemma":0.005468281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007139244,"about_ca_topic_score_gemma":0.00009808665,"domain_scores_codex":[0.9952561,0.0002107482,0.001801151,0.000653395,0.001247459,0.0008311696],"domain_scores_gemma":[0.9948749,0.00298447,0.000364102,0.0005977114,0.0003574809,0.0008213448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001383107,0.0001822171,0.00003208363,0.07254691,0.0002021922,0.0003413213,0.005975178,0.0005428006,0.000003565517,0.001711063,0.2616896,0.6566347],"study_design_scores_gemma":[0.0008538497,0.0003935529,0.00007661273,0.01170846,0.0001698891,0.0002111665,0.0002507036,0.001149408,0.000007505546,0.0002100983,0.9843857,0.000583111],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004932478,0.8835856,0.006433654,0.09467048,0.0004000589,0.01188618,0.0009542525,0.0005548975,0.001021676],"genre_scores_gemma":[0.00003965683,0.7919257,0.02480252,0.1820294,0.0001619595,0.0003799204,0.0004897856,0.0001302359,0.00004084406],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7226961,"threshold_uncertainty_score":0.9996026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120506007","doi":"10.1148/radiol.2021203957","title":"The RSNA International COVID-19 Open Radiology Database (RICORD)","year":2021,"lang":"en","type":"article","venue":"Radiology","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Toronto","funders":"National Institutes of Health; National Science Foundation","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Radiology; Generalizability theory; Medical imaging; Medical physics; Radiography; Database; Pathology; Infectious disease (medical specialty); Disease; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06861568055788676,"gpt":0.4014884995381514,"spread":0.3328728189802646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008577411,0.0001776691,0.0004378719,0.0000988129,0.0002786866,0.00006362011,0.0007924958,0.0001643691,0.001382241],"category_scores_gemma":[0.007971505,0.0001342225,0.0001065986,0.0002469852,0.0003709649,0.00008763775,0.0007239255,0.0003689273,0.0001921608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005392665,"about_ca_system_score_gemma":0.00177837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003030787,"about_ca_topic_score_gemma":0.0002481337,"domain_scores_codex":[0.9979684,0.0004648153,0.000375737,0.0006074283,0.0001651456,0.0004184654],"domain_scores_gemma":[0.9954605,0.003022627,0.0001272611,0.0009281692,0.0001510483,0.0003104295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004844761,0.0002312208,0.02512546,0.00004219896,0.0003821687,0.002075134,0.0002392347,0.0001046887,0.005843324,0.02142307,0.9383956,0.005653385],"study_design_scores_gemma":[0.002381159,0.0001444912,0.006561684,0.00001928229,0.00007465317,0.005142028,0.0001187077,0.0004756045,0.0003970329,0.0009503235,0.9835923,0.0001426757],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.05107893,0.004585444,0.005044094,0.9264991,0.005273415,0.0009313485,0.0001538541,0.0002030266,0.006230783],"genre_scores_gemma":[0.3097431,0.006446552,0.006209648,0.6597084,0.0028609,0.0004004015,0.002027555,0.0001043075,0.0124991],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.2667907,"threshold_uncertainty_score":0.9995306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2775469102","doi":"10.1016/j.media.2018.12.007","title":"Learning to detect chest radiographs containing pulmonary lesions using visual attention networks","year":2019,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Guy's and St Thomas' NHS Foundation Trust; National Medical Research Council; Medical Research Council; Centro de Investigación Biomédica en Red de Salud Mental; University College London; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Cancer Research UK; King's College London; King's University College; King's College Hospital NHS Foundation Trust","keywords":"Softmax function; Artificial intelligence; Radiography; Computer science; Convolutional neural network; Deep learning; Bounding overwatch; Pattern recognition (psychology); Chest radiograph; Nodule (geology); Radiology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01717862914978598,"gpt":0.3354733133084721,"spread":0.3182946841586862,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001272122,0.0002645801,0.0008426104,0.001227528,0.000222,0.00007845804,0.0001873423,0.0002432044,0.001741347],"category_scores_gemma":[0.00154904,0.0002457112,0.0007407244,0.003870555,0.0001153196,0.0001483637,0.0001752456,0.0007452492,0.0001380794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002160308,"about_ca_system_score_gemma":0.0001604405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007569455,"about_ca_topic_score_gemma":0.00005894699,"domain_scores_codex":[0.996887,0.0002548344,0.0005589613,0.0006843617,0.001041443,0.0005734103],"domain_scores_gemma":[0.9978971,0.0006056352,0.0001560211,0.0004189853,0.0001903033,0.000731979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003170529,0.0004429833,0.778053,0.0001615491,0.00331896,0.001521013,0.0003723239,0.02248846,0.03100012,0.000003388992,0.0009638798,0.1613573],"study_design_scores_gemma":[0.0008205824,0.0003689812,0.1485877,0.0004202176,0.004243428,0.00005321774,0.0004398797,0.8410237,0.0001963536,0.000003202659,0.003521976,0.0003207291],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8376007,0.0002581725,0.155626,0.005749913,0.0001381647,0.0003172609,0.000001098557,0.0001841214,0.0001245207],"genre_scores_gemma":[0.9875542,0.00009414442,0.003366133,0.008239152,0.0003212749,0.00001925107,0.00009285208,0.00004942886,0.000263567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8185353,"threshold_uncertainty_score":0.9999995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197562226","doi":"10.3390/bdcc5030041","title":"A Review of Artificial Intelligence, Big Data, and Blockchain Technology Applications in Medicine and Global Health","year":2021,"lang":"en","type":"review","venue":"Big Data and Cognitive Computing","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Big data; Computer science; Context (archaeology); Data science; Wearable technology; Health care; Cloud computing; Analytics; Applications of artificial intelligence; Protocol (science); Artificial intelligence; Field (mathematics); Wearable computer; Medicine; Data mining; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.3100406218550014,"gpt":0.485184447604534,"spread":0.1751438257495326,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001491465,0.0003463886,0.002449865,0.0003806853,0.0001083128,0.00001840995,0.0003794355,0.0001891316,0.000003409594],"category_scores_gemma":[0.002895965,0.0002925168,0.00003553604,0.001656113,0.0005289324,0.0000224844,0.002365697,0.0004275915,0.00000110185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005985223,"about_ca_system_score_gemma":0.0009446073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001874172,"about_ca_topic_score_gemma":0.0001800732,"domain_scores_codex":[0.9969181,0.0002390225,0.001164722,0.00120246,0.0001928148,0.0002829004],"domain_scores_gemma":[0.9966735,0.001345942,0.0006124248,0.001015424,0.0001999527,0.0001527864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002644504,0.00008699945,0.0001106471,0.07460165,0.00009311701,0.00001885624,0.00003107157,6.312807e-9,6.737502e-8,0.0001722565,0.0006685304,0.9242141],"study_design_scores_gemma":[0.0001595041,0.0001005677,0.00002690497,0.3913942,0.00115263,0.000222594,0.0003478994,0.0003068195,1.961631e-7,0.0001041437,0.6060072,0.0001772762],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001310002,0.97149,0.02043557,0.004546311,0.0001013137,0.001565542,0.001804803,0.00002927645,0.00001406153],"genre_scores_gemma":[0.0002345433,0.9896273,0.0006058484,0.004043079,0.0004142497,0.00002940155,0.005023564,0.00002092424,0.000001080836],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9240369,"threshold_uncertainty_score":0.9999527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3202962003","doi":"10.1145/3465398","title":"A Survey on Applications of Artificial Intelligence in Fighting Against COVID-19","year":2021,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Pandemic; Computer science; Big data; Scope (computer science); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data science; 2019-20 coronavirus outbreak; Transmission (telecommunications); Applications of artificial intelligence; Artificial intelligence; Outbreak; Disease; Infectious disease (medical specialty); Virology; Medicine; Data mining; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.1946503451717503,"gpt":0.445800451926725,"spread":0.2511501067549746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01113145,0.0005673449,0.002943933,0.000879447,0.0001480755,0.00005769835,0.0007019702,0.0004440687,0.00005121272],"category_scores_gemma":[0.03263218,0.0005610921,0.0005179408,0.003179435,0.0001457843,0.00002502271,0.0006326262,0.001067037,0.00006006891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008601064,"about_ca_system_score_gemma":0.003057715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002161862,"about_ca_topic_score_gemma":0.001079392,"domain_scores_codex":[0.9912472,0.004476825,0.002020802,0.001155872,0.0005658588,0.0005334818],"domain_scores_gemma":[0.9696202,0.02677377,0.001013025,0.00195314,0.0003417634,0.0002981234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004385368,0.0004598935,0.001079837,0.01076036,0.0001052307,0.00009183461,0.0001351755,0.0005502508,4.480385e-7,0.00007510357,0.0009698053,0.9857677],"study_design_scores_gemma":[0.0002922964,0.0001756056,0.003481229,0.05814915,0.0004407127,0.00003650167,0.00005806002,0.001957451,0.00001420629,0.0001056691,0.9341787,0.001110423],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000130035,0.963834,0.032286,0.0007220381,0.0003653312,0.002085238,0.0003445446,0.0001737198,0.00005909756],"genre_scores_gemma":[0.00191227,0.9885464,0.002269112,0.003199647,0.0004409649,0.0001239556,0.003302962,0.0001624192,0.0000422247],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9846572,"threshold_uncertainty_score":0.999684,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2514505281","doi":"10.5588/ijtld.15.0926","title":"Computer-aided detection of pulmonary tuberculosis on digital chest radiographs: a systematic review","year":2016,"lang":"en","type":"review","venue":"The International Journal of Tuberculosis and Lung Disease","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canada Research Chairs","keywords":"Medicine; Tuberculosis; CAD; Pulmonary tuberculosis; Human immunodeficiency virus (HIV); Radiography; Receiver operating characteristic; MEDLINE; Systematic review; Medical physics; Internal medicine; Radiology; Pathology; Virology","retraction":null,"screen_n_in":null,"score":{"opus":0.01951200839345262,"gpt":0.3200688199235718,"spread":0.3005568115301192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008484142,0.0004726499,0.002410799,0.0006758112,0.00006558791,0.0001173941,0.0006316857,0.000116873,0.00003688041],"category_scores_gemma":[0.0008938524,0.0002461447,0.002016076,0.0003075335,0.0001417318,0.0002182321,0.0001490362,0.0004042509,0.0000138435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000433794,"about_ca_system_score_gemma":0.0002979749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009048755,"about_ca_topic_score_gemma":3.474354e-7,"domain_scores_codex":[0.9961023,0.0002889886,0.0018304,0.0003313604,0.001251634,0.0001952918],"domain_scores_gemma":[0.995228,0.001410041,0.001850319,0.0005312731,0.0006310217,0.0003493312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002329109,0.0007005501,0.00007754927,0.6707585,0.005819371,0.0003399417,0.00002633,0.000002337914,0.000006696137,0.00002660412,0.00237731,0.3196319],"study_design_scores_gemma":[0.000468071,0.0001821277,0.0002266859,0.9350877,0.01719576,0.001221106,0.000005650761,0.0001794536,0.000004258632,0.00003294397,0.04512813,0.0002681185],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001873147,0.9904456,0.0001021192,0.007156999,0.0005767047,0.00130477,0.0001877774,0.00001803857,0.00002069093],"genre_scores_gemma":[0.006788757,0.9894313,0.00001249615,0.002886994,0.0006845467,0.00007342768,0.00003400438,0.00005804909,0.00003045796],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3193637,"threshold_uncertainty_score":0.9999991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036790661","doi":"10.59275/j.melba.2020-48g7","title":"COVID-19 Image Data Collection: Prospective Predictions are the Future","year":2020,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; Université de Montréal","funders":"Compute Canada; Canadian Institute for Advanced Research","keywords":"Metadata; Coronavirus disease 2019 (COVID-19); Data collection; Computer science; Resource (disambiguation); Data science; Code (set theory); Intensive care unit; Medicine; Medical physics; Medical emergency; Information retrieval; Artificial intelligence; Intensive care medicine; World Wide Web; Disease; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.03905790863781753,"gpt":0.3697702149244061,"spread":0.3307123062865886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004512691,0.0004575744,0.0009080207,0.0003774221,0.001216358,0.0002025249,0.001715946,0.0002216547,0.0001731148],"category_scores_gemma":[0.01748254,0.0002569855,0.0004460812,0.0007705056,0.0008339927,0.0001740488,0.001841085,0.006010998,0.000008304047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009289461,"about_ca_system_score_gemma":0.003226576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002509303,"about_ca_topic_score_gemma":0.00002311892,"domain_scores_codex":[0.9959441,0.0007171099,0.001041581,0.0005832785,0.001270075,0.0004438998],"domain_scores_gemma":[0.9930391,0.002565827,0.001816355,0.001123461,0.0006204338,0.0008348483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002559711,0.0006214273,0.01668695,0.002203318,0.001872276,0.0004400926,0.004844059,0.002492706,0.000611301,0.00004042862,0.9600375,0.007590245],"study_design_scores_gemma":[0.003483721,0.000479906,0.005006555,0.0009974821,0.002848606,0.002451492,0.002067909,0.2043349,0.00002819263,0.001304397,0.7766981,0.0002987169],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.0006230681,0.005623883,0.1566202,0.8329017,0.002362306,0.001366926,0.0002634614,0.0001893232,0.00004918189],"genre_scores_gemma":[0.6872095,0.00953888,0.03290452,0.2113638,0.05364275,0.0003064842,0.002753128,0.0007582913,0.001522655],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.6865864,"threshold_uncertainty_score":0.9999883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3169061343","doi":"10.12700/aph.18.5.2021.5.3","title":"Robotics and Intelligent Systems Against a Pandemic","year":2021,"lang":"en","type":"article","venue":"Acta Polytechnica Hungarica","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick; General Motors (Canada)","funders":"Emberi Eroforrások Minisztériuma; Magyar Tudományos Akadémia","keywords":"Robotics; Artificial intelligence; Pandemic; Computer science; Coronavirus disease 2019 (COVID-19); Engineering; Robot; Medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.0367094453038945,"gpt":0.308281143179252,"spread":0.2715716978753575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002495642,0.0002358456,0.0004922313,0.0001529081,0.0001175162,0.0000818042,0.0001513,0.0002415703,0.000029894],"category_scores_gemma":[0.0007542868,0.0002252691,0.0001135007,0.0004544892,0.0001228398,0.00006115995,0.0002747771,0.0004743656,0.00003271579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002587617,"about_ca_system_score_gemma":0.0003889594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007160748,"about_ca_topic_score_gemma":0.00001687968,"domain_scores_codex":[0.9982262,0.00007234202,0.000423835,0.0005333507,0.0003478949,0.0003963387],"domain_scores_gemma":[0.9981181,0.0004828344,0.0001190896,0.0008438262,0.000154445,0.0002817112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003287252,0.003027421,0.06232474,0.002165301,0.001233047,0.002460673,0.001443403,0.001546245,0.5932024,0.004210541,0.2441065,0.08395106],"study_design_scores_gemma":[0.001799411,0.0004713139,0.01619027,0.00147771,0.0007731983,0.001315225,0.0004350936,0.00864711,0.01467095,0.0001202957,0.953218,0.0008814271],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4722178,0.06259616,0.02400044,0.4116155,0.00380306,0.00564005,0.0001115887,0.006173099,0.01384226],"genre_scores_gemma":[0.9817616,0.003269731,0.001916776,0.01184381,0.0001622053,0.00004037157,0.00002985314,0.00005456173,0.0009210689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7091115,"threshold_uncertainty_score":0.9186209,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224323274","doi":"10.3390/jpm12050680","title":"LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images","year":2022,"lang":"en","type":"article","venue":"Journal of Personalized Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"","keywords":"Artificial intelligence; Lung; Multiclass classification; Receiver operating characteristic; Interstitial lung disease; Medicine; Convolutional neural network; Idiopathic pulmonary fibrosis; Pattern recognition (psychology); Computer science; Machine learning; Support vector machine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.08158924079320526,"gpt":0.3674047390791457,"spread":0.2858154982859404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001207002,0.0001711519,0.0006028677,0.0004417422,0.0001682075,0.000007391056,0.0001024379,0.00004640431,0.00006915932],"category_scores_gemma":[0.001438268,0.000140367,0.0001807874,0.000259157,0.0002258521,0.0001348364,0.00004311321,0.000288461,6.446148e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004751386,"about_ca_system_score_gemma":0.0005784327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002461456,"about_ca_topic_score_gemma":0.000001099411,"domain_scores_codex":[0.9978653,0.0001039824,0.0007766847,0.0002307854,0.0008263868,0.0001969031],"domain_scores_gemma":[0.9977361,0.0004479403,0.0007632117,0.0001954673,0.0005451924,0.0003121122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01438518,0.001542132,0.04004722,0.00339631,0.0007812845,0.0001558974,0.009678548,0.01718029,0.824362,0.0003086884,0.08511201,0.003050378],"study_design_scores_gemma":[0.01265585,0.0007318041,0.02020721,0.0008171406,0.001993084,0.000128297,0.0008854894,0.9581627,0.0002139916,0.00009706336,0.004004948,0.0001024088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8425235,0.007723237,0.06986842,0.07765961,0.0006205883,0.001277337,0.000261736,0.00004932301,0.00001625641],"genre_scores_gemma":[0.9900903,0.0002607293,0.006492429,0.002243807,0.0004847923,0.00003784236,0.00003887315,0.00003899445,0.000312213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9409824,"threshold_uncertainty_score":0.5723999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3134978274","doi":"10.3389/fmed.2021.629134","title":"The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective","year":2021,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver General Hospital; University of Manitoba; Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Overfitting; Deep learning; Artificial intelligence; Computer science; Coronavirus disease 2019 (COVID-19); Transformation (genetics); Machine learning; Training set; Perspective (graphical); Artificial neural network; Image (mathematics); Geometric transformation; Early stopping; Pattern recognition (psychology); Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01561574484348434,"gpt":0.3347402999070178,"spread":0.3191245550635335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004046949,0.0001520362,0.0005657412,0.0007097416,0.0001523202,0.0000124614,0.00008663444,0.0001063498,0.00001189561],"category_scores_gemma":[0.01773787,0.0001233334,0.00008337198,0.002090435,0.0001748981,0.0001201223,0.00001825857,0.0004051989,2.652667e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001639596,"about_ca_system_score_gemma":0.0002547363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004689298,"about_ca_topic_score_gemma":0.000209631,"domain_scores_codex":[0.9979995,0.0005698212,0.0005003871,0.000307714,0.0003195517,0.000303033],"domain_scores_gemma":[0.9950998,0.004145083,0.000172825,0.000180273,0.0002936919,0.0001083166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01769905,0.001049078,0.3868767,0.01004673,0.0008416334,0.0003776296,0.06381603,0.1991842,0.018629,0.001386552,0.004547297,0.2955461],"study_design_scores_gemma":[0.0488956,0.002624183,0.2807481,0.005027371,0.0008261827,0.0000906813,0.1589107,0.474049,0.01573171,0.005477261,0.006976012,0.0006431945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07358105,0.006644945,0.9074005,0.01003594,0.0007107041,0.001436333,0.000001530241,0.00004032008,0.0001486285],"genre_scores_gemma":[0.993319,0.0009079367,0.004037207,0.001275782,0.0001316725,0.0002325753,0.00004876215,0.00002788314,0.00001916785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9197379,"threshold_uncertainty_score":0.9905362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3141346607","doi":"10.1109/rbme.2021.3069815","title":"A Wearable Tele-Health System towards Monitoring COVID-19 and Chronic Diseases","year":2021,"lang":"en","type":"article","venue":"IEEE Reviews in Biomedical Engineering","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wearable computer; Telehealth; Pandemic; Disease; Remote patient monitoring; Wearable technology; Telemedicine; Coronavirus disease 2019 (COVID-19); Continuous monitoring","retraction":null,"screen_n_in":null,"score":{"opus":0.0419620570526319,"gpt":0.3560694592686865,"spread":0.3141074022160546,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008483639,0.0002652392,0.000991966,0.0002657795,0.00006703394,0.00003453014,0.0001141108,0.000132532,0.00003440167],"category_scores_gemma":[0.002094324,0.0002386163,0.0001333401,0.0009208306,0.00006716602,0.00007082281,0.00007900262,0.0003861373,0.00002109103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002291908,"about_ca_system_score_gemma":0.001553478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001600369,"about_ca_topic_score_gemma":0.000006274113,"domain_scores_codex":[0.9976678,0.0001103377,0.0007351067,0.0005219436,0.0004235569,0.0005412734],"domain_scores_gemma":[0.9980404,0.0002911601,0.00009842913,0.0004314247,0.00003378784,0.001104841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006038546,0.00108458,0.01099964,0.2436597,0.0002938034,0.004621996,0.001167189,0.003327929,0.01861485,0.0002969103,0.02219057,0.6936824],"study_design_scores_gemma":[0.001798406,0.0001635842,0.003056886,0.02403148,0.0001044366,0.0004247281,0.00006190756,0.01290141,0.0006617,0.000003610757,0.95644,0.0003518437],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.02479156,0.9099134,0.02117725,0.03841918,0.00320024,0.00173075,0.0000369333,0.0007043412,0.00002629977],"genre_scores_gemma":[0.5725626,0.3936014,0.0158554,0.01148384,0.004997988,0.0009616508,0.00006434252,0.0002403977,0.0002323588],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9342495,"threshold_uncertainty_score":0.9730492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3048538617","doi":"10.1016/j.compbiomed.2020.103960","title":"COVID-19 pathways for brain and heart injury in comorbidity patients: A role of medical imaging and artificial intelligence-based COVID severity classification: A review","year":2020,"lang":"en","type":"review","venue":"Computers in Biology and Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":109,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"AllerGen; Queen's University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Comorbidity; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Betacoronavirus; Medical emergency; Artificial intelligence; Intensive care medicine; Computer science; Psychiatry; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.124185283888595,"gpt":0.4452115303360742,"spread":0.3210262464474792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002354066,0.0003797408,0.002678263,0.000417781,0.00006647741,0.000006236994,0.0001928746,0.0004081836,0.00002951243],"category_scores_gemma":[0.008959904,0.000299205,0.0001072114,0.0004775452,0.001203675,0.00002881387,0.0001911471,0.0006313163,5.227613e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002518562,"about_ca_system_score_gemma":0.001602364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000165881,"about_ca_topic_score_gemma":0.00004233862,"domain_scores_codex":[0.9967903,0.0006312329,0.001269965,0.0007990177,0.0002320149,0.0002774222],"domain_scores_gemma":[0.9948547,0.003760173,0.0003880552,0.000295511,0.00008146469,0.0006200299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001169297,0.0001910627,0.003553484,0.05376499,0.00003427402,0.00002590238,0.0002547046,7.135947e-8,0.000002910104,0.0009285164,0.006771146,0.934356],"study_design_scores_gemma":[0.001179628,0.0006440978,0.0006302632,0.05208799,0.0003047182,0.00006488484,0.00005667153,0.002294864,8.622791e-7,0.001525586,0.9409676,0.0002427902],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000129422,0.872446,0.003556243,0.1214648,0.0002420597,0.002038686,0.0000894671,0.00003036374,0.000002902981],"genre_scores_gemma":[0.0009959253,0.9170362,0.0007040557,0.08041305,0.000200668,0.0001691223,0.0004605436,0.00002012942,2.433229e-7],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9341965,"threshold_uncertainty_score":0.999946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200587732","doi":"10.1038/s41598-021-03265-0","title":"Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Global Affairs Canada; European Commission","keywords":"CAD; Software; Computer science; Medical physics; Medicine; Artificial intelligence; Engineering drawing; Operating system; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1196407561490396,"gpt":0.3737925386569035,"spread":0.254151782507864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005761217,0.0000725148,0.000169663,0.0001496791,0.0002586728,0.00003933148,0.00005343555,0.00005991598,0.0001309358],"category_scores_gemma":[0.003808973,0.00005796561,0.0001709932,0.000598643,0.0002137456,0.00006439399,0.00005887349,0.00007626099,0.000002417908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609029,"about_ca_system_score_gemma":0.0008806754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001018814,"about_ca_topic_score_gemma":0.0005080938,"domain_scores_codex":[0.997663,0.00007772638,0.0006259289,0.0004027667,0.001055418,0.0001751876],"domain_scores_gemma":[0.9967186,0.0002896434,0.0003405742,0.0007616905,0.001844032,0.00004538685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003765059,0.0005216138,0.0009851629,0.0001699916,0.0001149294,0.00001466594,0.0008615656,0.006765078,0.7980012,0.0002501483,0.001482041,0.190796],"study_design_scores_gemma":[0.00008359412,0.00005447979,0.005168614,0.0001188732,0.0006579214,0.0001028038,0.0005140404,0.03097247,0.9472552,0.01129778,0.003709425,0.0000647886],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8870324,0.001652383,0.08747412,0.009131687,0.01229938,0.002194646,0.00001234375,0.0000495081,0.0001535444],"genre_scores_gemma":[0.9993368,0.0000100315,0.0002643741,0.00007851273,0.00006921585,0.00009721963,0.00002285762,0.000008214433,0.0001127517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1907312,"threshold_uncertainty_score":0.4559972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121590924","doi":"10.3389/fmed.2021.729287","title":"COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 From Chest CT Images Through Bigger, More Diverse Learning","year":2022,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hamilton Health Sciences; McMaster University; Niagara Health System; University of Waterloo","funders":"Frederick National Laboratory for Cancer Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Leverage (statistics); Deep learning; Cohort; Computer science; Coronavirus disease 2019 (COVID-19); Artificial neural network; Benchmark (surveying); Machine learning; Medical physics; Clickstream; Medicine; Radiology; Geography; The Internet; Cartography; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.02623701137377057,"gpt":0.3202239473200387,"spread":0.2939869359462681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009732894,0.000371313,0.001146333,0.0004645621,0.0004173718,0.00001109493,0.0003317392,0.00007756319,0.0004520344],"category_scores_gemma":[0.004893949,0.0003629457,0.0001886312,0.0009533394,0.0005289553,0.0001461544,0.0002084378,0.0009425417,0.00000101947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386206,"about_ca_system_score_gemma":0.0002909724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00415037,"about_ca_topic_score_gemma":0.0001373102,"domain_scores_codex":[0.9968589,0.0003227,0.0007440498,0.0007753645,0.0007310617,0.000567918],"domain_scores_gemma":[0.9974145,0.001105991,0.0004691396,0.0005214085,0.0001039466,0.0003850468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006090239,0.0009020328,0.115349,0.001645001,0.0007544618,0.001126092,0.02031859,0.4615582,0.02347197,0.00001250785,0.2867438,0.0820282],"study_design_scores_gemma":[0.03209184,0.003835422,0.009864278,0.0004632253,0.001598242,0.0001189687,0.04107153,0.5199651,0.009174065,0.0007675363,0.3800091,0.001040732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2305055,0.008757534,0.7144977,0.03811888,0.00546944,0.00217516,0.0000899075,0.0003268132,0.00005910957],"genre_scores_gemma":[0.9673342,0.0005644402,0.004487952,0.02574927,0.0007246151,0.000378489,0.0004898809,0.00008291502,0.0001883098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7368286,"threshold_uncertainty_score":0.9998822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186482562","doi":"10.1186/s12967-021-02992-2","title":"Self-supervised deep learning model for COVID-19 lung CT image segmentation highlighting putative causal relationship among age, underlying disease and COVID-19","year":2021,"lang":"en","type":"article","venue":"Journal of Translational Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Medical Service Foundation","keywords":"Artificial intelligence; Deep learning; Computer science; Segmentation; Coronavirus disease 2019 (COVID-19); Machine learning; Medicine; Pattern recognition (psychology); Disease; Pathology; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.09401131649259753,"gpt":0.3989374486889927,"spread":0.3049261321963951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00161312,0.0002911539,0.0006322954,0.0005204798,0.0005827207,0.00006190097,0.00009459828,0.00008659975,0.0001006261],"category_scores_gemma":[0.009018946,0.0002629501,0.0002064483,0.0004688914,0.0002271784,0.0005520629,0.00001944849,0.000530996,7.033989e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007450105,"about_ca_system_score_gemma":0.002343349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003105546,"about_ca_topic_score_gemma":0.00004847974,"domain_scores_codex":[0.9968641,0.0003261846,0.001088343,0.000414258,0.0009977685,0.0003093552],"domain_scores_gemma":[0.9918668,0.00543334,0.000612404,0.0001476738,0.0006369756,0.001302766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00306831,0.0007731232,0.3666247,0.0084192,0.001597568,0.004660416,0.05717244,0.5362891,0.009558896,0.003328098,0.004801309,0.003706859],"study_design_scores_gemma":[0.01524315,0.0003222913,0.06528809,0.0007304111,0.002567162,0.0004615342,0.002755997,0.9043197,0.00007898131,0.00665777,0.001246923,0.0003280106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1048059,0.002339118,0.7362465,0.1555898,0.0001558932,0.000720223,0.00002782306,0.00007979663,0.00003496447],"genre_scores_gemma":[0.8984435,0.0002876713,0.08744004,0.01275184,0.0004513986,0.00003527604,0.0003854001,0.0000603908,0.0001445317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7936376,"threshold_uncertainty_score":0.9999823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380758096","doi":"10.1016/j.inffus.2023.101880","title":"FTransCNN: Fusing Transformer and a CNN based on fuzzy logic for uncertain medical image segmentation","year":2023,"lang":"en","type":"article","venue":"Information Fusion","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":104,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Fuzzy logic; Transformer; Scale-space segmentation; Image segmentation; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.03324935523160569,"gpt":0.345530683033493,"spread":0.3122813278018873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006484366,0.0001400921,0.0001766132,0.0004102347,0.0001833658,0.00005524407,0.0000502897,0.0001433246,0.0002124292],"category_scores_gemma":[0.0004051294,0.0001191942,0.0000777821,0.0003973025,0.00005159255,0.0004525671,0.00000867244,0.0001279461,0.0001237278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000122992,"about_ca_system_score_gemma":0.0001831473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003476463,"about_ca_topic_score_gemma":0.00000756834,"domain_scores_codex":[0.9986194,0.00002579513,0.0003920812,0.0001424322,0.0005975833,0.0002226759],"domain_scores_gemma":[0.9991645,0.0003452394,0.00008307125,0.0001347337,0.0001274071,0.0001450613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002925009,0.0004086494,0.00116803,0.004281296,0.0000655791,0.00004620488,0.01109393,0.003935701,0.05004708,0.001401612,0.0564307,0.8681962],"study_design_scores_gemma":[0.01840263,0.001765472,0.01179779,0.001767125,0.0002171811,0.00003686085,0.002049207,0.808744,0.02071415,0.0008970741,0.1329907,0.0006178328],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4835571,0.00004801166,0.1892016,0.3131203,0.0009262055,0.00540322,0.0001637862,0.001336282,0.006243552],"genre_scores_gemma":[0.889158,0.0002476818,0.007709553,0.099857,0.000217619,0.0003499329,0.002310919,0.00004146124,0.0001079198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8675784,"threshold_uncertainty_score":0.4860597,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}