{"id":"W3120666722","doi":"10.21203/rs.3.rs-126892/v1","title":"Federated Learning used for predicting outcomes in SARS-COV-2 patients","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Schwartz/Reisman Emergency Medicine Institute; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institutes of Health; Department of Health and Social Care; National Institute of Allergy and Infectious Diseases; Lunit; Nvidia; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Massachusetts General Hospital","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; Data set; Health care; Set (abstract data type); Anonymity; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data sharing; Artificial intelligence; Pandemic; 2019-20 coronavirus outbreak; Federated learning; Data science; Machine learning; Medicine; Computer security; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004990855,0.0007728486,0.001448227,0.001225482,0.0005263005,0.001578287,0.001059741,0.001220054,0.002039982],"category_scores_gemma":[0.01299805,0.0002272331,0.001105216,0.0007714197,0.0003613313,0.001366297,0.001147016,0.00135117,0.0006710735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007205321,"about_ca_system_score_gemma":0.001349186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003146793,"about_ca_topic_score_gemma":0.002614541,"domain_scores_codex":[0.9979976,0.000813166,0.0001915887,0.0005040533,0.000243004,0.0002505661],"domain_scores_gemma":[0.9946249,0.002995366,0.0004013816,0.001039693,0.0006069032,0.0003317386],"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":[0.01003286,0.002648171,0.2892028,0.0002473933,0.001179658,0.000656385,0.0002685101,0.2441904,0.003410263,0.003036834,0.01232381,0.4328029],"study_design_scores_gemma":[0.0001597166,0.0009762966,0.01819847,0.0000598077,0.0002210258,0.0002872489,0.0001416238,0.9677745,0.003375643,0.007576606,0.001192271,0.00003688787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8741605,0.001435542,0.1121043,0.002185224,0.0004581789,0.0002040394,0.005137439,0.001811762,0.002502967],"genre_scores_gemma":[0.9810739,0.0001681208,0.01512079,0.000184679,0.00009518963,0.00004880983,0.00246117,0.00001705133,0.0008304254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004990855,"threshold_uncertainty_score":0.02639449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1304221671819538,"score_gpt":0.4164207460242476,"score_spread":0.2859985788422937,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}