{"id":"W4380304133","doi":"10.2139/ssrn.4473138","title":"Characterization of Long Covid Temporal Sub-Phenotypes by Distributed Learning from Electronic Health Record Data","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Electronic health record; Phenotype; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Health records; 2019-20 coronavirus outbreak; Characterization (materials science); Virology; Biology; Medicine; Genetics; Political science; Infectious disease (medical specialty); Health care; Pathology; Nanotechnology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00606769,0.000569919,0.001007138,0.000343326,0.0005478589,0.0003615441,0.004879002,0.0005458425,0.00001931063],"category_scores_gemma":[0.0006204012,0.0006011336,0.000186485,0.0007000703,0.00006520351,0.0005950197,0.002719038,0.01597911,0.00003369601],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003465648,"about_ca_system_score_gemma":0.01967458,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008678849,"about_ca_topic_score_gemma":0.008024432,"domain_scores_codex":[0.9905609,0.001669051,0.001489905,0.00147465,0.0009592673,0.003846194],"domain_scores_gemma":[0.9942731,0.0002878395,0.002910606,0.001911485,0.0002841807,0.0003327453],"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":[0.0005400465,0.0006674944,0.4045479,0.001657632,0.002947334,0.00008145901,0.002919109,0.01012938,0.005042228,0.03799117,0.003217468,0.5302588],"study_design_scores_gemma":[0.003972253,0.004619238,0.08855692,0.002749143,0.0003287391,0.0005700548,0.0008241276,0.5357024,0.000678267,0.3277135,0.02959268,0.00469264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1649115,0.003953029,0.8171335,0.01165249,0.001034306,0.0004808917,0.0004029408,0.00042781,0.000003541477],"genre_scores_gemma":[0.9549453,0.02394197,0.0009754116,0.0002293198,0.0006758855,0.0000210905,0.01876202,0.0001324197,0.0003166446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8161581,"threshold_uncertainty_score":0.999644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03327289252343887,"score_gpt":0.3078410859899465,"score_spread":0.2745681934665076,"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."}}