{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00383388,0.000284169,0.0005001153,0.001722371,0.00038795,0.001159459,0.000961093,0.000751054,0.001003536],"category_scores_gemma":[0.01805376,0.0001997207,0.000523607,0.001582838,0.000483606,0.001123051,0.001086397,0.0009505348,0.000358026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005035438,"about_ca_system_score_gemma":0.0007819952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00338912,"about_ca_topic_score_gemma":0.004456181,"domain_scores_codex":[0.9984546,0.0005779214,0.0001411744,0.000450678,0.0002133643,0.0001622795],"domain_scores_gemma":[0.9789678,0.01425761,0.00233856,0.001876839,0.001874999,0.0006840285],"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":[0.0009172292,0.0004759403,0.8646861,0.0001281042,0.0002503131,0.0005618343,0.000434814,0.02311342,0.009585666,0.004322125,0.002974027,0.09255051],"study_design_scores_gemma":[0.0000534537,0.0002734453,0.4163558,0.00004728538,0.0001196825,0.0006375525,0.0006803612,0.5592656,0.002856574,0.01779762,0.00188038,0.00003226733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9368111,0.0004815674,0.05831591,0.0009384121,0.0000425497,0.00006083969,0.002419814,0.0001801256,0.0007495199],"genre_scores_gemma":[0.9894997,0.0000907718,0.007035884,0.00006442604,0.00003636023,0.0000390842,0.002766038,0.00002405245,0.0004435839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00383388,"threshold_uncertainty_score":0.02027571,"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."}}