{"id":"W4225131847","doi":"10.1101/2022.04.23.22274218","title":"Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review","year":2022,"lang":"en","type":"review","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Machine learning; Artificial intelligence; Computer science; Scalability; Data science; Health records; Deep learning; Electronic health record; Health care; Data mining; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02668994,0.001594603,0.002948158,0.02009708,0.0007897068,0.003770065,0.003089407,0.002277747,0.003766371],"category_scores_gemma":[0.07888038,0.0009474877,0.003357863,0.01528713,0.001912868,0.005582127,0.002455627,0.003305781,0.001111082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003861448,"about_ca_system_score_gemma":0.008475914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003251194,"about_ca_topic_score_gemma":0.003457814,"domain_scores_codex":[0.9864947,0.006383855,0.00308127,0.00106462,0.0027608,0.0002149415],"domain_scores_gemma":[0.8756014,0.1083854,0.004818295,0.002195873,0.008609378,0.0003898078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00007972985,0.00007863206,0.001405018,0.1747958,0.00197437,0.0001554775,0.0003492431,0.001319119,0.0002457774,0.01900532,0.03057013,0.7700214],"study_design_scores_gemma":[0.00008182806,0.0001844641,0.00512384,0.4051203,0.005019523,0.001102755,0.0004542062,0.003070827,0.0007828242,0.0311004,0.5477428,0.0002162123],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001242445,0.9915656,0.004506222,0.002370056,0.0005743791,0.00009174837,0.0001258698,0.00002604892,0.0006159262],"genre_scores_gemma":[0.00358141,0.984082,0.009583728,0.001252747,0.0007734938,0.0003702566,0.0001570532,0.00001989655,0.0001795093],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.02668994,"threshold_uncertainty_score":0.1411515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2022358419498459,"score_gpt":0.4105729637999238,"score_spread":0.2083371218500779,"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."}}