{"id":"W4294243523","doi":"10.23889/ijpds.v7i3.1851","title":"Developing Machine Learning Algorithms on Routinely Collected Administrative Health Data - Lessons from Ontario, Canada.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Machine learning; Health care; Artificial intelligence; Computer science; Timeline; Population health; Decision tree; Feature (linguistics); Multidisciplinary approach; Medicine; Population; Data science; Data mining; Statistics; Mathematics; Environmental health; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.006942658,0.001091278,0.0006217181,0.001717188,0.001756487,0.002137345,0.002059004,0.0007137314,0.001649206],"category_scores_gemma":[0.02557661,0.000682051,0.001034898,0.00383355,0.0009605638,0.001285047,0.0009678002,0.001537998,0.0007197641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03597254,"about_ca_system_score_gemma":0.06913984,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9897202,"about_ca_topic_score_gemma":0.990281,"domain_scores_codex":[0.9975854,0.0005327161,0.0001804429,0.0003919297,0.001009142,0.0003004058],"domain_scores_gemma":[0.985526,0.005200188,0.0005137516,0.0009560396,0.007210305,0.0005936893],"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":[0.0002356997,0.0001957945,0.171782,0.0007284834,0.0005637686,0.0004486721,0.001551531,0.2370307,0.001018329,0.01468603,0.1598244,0.4119346],"study_design_scores_gemma":[0.0001331134,0.0001057607,0.08908152,0.000484549,0.0002251442,0.0001359376,0.001744911,0.8186802,0.00176081,0.01405581,0.07348336,0.0001089689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4406656,0.03017701,0.343991,0.06469114,0.001489268,0.001913979,0.05894814,0.007400974,0.05072287],"genre_scores_gemma":[0.7088931,0.009101893,0.2312706,0.002154137,0.0002514682,0.0003921831,0.03096819,0.0005965463,0.01637178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03597254,"threshold_uncertainty_score":0.2610002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2251618011809224,"score_gpt":0.4473643488185622,"score_spread":0.2222025476376399,"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."}}