{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.00313995,0.0001751353,0.0002120938,0.0003238794,0.003285876,0.0007283075,0.01032638,0.00002158282,0.0001299155],"category_scores_gemma":[0.001597226,0.0001785038,0.00002484999,0.0007491795,0.00004613478,0.002014668,0.004103964,0.0009630433,0.00000170248],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.003846626,"about_ca_system_score_gemma":0.01409542,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8876199,"about_ca_topic_score_gemma":0.89495,"domain_scores_codex":[0.9951631,0.0003007342,0.0007050487,0.001003611,0.002352562,0.0004749402],"domain_scores_gemma":[0.9969214,0.0004198811,0.0008790235,0.001083399,0.000453614,0.0002426709],"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":[0.0004864358,0.0004043023,0.2797692,0.00002960297,0.0003529267,0.0003429404,0.006705334,0.1298392,0.00007545582,0.1843201,0.05303453,0.34464],"study_design_scores_gemma":[0.0004401624,0.0001532047,0.1263448,0.00004085503,0.000003199207,0.0001442983,0.0001335472,0.7610809,0.000006326281,0.001030117,0.110408,0.0002145405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03985015,0.0001769955,0.7943265,0.140548,0.01455243,0.0008411867,0.009288547,0.0001923479,0.0002238299],"genre_scores_gemma":[0.8373965,0.00001400534,0.1496682,0.002831892,0.0003195103,0.00001692332,0.009208998,0.00001761444,0.0005263576],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7975463,"threshold_uncertainty_score":0.9999774,"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."}}