{"id":"W3112205323","doi":"10.23889/ijpds.v5i5.1467","title":"Use of Machine Learning and Linked Population Health Data to Develop Predictive Risk Algorithms for Population Health Decision-Making","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Computer science; Machine learning; Population health; Population; Overfitting; Artificial intelligence; Health care; Data mining; Data science; Artificial neural network; Medicine; Environmental health","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":[0.01231798,0.001042248,0.001109585,0.002992887,0.0006631024,0.002704497,0.002419658,0.001579084,0.00240416],"category_scores_gemma":[0.03963873,0.0006062358,0.001254784,0.002188216,0.000976474,0.00214192,0.001787601,0.002598878,0.0005482989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002371324,"about_ca_system_score_gemma":0.002069433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01126517,"about_ca_topic_score_gemma":0.006080325,"domain_scores_codex":[0.9959819,0.002428383,0.0002419263,0.0004395387,0.0007390896,0.000169047],"domain_scores_gemma":[0.9749398,0.01998635,0.001331866,0.001095405,0.002338204,0.0003084386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005871477,0.0001252618,0.007655839,0.00009715166,0.0001512012,0.0000766395,0.0001033727,0.8837962,0.000148986,0.01582476,0.001532261,0.09042964],"study_design_scores_gemma":[0.000006385672,0.00001223592,0.0003564396,0.00002717976,0.000007333494,0.00001179629,0.00001316965,0.9855717,0.0001562039,0.01341816,0.0004127461,0.000006695587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03527964,0.0007662434,0.9581712,0.002050485,0.0001242999,0.0002000942,0.0004051903,0.0006220153,0.002380919],"genre_scores_gemma":[0.4601062,0.0007282615,0.5352682,0.0004982013,0.0001963219,0.0005757348,0.001170063,0.00007975214,0.001377236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01231798,"threshold_uncertainty_score":0.06514442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2074049314392213,"score_gpt":0.4937614469410697,"score_spread":0.2863565155018485,"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."}}