{"id":"W3097208481","doi":"10.1136/bmjopen-2020-037860","title":"Predicting population health with machine learning: a scoping review","year":2020,"lang":"en","type":"review","venue":"BMJ Open","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Impact; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; Public Health Ontario; University of Toronto; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Medicine; Population health; Machine learning; Population; Data science; Artificial intelligence; Medical education; Environmental health; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001532565,0.0002755132,0.002276295,0.00008144882,0.0002196254,0.00006933849,0.000231446,0.0001223665,0.0001755331],"category_scores_gemma":[0.0009345298,0.0001969643,0.0001476718,0.0005314178,0.00001589262,0.0001269627,0.0001292732,0.0006770575,0.0001553122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000288193,"about_ca_system_score_gemma":0.003557771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004313937,"about_ca_topic_score_gemma":0.0004865628,"domain_scores_codex":[0.9971481,0.0004546039,0.001329694,0.0004692614,0.000320651,0.0002776659],"domain_scores_gemma":[0.997917,0.0001633782,0.001146439,0.0003894694,0.0001021871,0.0002815264],"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":[0.00001629662,0.0000145383,0.0008550701,0.3193948,0.00002652856,0.000007928308,0.00009974906,3.790813e-7,1.128524e-9,0.00000885079,0.0003866874,0.6791892],"study_design_scores_gemma":[0.00001852004,0.0003343008,0.000007443966,0.6128489,0.000243741,0.0001472948,0.00003006428,0.00004134382,5.452367e-8,0.000003530986,0.386201,0.0001237217],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[6.229993e-7,0.9587376,0.00004018177,0.005091695,0.0001326396,0.03519957,0.000004284702,0.00006773125,0.0007256572],"genre_scores_gemma":[0.000003087627,0.9921077,0.0007748287,0.00254615,0.0005625734,0.002413333,0.001072978,0.0000663933,0.0004529769],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6790655,"threshold_uncertainty_score":0.8031971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5750623230218084,"score_gpt":0.6226561761114598,"score_spread":0.04759385308965147,"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."}}