{"id":"W3088213682","doi":"10.1146/annurev-biodatasci-092820-033938","title":"Probabilistic Machine Learning for Healthcare","year":2021,"lang":"en","type":"preprint","venue":"Annual Review of Biomedical Data Science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute","keywords":"Probabilistic logic; Machine learning; Computer science; Artificial intelligence; Generative grammar; Pipeline (software); Health care; Statistical model","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004806476,0.001061838,0.001355469,0.001663074,0.0005770928,0.003511854,0.001364431,0.00318288,0.008233107],"category_scores_gemma":[0.01684559,0.000565612,0.0009471023,0.002040453,0.002390231,0.003921225,0.002272271,0.005495241,0.003289373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002149364,"about_ca_system_score_gemma":0.002063523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002539893,"about_ca_topic_score_gemma":0.001350022,"domain_scores_codex":[0.9970958,0.001469644,0.0001126062,0.0004430784,0.0007780418,0.0001008026],"domain_scores_gemma":[0.9931456,0.005251022,0.0002566802,0.0005505464,0.0006068195,0.0001892699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004477301,0.00003955295,0.001081409,0.0007305613,0.0001255446,0.0001139026,0.000132379,0.03445445,0.0002814031,0.6887876,0.05329898,0.2209093],"study_design_scores_gemma":[0.00001091678,0.00001694317,0.0002952352,0.0002537309,0.00001504915,0.00008444153,0.00002633024,0.03929657,0.0001189281,0.8988251,0.06103189,0.00002496999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.00262127,0.1764182,0.7344178,0.05153031,0.00313186,0.00009458814,0.001115574,0.001048454,0.0296219],"genre_scores_gemma":[0.3037293,0.2659435,0.3679999,0.01226161,0.01636687,0.0007057723,0.003282006,0.000726401,0.02898469],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.008233107,"threshold_uncertainty_score":0.02754247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0634074103074424,"score_gpt":0.4039377773913714,"score_spread":0.340530367083929,"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."}}