{"id":"W4291127738","doi":"10.2196/preprints.41725","title":"Machine Learning and Causal Approaches to Predict Readmissions and Its Economic Consequences Among Canadian Patients With Heart Disease: Retrospective Study (Preprint)","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ensemble learning; Machine learning; Artificial intelligence; Computer science; Receiver operating characteristic; Ensemble forecasting; Retrospective cohort study; Principal component analysis; Statistics; Data mining; Medicine; Mathematics; Surgery","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":[0.00308767,0.0005202058,0.0004921544,0.00229798,0.001182333,0.001108645,0.001137422,0.0004336294,0.003361217],"category_scores_gemma":[0.01758143,0.0003208141,0.001266078,0.004713378,0.0003570033,0.0005197208,0.0007002155,0.001072088,0.0005321286],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01204181,"about_ca_system_score_gemma":0.02502081,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9543394,"about_ca_topic_score_gemma":0.9481668,"domain_scores_codex":[0.9983459,0.0001741702,0.0001646578,0.0002456414,0.000774009,0.0002956012],"domain_scores_gemma":[0.9903493,0.001913186,0.001528308,0.0008318395,0.00474777,0.0006296702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001182834,0.00003799843,0.9792113,0.0001043167,0.0001944414,0.00006594136,0.0001621201,0.0008152489,0.00004130391,0.000262707,0.008442744,0.0105437],"study_design_scores_gemma":[0.00001939362,0.00004812012,0.9877697,0.0001361837,0.0002094329,0.0001465718,0.0005270496,0.004968369,0.000187977,0.0002002078,0.00574924,0.00003782102],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8748496,0.003181539,0.004116616,0.002747978,0.0001559278,0.0002649327,0.1092313,0.0002254048,0.005226708],"genre_scores_gemma":[0.951038,0.001890569,0.003970187,0.0003877757,0.000092872,0.0001777969,0.04042857,0.00005441356,0.001959842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9879582,"threshold_uncertainty_score":0.09185898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2359381290784551,"score_gpt":0.3563821468970194,"score_spread":0.1204440178185643,"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."}}