{"id":"W1926248049","doi":"10.1002/bimj.201100251","title":"Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble‐based methods?","year":2012,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Logistic regression; Regression; Statistics; Random forest; Regression analysis; Covariate; Predictive modelling; Population; Medicine; Machine learning; Artificial intelligence; Computer science; Mathematics","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":[0.004725536,0.0002679887,0.0005505503,0.0007592107,0.001012166,0.000064774,0.0002400359,0.0002602359,0.00006794252],"category_scores_gemma":[0.001702908,0.000185514,0.0002899475,0.001735926,0.00006369017,0.0007852926,0.00009521145,0.0008199941,0.000005298013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001082439,"about_ca_system_score_gemma":0.0003542378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004323881,"about_ca_topic_score_gemma":0.00001343484,"domain_scores_codex":[0.9948364,0.001405771,0.001139155,0.0003791161,0.001101809,0.001137722],"domain_scores_gemma":[0.9963224,0.001181128,0.0005789975,0.0004597452,0.000558535,0.0008992084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004049266,0.0003271815,0.8384661,0.0001491604,0.0001262041,0.000001911601,0.0004137163,0.00003663724,0.000344031,0.000003267986,0.000196673,0.1595302],"study_design_scores_gemma":[0.003875797,0.001014065,0.9496525,0.002787298,0.0006509281,0.000001658903,0.005033957,0.02511976,0.003889166,0.00025678,0.006889802,0.000828316],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8852447,0.004796519,0.1066954,0.0002880205,0.001364299,0.001501843,0.00007323764,0.00003106497,0.000004927506],"genre_scores_gemma":[0.984617,0.0001426662,0.0139392,0.0005058799,0.0006023658,0.00009899155,0.00003203768,0.00005053224,0.0000113301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1587019,"threshold_uncertainty_score":0.7784867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2283951564065257,"score_gpt":0.5023475563129224,"score_spread":0.2739523999063966,"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."}}