{"id":"W3199493908","doi":"10.2196/32771","title":"Predictability of Mortality in Patients With Myocardial Injury After Noncardiac Surgery Based on Perioperative Factors via Machine Learning: Retrospective Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; Korea Health Industry Development Institute; National IT Industry Promotion Agency","keywords":"Medicine; Receiver operating characteristic; Perioperative; Machine learning; Gradient boosting; Artificial intelligence; Medical prescription; Area under the curve; Retrospective cohort study; Emergency medicine; Internal medicine; Surgery; Computer science; Random forest","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009994447,0.0003026188,0.001641431,0.0001642339,0.00004804148,0.00002065145,0.00007545516,0.0002257394,0.0003656104],"category_scores_gemma":[0.001415873,0.0002004018,0.0004714866,0.0005325982,0.000246955,0.0001654947,0.00006368573,0.0008160332,0.000006188104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002037664,"about_ca_system_score_gemma":0.0005026622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007453925,"about_ca_topic_score_gemma":0.00003477195,"domain_scores_codex":[0.99582,0.0004414502,0.001008056,0.0002382546,0.002171375,0.0003208037],"domain_scores_gemma":[0.9979466,0.0006541895,0.00019399,0.000472808,0.0003587647,0.0003736687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001422195,0.001688377,0.9912752,0.0001461385,0.0002203511,0.000107692,0.004588005,0.00001440239,5.056812e-7,0.000005574684,0.00001426428,0.00051733],"study_design_scores_gemma":[0.002577941,0.001262154,0.9930348,0.0001520696,0.0001269167,0.000002025629,0.001453686,0.0007525944,0.00004810872,6.470239e-7,0.0003932018,0.0001958273],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966009,0.00001071028,0.00004002242,0.00007703785,0.0001319643,0.001041893,0.00005724073,0.00004256891,0.001997651],"genre_scores_gemma":[0.9991513,0.000005682843,0.00004987172,0.0003892527,0.00005092762,0.00009584964,0.0001901878,0.00002021818,0.00004674214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003134319,"threshold_uncertainty_score":0.8172148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008342917900391171,"score_gpt":0.2650470897946566,"score_spread":0.2567041718942654,"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."}}