{"id":"W4386780865","doi":"10.2196/48487","title":"Machine Learning for Early Prediction of Major Adverse Cardiovascular Events After First Percutaneous Coronary Intervention in Patients With Acute Myocardial Infarction: Retrospective Cohort Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Conventional PCI; Medicine; Mace; Receiver operating characteristic; Percutaneous coronary intervention; Logistic regression; Machine learning; Myocardial infarction; Internal medicine; Random forest; Coronary artery disease; Cardiology; Incidence (geometry); Cohort; Artificial intelligence; Computer science; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003017282,0.0004028969,0.0006380688,0.0008930346,0.0004574971,0.0007943442,0.0005502916,0.0005648214,0.0009240175],"category_scores_gemma":[0.005602078,0.000405368,0.001246929,0.0009406821,0.0002186953,0.0007576011,0.0005003028,0.001030945,0.0002281447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003534524,"about_ca_system_score_gemma":0.0005277168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002474941,"about_ca_topic_score_gemma":0.002581816,"domain_scores_codex":[0.9986061,0.0003952871,0.0001919694,0.0003674169,0.0002821086,0.0001570503],"domain_scores_gemma":[0.9962453,0.0008518049,0.001410332,0.0006526501,0.000482956,0.000356895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001940228,0.00004985513,0.9988585,0.000008098414,0.0001191282,0.00004909869,0.00002070852,0.00005606273,0.00004453201,0.00001171281,0.0000577779,0.0005306032],"study_design_scores_gemma":[0.00003698156,0.0003553689,0.9972806,0.00001312538,0.0001750407,0.0004131573,0.000100949,0.001294469,0.00005696673,0.0000416052,0.0002214453,0.00001022101],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985732,0.0003714616,0.0003399729,0.00003689136,0.00001259673,0.00003363337,0.0004488591,0.000003878798,0.0001793858],"genre_scores_gemma":[0.9987766,0.0001697386,0.000249377,0.00001920414,0.00002002008,0.00003838285,0.0006429592,0.00000266871,0.00008097321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003017282,"threshold_uncertainty_score":0.01595706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698701617826666,"score_gpt":0.3193420990536232,"score_spread":0.3023550828753566,"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."}}