{"id":"W4415793817","doi":"10.1161/circ.152.suppl_3.4368538","title":"Abstract 4368538: Fusion Machine Learning Architectures for Improving ECG classification of acute coronary events","year":2025,"lang":"en","type":"article","venue":"Circulation","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thornhill Medical (Canada)","funders":"","keywords":"Random forest; Deep learning; Acute coronary syndrome; Artificial neural network; Test set; Myocardial infarction; Tree (set theory); Decision tree","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001781191,0.00007650082,0.0001573829,0.0001793926,0.0001025351,0.000005383271,0.00003697174,0.0000696504,0.00001054248],"category_scores_gemma":[0.0001075818,0.00007101989,0.0001115477,0.0001625407,0.00001339755,0.00002156859,0.00001239713,0.0001185608,0.000001602218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006013424,"about_ca_system_score_gemma":0.00004023287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004868662,"about_ca_topic_score_gemma":0.000002926688,"domain_scores_codex":[0.9993556,0.00001859623,0.0002331627,0.0001705573,0.0001276368,0.00009451363],"domain_scores_gemma":[0.9995151,0.0000662986,0.0001482239,0.0001413899,0.0001015048,0.00002747676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008124818,0.00003897206,0.5878173,0.0001776127,0.00008713928,5.216585e-7,0.00005331765,0.001834796,0.30538,0.00001589025,0.000003705222,0.1045095],"study_design_scores_gemma":[0.0004898019,0.00002834605,0.8230858,0.0001101438,0.0002973514,0.000001722871,0.00002856732,0.1713084,0.00435966,0.000216492,0.00002887593,0.00004484289],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741644,0.0001495521,0.02488638,0.0002072641,0.0001104351,0.0002260868,0.000005615646,0.00004512285,0.0002051698],"genre_scores_gemma":[0.99832,0.000007996726,0.001112826,0.00001689245,0.00006999015,0.00001519223,0.0002146682,0.000009838339,0.0002325303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3010203,"threshold_uncertainty_score":0.2896107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02009311199946083,"score_gpt":0.3048337090431422,"score_spread":0.2847405970436814,"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."}}