{"id":"W3088406258","doi":"10.1016/j.compbiomed.2020.104013","title":"A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Cardiac Arrhythmias and Treatments","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University; Health Sciences Centre","funders":"Biosense Webster; National Heart, Lung, and Blood Institute; Medtronic; Abbott Laboratories; National Institutes of Health; National Science Foundation","keywords":"Ventricular tachycardia; Lead (geology); Electrocardiography; Computer science; Internal medicine; Artificial intelligence; Tachycardia; Cardiology; Machine learning; Pattern recognition (psychology); Medicine; Geology","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":[0.0002761668,0.0001592604,0.0006198186,0.0001068307,0.00006682775,0.000002930906,0.00006482617,0.0000594633,0.000002156221],"category_scores_gemma":[0.00007639729,0.00009652856,0.00009933006,0.000272825,0.0001762798,0.00001469664,0.00008229739,0.0002730446,0.000001044429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003829365,"about_ca_system_score_gemma":0.00002681802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001480357,"about_ca_topic_score_gemma":7.03306e-7,"domain_scores_codex":[0.9989665,0.0001325327,0.0002519362,0.000301206,0.0001039824,0.000243859],"domain_scores_gemma":[0.9995231,0.00009648432,0.00006696326,0.0001412107,0.00002956539,0.0001426953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001275355,0.0002232422,0.8520684,0.0003999105,0.001783895,0.001820529,0.003582906,0.002821499,0.003732227,0.001925297,0.001375432,0.1289913],"study_design_scores_gemma":[0.04124147,0.01492978,0.1072026,0.002566183,0.004145745,0.01519268,0.00209452,0.6412907,0.004292433,0.001340252,0.1639677,0.001735857],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8501328,0.01078997,0.1344361,0.002644357,0.0003096162,0.0007129146,0.000006330519,0.00004472056,0.0009232423],"genre_scores_gemma":[0.9946102,0.0002452255,0.003211675,0.00146038,0.0003797402,0.000008858342,0.00006780031,0.00001214996,0.000004002595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7448658,"threshold_uncertainty_score":0.3936321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02933363770916961,"score_gpt":0.2993521894098047,"score_spread":0.270018551700635,"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."}}