{"id":"W4289731377","doi":"10.1093/jamia/ocac122","title":"Toward ECG-based analysis of hypertrophic cardiomyopathy: a novel ECG segmentation method for handling abnormalities","year":2022,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"QRS complex; Segmentation; Hypertrophic cardiomyopathy; Artificial intelligence; Medicine; Atrial fibrillation; Cardiology; Repolarization; Internal medicine; Electrocardiography; Pattern recognition (psychology); ST segment; Computer science; Electrophysiology; Myocardial infarction","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":[0.004005458,0.00009752731,0.0007854382,0.0005100545,0.0001647778,0.00002089757,0.0002075057,0.00003975038,0.00002301101],"category_scores_gemma":[0.001919897,0.00006908985,0.0008329194,0.00136082,0.00004385468,0.00009403093,0.00005157776,0.0003579185,1.882705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006943552,"about_ca_system_score_gemma":0.0004435582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001458131,"about_ca_topic_score_gemma":0.000003214562,"domain_scores_codex":[0.9967188,0.0001852164,0.001080994,0.00005196457,0.001793367,0.0001696282],"domain_scores_gemma":[0.9951618,0.0007403114,0.003309153,0.0001482637,0.0005304095,0.0001100804],"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":[0.0008148361,0.0006585252,0.5770957,0.0004467894,0.01885426,0.000007616236,0.009439656,0.3189004,0.00496491,0.00003601912,0.001434579,0.06734668],"study_design_scores_gemma":[0.00155481,0.0005053598,0.01475358,0.00006623448,0.007195876,0.00001959412,0.008499453,0.9655942,0.001279279,0.00002361608,0.0004148355,0.00009320468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6004438,0.00003780952,0.3968206,0.002293485,0.0002222308,0.0001050748,0.00004237884,0.000006948509,0.00002770861],"genre_scores_gemma":[0.9247382,0.00003419259,0.07367149,0.001250269,0.0001898108,0.00001439548,0.00002987127,0.000009610229,0.00006213967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6466938,"threshold_uncertainty_score":0.2817402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02240530179786304,"score_gpt":0.3214183110499285,"score_spread":0.2990130092520654,"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."}}