{"id":"W3197741533","doi":"10.1016/j.cjca.2021.08.014","title":"A Deep Learning–Enabled Electrocardiogram Model for the Identification of a Rare Inherited Arrhythmia: Brugada Syndrome","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Taipei Veterans General Hospital; National Health Research Institutes; Ministry of Science and Technology, Taiwan; Academia Sinica","keywords":"Medicine; Brugada syndrome; Deep learning; Internal medicine; Right bundle branch block; Cardiology; Medical diagnosis; Sudden cardiac death; Receiver operating characteristic; Cardiac arrhythmia; Electrocardiography; Artificial intelligence; Machine learning; Atrial fibrillation; Radiology; Computer science","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":[0.000575684,0.0001482433,0.0008515099,0.0002287623,0.0001856675,0.00001477207,0.0001183906,0.0002240856,0.00000962514],"category_scores_gemma":[0.0008731225,0.0001175731,0.000769766,0.0003643127,0.0001953028,0.00005576573,0.00001124661,0.00059583,0.000002523781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001368728,"about_ca_system_score_gemma":0.002137033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005767774,"about_ca_topic_score_gemma":0.0002381205,"domain_scores_codex":[0.9984224,0.0002260534,0.0006076833,0.0001922709,0.0001250361,0.0004265987],"domain_scores_gemma":[0.9978945,0.0002489654,0.0003472339,0.0002977847,0.0009507921,0.0002606768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"case_report","study_design_scores_codex":[0.001617077,0.00001369721,0.006565681,0.0003132266,0.007809068,0.008752284,0.001055138,0.8302804,0.1050211,0.001592587,0.008568004,0.02841171],"study_design_scores_gemma":[0.0160961,0.00635001,0.205636,0.0005380118,0.009542361,0.3934289,0.002868214,0.1803266,0.01605268,0.01063077,0.1569835,0.00154683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7803748,0.0176456,0.1952926,0.004471072,0.0009066567,0.0006431033,0.00003312338,0.00001812051,0.0006149306],"genre_scores_gemma":[0.9977265,0.0004689925,0.0002814827,0.0002010588,0.0007945728,0.00002447984,0.00003285113,0.00002564713,0.0004444309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6499539,"threshold_uncertainty_score":0.4794492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01075242123868973,"score_gpt":0.2351053922901514,"score_spread":0.2243529710514617,"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."}}