{"id":"W2090472274","doi":"10.1109/bibm.2014.6999159","title":"Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals","year":2014,"lang":"en","type":"article","venue":"","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Heart, Lung, and Blood Institute","keywords":"Hypertrophic cardiomyopathy; Heartbeat; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Electrocardiography; Random forest; Support vector machine; Computer science; Medicine; Cardiology","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":[0.0003201971,0.0002466761,0.0005745453,0.0001769211,0.000191695,0.0001086913,0.0001469497,0.0001521567,0.0001653006],"category_scores_gemma":[0.0001773321,0.0002060486,0.0002689172,0.0002149231,0.00004583432,0.0001428262,0.00009196894,0.00029255,0.0002448641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005963758,"about_ca_system_score_gemma":0.00002686963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007910273,"about_ca_topic_score_gemma":0.00001354144,"domain_scores_codex":[0.9978434,0.0001327563,0.000401121,0.0004998461,0.0007142586,0.0004086601],"domain_scores_gemma":[0.9989324,0.0001506276,0.0001060418,0.0004421305,0.0001165731,0.0002522096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003218571,0.000212738,0.9203278,0.0000467299,0.0004126901,0.00001129893,0.0002144051,0.00001060901,0.02893319,0.000002872218,0.009429073,0.04036641],"study_design_scores_gemma":[0.01187722,0.001751048,0.8323988,0.001531451,0.004327619,0.00002086395,0.001564249,0.01493735,0.09504696,0.0006429864,0.0338372,0.002064257],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907573,0.000415513,0.005036708,0.0003322509,0.0004061753,0.0001356198,0.0000298811,0.0001767542,0.002709834],"genre_scores_gemma":[0.9935138,0.0000427352,0.00318154,0.0004727732,0.0007098875,0.00001427727,0.0002495732,0.00004375586,0.001771703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.087929,"threshold_uncertainty_score":0.8402416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03432964689571668,"score_gpt":0.2695154932662372,"score_spread":0.2351858463705205,"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."}}