{"id":"W4388236068","doi":"10.2196/47803","title":"Optimization of Using Multiple Machine Learning Approaches in Atrial Fibrillation Detection Based on a Large-Scale Data Set of 12-Lead Electrocardiograms: Cross-Sectional Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science and Technology Council; Shanghai Educational Development Foundation","keywords":"Atrial fibrillation; Data set; Scale (ratio); Lead (geology); Set (abstract data type); Cross-sectional study; Computer science; Cross-validation; Artificial intelligence; Machine learning; Data mining; Medicine; Cardiology; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008372872,0.0007541304,0.0007037266,0.0009604983,0.0003078795,0.0007177346,0.0005277409,0.0007713505,0.0006636566],"category_scores_gemma":[0.01307678,0.0003339887,0.0009755224,0.0006020212,0.0003150447,0.0005979645,0.00045016,0.0005592123,0.0003506712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002357226,"about_ca_system_score_gemma":0.0002973279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00157335,"about_ca_topic_score_gemma":0.001592653,"domain_scores_codex":[0.9969215,0.001703225,0.0001851147,0.0007039012,0.0003430133,0.0001431927],"domain_scores_gemma":[0.9899131,0.00583429,0.001138892,0.0007991076,0.001957725,0.000356854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001554528,0.001801887,0.9535667,0.00008838574,0.0009516347,0.000194111,0.0003402885,0.005536725,0.002533572,0.00007038625,0.0004865114,0.03287518],"study_design_scores_gemma":[0.00007829763,0.004540628,0.9312754,0.00003776831,0.0006852561,0.0005835004,0.0005365793,0.05879416,0.002463129,0.0001866403,0.0007670751,0.00005148398],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946503,0.0002349511,0.004691235,0.00003105275,0.00001602868,0.0000675842,0.000157248,0.00001511124,0.0001364926],"genre_scores_gemma":[0.9949121,0.00009763638,0.00428756,0.00002766029,0.00002513032,0.00007657613,0.000414235,0.00001446081,0.0001447014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008372872,"threshold_uncertainty_score":0.04428053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2151811778236834,"score_gpt":0.4457797084956934,"score_spread":0.23059853067201,"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."}}