{"id":"W2799357314","doi":"10.1088/2057-1976/aabef4","title":"Atrial fibrillation classification using step-by-step machine learning","year":2018,"lang":"en","type":"article","venue":"Biomedical Physics & Engineering Express","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Artificial intelligence; F1 score; Computer science; Waveform; Pattern recognition (psychology); Atrial fibrillation; Rhythm; Feature extraction; Sinus rhythm; Decision tree; Machine learning; Medicine; Cardiology; Internal medicine","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":[0.0001609659,0.0001796397,0.0002826047,0.00009616578,0.000112593,0.00003321422,0.00008528128,0.0001354708,0.00002420639],"category_scores_gemma":[0.0001427837,0.0001692715,0.0001674652,0.0003922761,0.0000829942,0.0000940453,0.00004368156,0.0002503956,0.00002758579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001010746,"about_ca_system_score_gemma":0.00003855459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008961757,"about_ca_topic_score_gemma":5.877357e-8,"domain_scores_codex":[0.9986743,0.00002786468,0.0002751942,0.0002962921,0.000448035,0.0002783098],"domain_scores_gemma":[0.999285,0.00007411515,0.00009375607,0.0002406558,0.0001005954,0.0002058075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004999575,0.00003568064,0.003570712,0.00009028018,0.0001532477,0.000003589773,0.00006248121,0.001363114,0.9754182,0.00005756834,0.001026535,0.01816859],"study_design_scores_gemma":[0.000653324,0.0001247984,0.0005220683,0.0001524639,0.0001520397,0.000004731416,0.00001655226,0.7658772,0.002378149,0.000004513604,0.2299399,0.0001743239],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1883728,0.0002996474,0.8103015,0.0001004158,0.0005419138,0.000103277,0.00001143508,0.0002381809,0.00003085422],"genre_scores_gemma":[0.9210599,0.00003165999,0.06988908,0.00001279779,0.008507365,0.000002542289,0.0002072896,0.00005164066,0.000237704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97304,"threshold_uncertainty_score":0.6902691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02364905652324965,"score_gpt":0.2807543054272675,"score_spread":0.2571052489040179,"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."}}