{"id":"W2770980084","doi":"10.1109/tim.2017.2769198","title":"False Alarm Reduction in Atrial Fibrillation Detection Using Deep Belief Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Artifact (error); Atrial fibrillation; False alarm; Computer science; Noise (video); Artificial intelligence; Noise reduction; Reduction (mathematics); Pattern recognition (psychology); Electrocardiography; Cardiology; Medicine; Mathematics","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":[0.0003568945,0.000128432,0.0001734858,0.0002326503,0.0005616637,0.00008592036,0.00003023878,0.00009376441,0.00001903412],"category_scores_gemma":[0.00001290262,0.0001317594,0.0001126452,0.0001103656,0.00004208631,0.0002414295,8.268053e-7,0.0001657894,0.000002841238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003811422,"about_ca_system_score_gemma":0.00003513524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004797158,"about_ca_topic_score_gemma":0.0003510244,"domain_scores_codex":[0.9988945,0.00004993944,0.0002864171,0.0002477575,0.0003709941,0.0001504342],"domain_scores_gemma":[0.9994294,0.000007332766,0.0001521469,0.0002124947,0.0001110591,0.00008755129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005717405,0.00007944626,0.006537559,0.00003670709,0.0001709306,0.000002584532,0.0002912615,0.0941396,0.0470572,0.000003087403,0.000001235394,0.8511087],"study_design_scores_gemma":[0.01316408,0.001030742,0.08878969,0.0008210951,0.001499058,0.0001398866,0.001746445,0.6169032,0.2748341,0.00007602155,0.000326368,0.0006693847],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7668677,0.00007653749,0.2313392,0.0001787052,0.001152427,0.0002822448,0.00000112339,0.00003333281,0.00006870546],"genre_scores_gemma":[0.9985487,0.0003191528,0.0006636403,0.00001547066,0.0003798172,0.00000943857,0.000002789088,0.00001361888,0.00004735112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8504393,"threshold_uncertainty_score":0.5372993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06011029691587319,"score_gpt":0.310054907188948,"score_spread":0.2499446102730748,"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."}}