{"id":"W4321524277","doi":"10.48550/arxiv.2302.10824","title":"Localizing the Origin of Idiopathic Ventricular Arrhythmia from ECG Using an Attention-Based Recurrent Convolutional Neural Network","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Catheter ablation; Ablation; Cardiac arrhythmia; Pattern recognition (psychology); Cardiology; Medicine; Atrial fibrillation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004360136,0.0002700978,0.0005269035,0.0001985364,0.0002243394,0.00002686325,0.0002888601,0.0002419685,0.00002581803],"category_scores_gemma":[0.00005011804,0.0002457556,0.0004963236,0.000738372,0.0001665251,0.00005722493,0.0002194792,0.0007283227,0.00001680183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003036842,"about_ca_system_score_gemma":0.0003278588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001304149,"about_ca_topic_score_gemma":0.00004171602,"domain_scores_codex":[0.9981692,0.0002853984,0.0003378869,0.0006834449,0.0002092724,0.0003148064],"domain_scores_gemma":[0.9983047,0.0001356418,0.000402121,0.000738644,0.0002587102,0.0001602115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001123015,0.00007251913,0.1979252,0.0001113279,0.0003249663,0.0006394223,0.00001867366,0.800263,0.00008677587,0.0001818752,0.00002864188,0.00023524],"study_design_scores_gemma":[0.0006184042,0.0000634327,0.0201126,0.001172782,0.001466838,0.000004861321,0.000144059,0.9748542,0.00004840303,0.001224367,0.00006497645,0.0002250768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9269968,0.0005988399,0.07082651,0.0001217255,0.001093097,0.0002070825,0.00004447377,0.0001021641,0.000009360961],"genre_scores_gemma":[0.9978185,0.00007341294,0.0003350034,0.00002361571,0.001364634,9.633982e-7,0.0002432995,0.00003195468,0.0001086742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1778126,"threshold_uncertainty_score":0.9999995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1460230958607817,"score_gpt":0.2461008850778961,"score_spread":0.1000777892171145,"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."}}