{"id":"W4403333782","doi":"10.36227/techrxiv.172866031.13011158/v1","title":"Toward Robust Automated Cardiovascular Arrhythmia Detection using Self-supervised Learning and 1-Dimensional Vision Transformers","year":2024,"lang":"en","type":"preprint","venue":"","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Cardiac arrhythmia; Transformer; Computer vision; Pattern recognition (psychology); Machine learning; Engineering; Medicine; Cardiology; Electrical engineering; 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":[0.0005567181,0.000403129,0.0008482629,0.0004655437,0.0001789936,0.0001159789,0.0000423831,0.0005083744,0.00004493133],"category_scores_gemma":[0.00003430051,0.0003406678,0.0008640724,0.0003267196,0.00004063952,0.0000495587,0.0001996097,0.001344395,0.00002031478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002721571,"about_ca_system_score_gemma":0.0001788239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006440954,"about_ca_topic_score_gemma":0.000004701051,"domain_scores_codex":[0.9977194,0.0001141792,0.0004127398,0.0008176377,0.000626336,0.0003096967],"domain_scores_gemma":[0.9992751,0.0000379541,0.00005875867,0.0002516751,0.0001674229,0.0002091163],"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":[0.0003158978,0.0001470938,0.001992288,0.01058279,0.02065209,0.001392274,0.002118776,0.5268088,0.05870451,0.000003651559,0.00006823977,0.3772136],"study_design_scores_gemma":[0.0006653501,0.0001134123,0.0002626062,0.001277629,0.00478981,0.00035048,0.0002744186,0.9871691,0.004165462,0.00002160263,0.0005487072,0.0003614289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9806964,0.006088007,0.008611878,0.0002716756,0.0008353731,0.0004004471,0.000004235927,0.00228878,0.0008031794],"genre_scores_gemma":[0.9819328,0.0005900942,0.01620467,0.00001607384,0.0007873563,0.00001523404,0.00005211768,0.00008228132,0.0003194397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4603603,"threshold_uncertainty_score":0.9999045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02318337252933917,"score_gpt":0.2774511668312168,"score_spread":0.2542677943018777,"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."}}