{"id":"W2972620123","doi":"10.1109/bhi.2019.8834583","title":"Atrial Fibrillation Detection Using Deep Features and Convolutional Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spectrogram; Computer science; Artificial intelligence; Atrial fibrillation; Pattern recognition (psychology); Convolutional neural network; Deep learning; Cardiac arrhythmia; Feature extraction; Noise (video); Frequency domain; Support vector machine; Cardiology; Computer vision; Medicine; Image (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":[0.00006442482,0.00004652641,0.00009567336,0.0000475669,0.0000487088,0.00001321024,0.000007103749,0.00006269222,0.00005244768],"category_scores_gemma":[0.00001823281,0.00003807375,0.0000623458,0.00008410936,0.00001125745,0.00004120968,0.000008357823,0.00006050661,0.000006214581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002982544,"about_ca_system_score_gemma":0.000009661725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001063334,"about_ca_topic_score_gemma":0.00001138018,"domain_scores_codex":[0.9996493,0.00001173146,0.00007269662,0.0001045628,0.00008742203,0.00007427158],"domain_scores_gemma":[0.9998068,0.00003325446,0.00002558872,0.00005937684,0.00003778835,0.00003721717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002303142,0.000004244832,0.888397,0.00002598184,0.0001746303,0.000001712641,0.00003873941,0.04982348,0.01251776,0.00008663903,0.00003275674,0.04866667],"study_design_scores_gemma":[0.0007422406,0.000069464,0.1959715,0.00002440866,0.0001526231,0.00006192871,0.0000497356,0.8018628,0.0006178886,0.00003026348,0.0003488334,0.00006830344],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856557,0.0006816952,0.01274068,0.00005196724,0.0002955467,0.00006691433,1.697575e-7,0.00003821237,0.0004690635],"genre_scores_gemma":[0.9960794,0.00003348405,0.001084238,0.00001793793,0.001610582,1.201013e-7,0.000005790726,0.000004797262,0.001163686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7520393,"threshold_uncertainty_score":0.1552602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0111499355926481,"score_gpt":0.2625245448869865,"score_spread":0.2513746092943384,"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."}}