{"id":"W3187907849","doi":"10.3389/fphys.2021.704122","title":"Deep Learning Classification of Unipolar Electrograms in Human Atrial Fibrillation: Application in Focal Source Mapping","year":2021,"lang":"en","type":"article","venue":"Frontiers in Physiology","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Toronto General Hospital; University Health Network","funders":"Heart and Stroke Foundation of Canada","keywords":"Atrial fibrillation; Catheter ablation; Convolutional neural network; Residual; Artificial intelligence; Ablation; Medicine; Deep learning; Receiver operating characteristic; Pattern recognition (psychology); Computer science; Cardiology; Algorithm; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001950938,0.00008005992,0.0003545365,0.0002811277,0.00002991523,0.000003472967,0.00004842904,0.0001380185,0.00000361196],"category_scores_gemma":[0.0000948387,0.00008985276,0.00008783771,0.0007592544,0.00004874167,0.00003331125,0.0000195956,0.0002809225,0.000001099029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001561446,"about_ca_system_score_gemma":0.00004147113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001666988,"about_ca_topic_score_gemma":0.00007968576,"domain_scores_codex":[0.9989426,0.0001795785,0.000348354,0.0002596364,0.00008578174,0.0001840766],"domain_scores_gemma":[0.9996023,0.00003816251,0.0001208235,0.0001666789,0.0000470073,0.00002500663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006238672,0.00003087814,0.7623071,0.00003794968,0.00002835749,0.000002262189,0.0003153135,0.008569484,0.174624,0.00006974623,0.000009039683,0.05394351],"study_design_scores_gemma":[0.00151042,0.0001143566,0.8157546,0.00009190073,0.00003375323,0.000003004715,0.002006212,0.1747322,0.002395422,0.001309154,0.001927899,0.0001210701],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9718602,0.001086022,0.02660588,0.0001341734,0.00009620551,0.0001063341,1.502603e-7,0.00001876943,0.00009223692],"genre_scores_gemma":[0.9965641,0.0001266167,0.002760299,0.000008328068,0.0003152593,0.000007628588,0.0001305631,0.0000100459,0.00007713665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1722285,"threshold_uncertainty_score":0.3664089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01359599664606459,"score_gpt":0.270105166127043,"score_spread":0.2565091694809784,"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."}}