{"id":"W4328127903","doi":"10.3390/computers12030068","title":"A Temporal Transformer-Based Fusion Framework for Morphological Arrhythmia Classification","year":2023,"lang":"en","type":"article","venue":"Computers","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Raw data; Encoder; Cardiac arrhythmia; Feature learning; Transformer; Pattern recognition (psychology); Recurrent neural network; Data mining; Machine learning; Artificial neural network; Atrial fibrillation; Engineering; Medicine; Cardiology","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":[0.0001545479,0.00009085108,0.0001869825,0.0001314047,0.00009048574,0.00001595158,0.00005727383,0.0001102273,0.00001307485],"category_scores_gemma":[0.00005432823,0.00007350364,0.0001740202,0.0003905681,0.00003428087,0.00001980131,0.000005651152,0.0001234682,0.00005255334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000355176,"about_ca_system_score_gemma":0.00003321117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000597174,"about_ca_topic_score_gemma":4.03994e-7,"domain_scores_codex":[0.9992767,0.00001730396,0.0001606517,0.000222262,0.000139514,0.0001835619],"domain_scores_gemma":[0.9994622,0.0001777949,0.00003874847,0.0001825518,0.00004565595,0.00009302236],"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":[0.0009735808,0.0003658018,0.08468989,0.0005959154,0.0002861138,0.0003987798,0.0007796965,0.002880803,0.04175218,0.002275116,0.02349938,0.8415027],"study_design_scores_gemma":[0.002781615,0.0009733858,0.112752,0.0005725665,0.0002592129,0.00002786911,0.000334489,0.8486391,0.004164799,0.00245757,0.02665291,0.0003844423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4462525,0.00001813416,0.545943,0.00692638,0.0003540747,0.0001911918,0.000004600139,0.0002630894,0.00004702041],"genre_scores_gemma":[0.9332305,0.00001071072,0.06541843,0.0003028958,0.0006654943,0.00004057114,0.0001549597,0.00001331646,0.0001631011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8457583,"threshold_uncertainty_score":0.2997392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07812892526486764,"score_gpt":0.3442902784390481,"score_spread":0.2661613531741805,"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."}}