{"id":"W4409346796","doi":"10.1016/j.engappai.2025.110675","title":"Advancing interpretable cardiac disease diagnosis via a transformer-convolutional hybrid network on electrocardiograms","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Transformer; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Electrical engineering; Voltage","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004618695,0.0006848308,0.0005027532,0.0005877281,0.0002004065,0.0004639385,0.0007489735,0.000642971,0.0008494775],"category_scores_gemma":[0.001157801,0.0002634861,0.000509586,0.0003944822,0.0002519181,0.0006266079,0.00074831,0.000761513,0.0003353444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000599491,"about_ca_system_score_gemma":0.0006177842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009437765,"about_ca_topic_score_gemma":0.0100204,"domain_scores_codex":[0.9997731,0.00003744131,0.0000138645,0.00007620392,0.00005095983,0.00004839545],"domain_scores_gemma":[0.9997008,0.0001334562,0.00002712278,0.00003156311,0.00008691457,0.00002019877],"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":[0.0004718515,0.0002097113,0.00480111,0.0001023008,0.0001332603,0.0004052972,0.000111912,0.3032242,0.02532444,0.002921014,0.003068148,0.6592267],"study_design_scores_gemma":[0.000004515949,0.00002912463,0.0005707255,0.000005689797,0.00002067285,0.00003602629,0.000006005377,0.9954172,0.002874254,0.0007830416,0.0002483226,0.000004417067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.24545,0.001871487,0.745175,0.0005659805,0.0001505989,0.0001070428,0.0003603878,0.002594125,0.003725367],"genre_scores_gemma":[0.9193789,0.0006287224,0.07512347,0.0002324794,0.00005449705,0.00004001672,0.0005654648,0.00003445405,0.003941988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009437765,"threshold_uncertainty_score":0.01876569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005759980811987348,"score_gpt":0.2603151570687818,"score_spread":0.2545551762567945,"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."}}