{"id":"W3214642206","doi":"10.1016/j.ijcard.2021.11.039","title":"Evolution of single-lead ECG for STEMI detection using a deep learning approach","year":2021,"lang":"en","type":"article","venue":"International Journal of Cardiology","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Medtronic Foundation","keywords":"Medicine; Lead (geology); Deep learning; Cardiology; Internal medicine; Artificial intelligence","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":[0.0003426116,0.00006102662,0.0003330727,0.0002198406,0.00002785208,0.000008103177,0.00006699463,0.00008145154,0.000002575696],"category_scores_gemma":[0.0005393683,0.00005548577,0.0003484517,0.00009800087,0.00003210686,0.00005880362,0.00001927319,0.0001709594,3.79221e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002628081,"about_ca_system_score_gemma":0.00009259791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007345604,"about_ca_topic_score_gemma":9.146481e-7,"domain_scores_codex":[0.9991164,0.00009676093,0.0003689738,0.00009464507,0.0002352408,0.0000880061],"domain_scores_gemma":[0.9979809,0.00009758298,0.0003342123,0.00005775873,0.001494618,0.00003494223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004869674,0.00007612652,0.08900442,0.00005309367,0.001815529,0.00009043214,0.0001039909,0.07674742,0.7830757,0.00004141502,0.00001115787,0.04849378],"study_design_scores_gemma":[0.01147933,0.003096364,0.04640391,0.001091213,0.004136643,0.03561027,0.007919762,0.5403743,0.338432,0.001187147,0.009708732,0.0005602865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4960424,0.0005720649,0.5024076,0.00005399243,0.0005881416,0.00002055235,0.000001020694,0.000003637189,0.0003105775],"genre_scores_gemma":[0.9832145,0.00003944557,0.01483722,0.000009580216,0.001802167,0.000001216043,0.000005866262,0.000008432968,0.00008158732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4875704,"threshold_uncertainty_score":0.2262644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03703112788715513,"score_gpt":0.3096184118827216,"score_spread":0.2725872839955665,"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."}}