{"id":"W2183913643","doi":"10.2310/8000.2013.131031","title":"Computerized interpretation of the prehospital electrocardiogram: predictive value for ST segment elevation myocardial infarction and impact on on-scene time","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Emergency Medicine","topic":"Cardiac Arrest and Resuscitation","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Heart Institute; Institut National d'Excellence en Santé et en Services Sociaux; McGill University; McGill University Health Centre; Jewish General Hospital; Montreal General Hospital","funders":"","keywords":"Medicine; ST segment; Elevation (ballistics); Myocardial infarction; Cardiology; Predictive value; Internal medicine; Medical emergency; Interpretation (philosophy); Myocardial infarction diagnosis; Value (mathematics); Emergency medicine; Machine learning; Computer science","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":[0.0006777612,0.0001462544,0.0003941318,0.0002933992,0.00009404167,0.000003738947,0.00006903854,0.00007288817,0.00003636476],"category_scores_gemma":[0.0005397029,0.000088707,0.0002759125,0.0002356875,0.00008681144,0.00007273125,0.000004825423,0.0002021661,8.355134e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002083516,"about_ca_system_score_gemma":0.0003107394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000250304,"about_ca_topic_score_gemma":0.00004147645,"domain_scores_codex":[0.9986987,0.0001236451,0.0005198285,0.0001293985,0.0003436278,0.0001848061],"domain_scores_gemma":[0.9986061,0.000115621,0.0003886317,0.0001439984,0.0004497784,0.0002958987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02365669,0.0004448085,0.4068286,0.00101392,0.009209538,0.00001889353,0.01956416,0.03685043,0.09248038,0.004570783,0.2376862,0.1676755],"study_design_scores_gemma":[0.004993773,0.01140149,0.951294,0.001228341,0.0009043214,0.00001446096,0.0001734952,0.02326005,0.0005163715,0.000959301,0.005076801,0.0001776008],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9678543,0.000251591,0.01636879,0.002988813,0.01043754,0.001012981,0.00004172147,0.000007912291,0.00103634],"genre_scores_gemma":[0.9977707,0.0000720994,0.00008654396,0.0001337711,0.001839733,0.000008068867,0.00004015876,0.00001447707,0.00003444642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5444654,"threshold_uncertainty_score":0.3617366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01287263077282875,"score_gpt":0.2888711803852282,"score_spread":0.2759985496123995,"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."}}