{"id":"W2093683326","doi":"10.1016/j.jelectrocard.2008.07.022","title":"Using inverse electrocardiography to image myocardial infarction—reflecting on the 2007 PhysioNet/Computers in Cardiology Challenge","year":2008,"lang":"en","type":"article","venue":"Journal of Electrocardiology","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Magnetic resonance imaging; Cardiology; Myocardial infarction; Torso; Medicine; Electrocardiography; Magnetocardiography; Internal medicine; Gold standard (test); Cardiac magnetic resonance; Radiology; Anatomy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001021558,0.0004213155,0.001703046,0.001133135,0.0003217139,0.00001038555,0.0002642543,0.0003285151,0.00001694623],"category_scores_gemma":[0.0004085744,0.0003097168,0.001386381,0.001172284,0.0002994704,0.0001347271,0.00007928882,0.001876224,0.00004617711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003856478,"about_ca_system_score_gemma":0.0005445882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002366069,"about_ca_topic_score_gemma":0.000003796662,"domain_scores_codex":[0.9963114,0.0009346132,0.0008379391,0.0004825892,0.0003956071,0.001037898],"domain_scores_gemma":[0.997965,0.0005628306,0.0003748814,0.0004735955,0.0003733988,0.0002502637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.01182085,0.0003626842,0.02606529,0.00005147035,0.007371328,0.01165325,0.001217401,0.03156931,0.8718486,0.001883282,0.03398472,0.002171756],"study_design_scores_gemma":[0.01797033,0.04623025,0.5705345,0.0006783263,0.002374918,0.2919369,0.0009595484,0.001624642,0.02490556,0.00764844,0.03209294,0.003043624],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884579,0.0008388354,0.002783275,0.002168481,0.001090203,0.0004994132,0.000001542305,0.00003698364,0.004123393],"genre_scores_gemma":[0.9887516,0.00148399,0.001733367,0.003872793,0.004069335,0.00001734531,0.000003837786,0.00005174468,0.00001590953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8469431,"threshold_uncertainty_score":0.9999355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04708397734964243,"score_gpt":0.3204350095433183,"score_spread":0.2733510321936758,"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."}}