{"id":"W4367598055","doi":"10.1038/s41746-023-00806-x","title":"Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Center for Advancing Translational Sciences; U.S. Department of Health and Human Services","keywords":"Mace; Interquartile range; Medicine; Myocardial perfusion imaging; Internal medicine; Acute coronary syndrome; Cardiology; Receiver operating characteristic; Confidence interval; Risk assessment; Cardiovascular event; Revascularization; Artificial intelligence; Perfusion; Computer science; Percutaneous coronary intervention; Myocardial infarction","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":[0.0005259046,0.0002270523,0.0005278455,0.0002202828,0.0001476158,0.00007877308,0.00004225847,0.00005488949,0.0001377394],"category_scores_gemma":[0.00115086,0.0001824478,0.0001814957,0.0002743611,0.0002627629,0.0001683733,0.00007872863,0.0002842262,0.0001166934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008390266,"about_ca_system_score_gemma":0.00004031405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008590352,"about_ca_topic_score_gemma":1.81806e-7,"domain_scores_codex":[0.9984088,0.00004207704,0.0002891488,0.0004047851,0.0004691575,0.0003860492],"domain_scores_gemma":[0.998484,0.0007773793,0.00008430362,0.0002122484,0.0001832574,0.0002588482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004897343,0.00008664408,0.5515761,0.0001817107,0.0001523886,0.0002396458,0.002068121,0.00003506146,0.00291641,0.00006690509,0.03104644,0.4111409],"study_design_scores_gemma":[0.00691427,0.0006487606,0.6799774,0.001024403,0.0006055376,0.0001026797,0.003039546,0.01561474,0.00005483702,0.0002563935,0.2913118,0.00044971],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592642,0.01535434,0.002969803,0.006156665,0.001031713,0.001186333,0.0001628708,0.0005759785,0.01329814],"genre_scores_gemma":[0.9929191,0.001118128,0.0002026587,0.0002447667,0.0009983615,0.00009075487,0.0005343078,0.00006024016,0.003831654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4106911,"threshold_uncertainty_score":0.7440005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008766639381066511,"score_gpt":0.2825659907993064,"score_spread":0.2737993514182399,"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."}}