{"id":"W4295774775","doi":"10.1016/j.jcmg.2022.06.006","title":"Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events","year":2022,"lang":"en","type":"article","venue":"JACC. Cardiovascular imaging","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Calgary","funders":"National Heart, Lung, and Blood Institute","keywords":"Mace; Medicine; Correction for attenuation; Nuclear medicine; Computed tomographic; Coronary artery calcium; Positron emission tomography; Radiology; Cohort; Risk stratification; Cardiac PET; Cardiology; Computed tomography; Internal medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007943336,0.0007884604,0.0006793144,0.0007213995,0.0001415921,0.0009246846,0.0006003618,0.000697532,0.001660872],"category_scores_gemma":[0.002519425,0.0002607082,0.0005773638,0.0003072511,0.0001949711,0.0005901851,0.0006177915,0.001242653,0.0008713366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003513813,"about_ca_system_score_gemma":0.0006040299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004480134,"about_ca_topic_score_gemma":0.007573689,"domain_scores_codex":[0.9997792,0.00006279369,0.00001538205,0.00006516316,0.0000320458,0.00004547161],"domain_scores_gemma":[0.9993423,0.0002985758,0.00009199753,0.00006511698,0.0001199813,0.00008206796],"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":[0.003077898,0.001990322,0.3362949,0.0002667865,0.0009563384,0.000356536,0.00007337958,0.08699407,0.01120219,0.001200643,0.02312282,0.5344642],"study_design_scores_gemma":[0.0002540641,0.0006135462,0.07465174,0.0001253032,0.000331849,0.0003367407,0.00007421435,0.9100108,0.004565861,0.006397967,0.002582049,0.00005585791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9492617,0.004265831,0.03511871,0.002208604,0.0002351124,0.00006946893,0.003069523,0.001126187,0.004644821],"genre_scores_gemma":[0.9905849,0.000687629,0.004468656,0.0002167318,0.0001062625,0.00001933184,0.002563953,0.00002717054,0.00132524],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004480134,"threshold_uncertainty_score":0.008908093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02047620488777782,"score_gpt":0.2577468052817443,"score_spread":0.2372706003939664,"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."}}