{"id":"W4301182844","doi":"10.1007/s12350-022-03099-x","title":"Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging","year":2022,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"National Heart, Lung, and Blood Institute","keywords":"Medicine; Mace; Myocardial perfusion imaging; Hazard ratio; Confidence interval; Receiver operating characteristic; Nuclear medicine; Internal medicine; Cardiology; Correction for attenuation; Perfusion; Area under the curve; Radiology; Myocardial infarction; Positron emission tomography; Percutaneous coronary intervention","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":[0.001282823,0.0007683889,0.001180461,0.0007478035,0.0001985214,0.001364759,0.0004651,0.0008295407,0.001054049],"category_scores_gemma":[0.004707038,0.0002931055,0.0005565149,0.0005424982,0.0001634591,0.0008360405,0.0006296253,0.001074112,0.000452973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002387135,"about_ca_system_score_gemma":0.0004986526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002068131,"about_ca_topic_score_gemma":0.003959368,"domain_scores_codex":[0.9993801,0.0002368179,0.00006521212,0.0001249112,0.000135752,0.00005725726],"domain_scores_gemma":[0.9978392,0.0009835134,0.000350658,0.0001714679,0.0004312827,0.0002238664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003167333,0.001350213,0.8592423,0.00006609068,0.0006082358,0.0001973676,0.00005619291,0.005418239,0.003515546,0.00008219253,0.001400554,0.1248957],"study_design_scores_gemma":[0.000197231,0.001906332,0.7776279,0.00005241949,0.000656356,0.0006170017,0.0001247245,0.2147485,0.002569527,0.000584966,0.0008634896,0.00005151058],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894182,0.001231483,0.006509371,0.0005464345,0.0001067012,0.00004703656,0.0003382169,0.0002327117,0.001569764],"genre_scores_gemma":[0.9948192,0.0003427411,0.003645163,0.0001016951,0.000127318,0.00001398125,0.0005390554,0.00002085727,0.00038994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002068131,"threshold_uncertainty_score":0.00678432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00995153058271093,"score_gpt":0.2215669108287921,"score_spread":0.2116153802460812,"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."}}