{"id":"W4393311713","doi":"10.1038/s41467-024-46977-3","title":"Predicting mortality from AI cardiac volumes mass and coronary calcium on chest computed tomography","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Calgary","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; U.S. Department of Health and Human Services","keywords":"Medicine; Cardiology; Coronary artery calcium; Risk stratification; Internal medicine; Radiology; Coronary artery disease; Computed tomography","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":[0.000181126,0.0001471347,0.0002586663,0.0001235089,0.0002029738,0.00008440944,0.0001989929,0.0002224396,0.000006430354],"category_scores_gemma":[0.0002399187,0.0001388046,0.0001641473,0.0003302979,0.0001925717,0.00006810186,0.0001707311,0.001433802,0.00001361507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005034838,"about_ca_system_score_gemma":0.00009588585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002774122,"about_ca_topic_score_gemma":0.00004360074,"domain_scores_codex":[0.9990852,0.0001056748,0.0001842712,0.0002604258,0.0002126198,0.0001518439],"domain_scores_gemma":[0.9972625,0.001129063,0.00003000232,0.001330956,0.0001211887,0.0001262711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001102244,0.00007651368,0.9747614,0.00004601687,0.000350249,0.00001672901,0.0002295025,0.000003787799,0.000313122,0.001416724,0.01940413,0.003370754],"study_design_scores_gemma":[0.0002314417,0.00003679834,0.9389791,0.0003271599,0.0004673716,0.00000732173,0.0001000661,0.00793182,0.0001621204,0.0002542854,0.05137513,0.000127373],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7106954,0.2343205,0.0006713228,0.03067975,0.002609869,0.000889223,0.00178947,0.0012597,0.01708474],"genre_scores_gemma":[0.9941689,0.0005081911,0.002690258,0.001267062,0.0002778775,0.00002929414,0.0009736267,0.00002655283,0.00005823758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2834734,"threshold_uncertainty_score":0.6229237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02310975964630574,"score_gpt":0.3277610280846923,"score_spread":0.3046512684383866,"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."}}