{"id":"W3126008863","doi":"10.1038/s41467-021-20966-2","title":"Deep convolutional neural networks to predict cardiovascular risk from computed tomography","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":231,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Heart, Lung, and Blood Institute; European Commission; National Cancer Institute; National Institutes of Health; American College of Radiology Imaging Network; Deutsche Forschungsgemeinschaft; American Heart Association","keywords":"Medicine; Convolutional neural network; Framingham Risk Score; Chest pain; Deep learning; Asymptomatic; Cardiology; Artificial intelligence; Radiology; Internal medicine; Computer science; Disease","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":[0.0006551394,0.0008308237,0.0004244094,0.0006104061,0.0001712986,0.0005274513,0.0006205101,0.0005971421,0.001213692],"category_scores_gemma":[0.002576737,0.0002962436,0.0003999321,0.0005086789,0.0002185588,0.000429016,0.0006003074,0.001028515,0.0006507765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007193006,"about_ca_system_score_gemma":0.0008597297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01549113,"about_ca_topic_score_gemma":0.02016043,"domain_scores_codex":[0.9997548,0.00006343637,0.00001620103,0.0000646029,0.00005460677,0.00004632649],"domain_scores_gemma":[0.9994954,0.0002618109,0.0000670019,0.00005050609,0.0001008399,0.00002450429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004425282,0.000395613,0.02729395,0.0001119128,0.0003212907,0.0002219494,0.00005924768,0.6066862,0.006681989,0.003538919,0.01174227,0.3425041],"study_design_scores_gemma":[0.000007160583,0.00001838789,0.001773693,0.000009001792,0.00001373479,0.00001672266,0.000002790341,0.9950314,0.0007679852,0.001910749,0.0004427583,0.000005544828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3865383,0.006468251,0.5881963,0.002166911,0.0003718234,0.0001319145,0.004033056,0.004819176,0.007274234],"genre_scores_gemma":[0.9285488,0.0009847212,0.06113229,0.0003334199,0.0001210011,0.0001211904,0.003906618,0.0000843147,0.004767704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01549113,"threshold_uncertainty_score":0.03080189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01035590317785821,"score_gpt":0.2602892254262583,"score_spread":0.2499333222484001,"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."}}