Play all audios:
Access through your institution Buy or subscribe Current risk prediction tools for coronary artery disease (CAD) do not measure disease on a continuous scale and use only a small number of
variables for risk prediction, disregarding much of the data contained in electronic health records (EHRs). In a new study, a machine learning model trained using clinical data from EHRs
generated a novel, in silico quantitative score for CAD that can quantify disease pathophysiology and clinical outcomes on a continuous spectrum. The machine learning model was trained using
EHRs from 95,935 participants (35,749 from the BioMe Biobank and 60,186 from the UK Biobank), and the resulting in silico score for CAD risk was measured against numerous clinical outcomes,
including coronary artery stenosis and all-cause death. In the validation stage, the model predicted CAD with an area under the receiver operating characteristic curve of 0.95, a
sensitivity of 0.94 and a specificity of 0.82. Angiogram-detected coronary stenosis increased quantitatively in parallel with increases in the in silico score. Similarly, all-cause death and
CAD sequelae (such as recurrent myocardial infarction and heart failure) also increased stepwise with gradations in the in silico score. This is a preview of subscription content, access
via your institution ACCESS OPTIONS Access through your institution Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription $29.99 / 30
days cancel any time Learn more Subscribe to this journal Receive 12 print issues and online access $209.00 per year only $17.42 per issue Learn more Buy this article * Purchase on
SpringerLink * Instant access to full article PDF Buy now Prices may be subject to local taxes which are calculated during checkout ADDITIONAL ACCESS OPTIONS: * Log in * Learn about
institutional subscriptions * Read our FAQs * Contact customer support REFERENCES ORIGINAL ARTICLE * Forrest, I. S. et al. Machine learning-based marker for coronary artery disease:
derivation and validation in two longitudinal cohorts. _Lancet_ https://doi.org/10.1016/S0140-6736(22)02079-7 (2022) Article PubMed Google Scholar Download references AUTHOR INFORMATION
AUTHORS AND AFFILIATIONS * Nature Reviews Cardiology http://www.nature.com/nrcardio/ Karina Huynh Authors * Karina Huynh View author publications You can also search for this author inPubMed
Google Scholar CORRESPONDING AUTHOR Correspondence to Karina Huynh. RIGHTS AND PERMISSIONS Reprints and permissions ABOUT THIS ARTICLE CITE THIS ARTICLE Huynh, K. A
machine-learning-derived, in silico marker for CAD identifies underdiagnosed patients. _Nat Rev Cardiol_ 20, 139 (2023). https://doi.org/10.1038/s41569-023-00833-x Download citation *
Published: 17 January 2023 * Issue Date: March 2023 * DOI: https://doi.org/10.1038/s41569-023-00833-x SHARE THIS ARTICLE Anyone you share the following link with will be able to read this
content: Get shareable link Sorry, a shareable link is not currently available for this article. Copy to clipboard Provided by the Springer Nature SharedIt content-sharing initiative