Machine learning to predict high-risk coronary artery disease on CT in the SCOT-HEART trial - study abstract

Aug 3, 2026

Machine learning using routine clinical characteristics was evaluated to predict coronary CT angiography (CCTA) findings and support more efficient resource use. Data from 1,769 SCOT-HEART trial participants trained and tested XGBoost models with 10-fold cross-validation and grid-search hyperparameter selection. One model predicted coronary artery disease (CAD) presence and outperformed the 10-year cardiovascular risk score; a second model predicted increased low-attenuation coronary plaque (LAP) burden but performed similarly and was not improved by clinical inputs alone.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

King’s Research Portal DOI: 10.1136/openhrt-2025-003162 Document Version Publisher's PDF, also known as Version of record Link to publication record in King's Research Portal Citation for published version (APA): Williams, M. C. , Guimaraes, A. R. M. , Jiang, M. , Kwieciński, J. , Weir-McCall, J. R. , Adamson, P. D. , Mills, N. L. , Roditi, G. H. , van Beek, E. J. R. , Nicol, E. , Berman, D. S. , Slomka, P. J. , Dweck, M. R. , Newby, D. E. , & Dey, D.(2025) . Machine learning to predict high-risk coronary artery disease on CT in the SCOT-HEART trial. Open Heart, 12(2), Article :e003162 . [https://doi.org/10.1136/openhrt-2025-003162](https://doi.org/10.1136/openhrt-2025-003162) Citing this paper Please note that where the full-text provided on King's Research Portal is the Author Accepted Manuscript or Post-Print version this may differ from the final Published version. If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections. General rights Copyright and moral rights for the publications made accessible in the Research Portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognize and abide by the legal requirements associated with these rights. •Users may download and print one copy of any publication from the Research Portal for the purpose of private study or research. •You may not further distribute the material or use it for any profit-making activity or commercial gain •You may freely distribute the URL identifying the publication in the Research Portal Take down policy If you believe that this document breaches copyright please contact [librarypure@kcl.ac.uk](librarypure@kcl.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 02. Aug. 2026 Open access Coronary artery disease Machine learning to predict high-risk coronary artery disease on CT in the SCOT-HEART trial Michelle Claire Williams ,1 Alan R M Guimaraes,1 Muchen Jiang,1 Jacek Kwieciński,1,2 Jonathan R Weir-McCall,3 Philip D Adamson ,1,4 Nicholas L Mills,1 Giles H Roditi,5 Edwin J R van Beek,1 Edward Nicol,6,7 Daniel S Berman,8 Piotr J Slomka ,8 Marc R Dweck ,1 David E Newby,1 Damini Dey 9 ► Additional supplemental material is published online only. To view, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[openhrt-2025-003162](openhrt-2025-003162)) . To cite: Williams MC, Guimaraes ARM, Jiang M, et al. Machine learning to predict high-risk coronary artery disease on CT in the SCOTHEART trial. Open Heart 2025;12:e003162 . doi:10 . 1136/ openhrt-2025-003162 Received 25 July 2025 Accepted 11 August 2025 © Author(s) (or their employer(s)) 2025. Re-use permitted under CC BY. Published by BMJ Group. For numbered affiliations see end of article. Correspondence to Dr Michelle Claire Williams; [michelle.williams@ed.ac.uk](michelle.williams@ed.ac.uk) ABSTRACT Background Machine learning based on clinical characteristics has the potential to predict coronary CT angiography (CCTA) findings and help guide resource utilisation. Methods From the SCOT-HEART (Scottish Computed Tomography of the HEART) trial, data from 1769 patients was used to train and to test machine learning models (XGBoost, 10-fold cross validation, grid search hyperparameter selection) . Two models were separately generated to predict the presence of coronary artery disease (CAD) and an increased burden of low-attenuation coronary artery plaque (LAP) using symptoms, demographic and clinical characteristics, electrocardiography and exercise tolerance testing (ETT) . Results Machine lear

FAQs

How were the machine learning models trained and tested in the SCOT-HEART study?

Models were trained and tested using SCOT-HEART trial data from 1,769 patients, with 10-fold cross-validation and grid-search hyperparameter selection.

Which model predicted coronary artery disease (CAD) presence, and how did it perform?

The CAD model predicted presence on CCTA and showed better discrimination than the 10-year cardiovascular risk score, with a higher AUC (0.80 vs 0.75, p=0.004).

Could clinical factors improve prediction of increased low-attenuation coronary plaque (LAP) burden?

No. The LAP burden model performed similarly to the 10-year cardiovascular risk score and did not show meaningful improvement using clinical factors alone.

Aug 3, 2026

Upload by Theodora