Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Current cardiovascular risk assessment tools use a small number of predictors. Here, we study how machine learning might: (1) enable principled selection from a large multimodal set of candidate variables and (2) improve prediction of incident coronary artery disease (CAD) events. An elastic net-based Cox model (ML4H EN-COX ) trained and evaluated in 173,274 UK Biobank participants selected 51 predictors from 13,782 candidates. Beyond most traditional risk factors, ML4H EN-COX selected a polygenic score, waist circumference, socioeconomic deprivation, and several hematologic indices. A more than 30-fold gradient in 10-year risk estimates was noted across ML4H EN-COX quintiles, ranging from 0.25% to 7.8%. ML4H EN-COX improved discrimination of incident CAD (C-statistic = 0.796) compared with the Framingham risk score, pooled cohort equations, and QRISK3 (range 0.754–0.761). This approach to variable selection and model assessment is readily generalizable to a broad range of complex datasets and disease endpoints.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Fry, A., Littlejohns, T. J., Sudlow, C., Doherty, N., Adamska, L., Sprosen, T., Collins, R., & Allen, N. E. (2017) · American Journal of Epidemiology · doi:10.1093/aje/kwx246 · Cited by 3,979 · cited 2×
“42 It could be the case that the predictors identified by ML4H EN-COX have predictive value specific to cohorts with these attributes.”
BackgroundMethodGoff, D. C., Lloyd-Jones, D. M., Bennett, G., Coady, S., D’Agostino, R. B., Gibbons, R., Greenland, P., Lackland, D. T., Levy, D., O’Donnell, C. J., et al. (2014) · Circulation · doi:10.1161/01.cir.0000437741.48606.98 · Cited by 3,697
Deo, R. C. (2015) · Circulation · doi:10.1161/circulationaha.115.001593 · Cited by 3,466
Khera, A. V., Chaffin, M., Aragam, K. G., Haas, M. E., Roselli, C., Choi, S. H., Natarajan, P., Lander, E. S., Lubitz, S. A., Ellinor, P. T., et al. (2018) · Nature Genetics · doi:10.1038/s41588-018-0183-z · Cited by 2,953 · cited 2×
“14 This score has previously been associated with risk of prevalent disease among UK Bio-bank and other study participants.”
BackgroundMethodSelf-citationHidden in Plain Sight — Reconsidering the Use of Race Correction in Clinical Algorithms
Vyas, D. A., Eisenstein, L. G., & Jones, D. S. (2020) · New England Journal of Medicine · doi:10.1056/nejmms2004740 · Cited by 1,731
Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints
van der Ploeg, T., Austin, P. C., & Steyerberg, E. W. (2014) · BMC Medical Research Methodology · doi:10.1186/1471-2288-14-137 · Cited by 809 · cited 1×
“cohorts that are well phenotyped enough to maximize and validate the utility of machine learning-based methods.(1,3) Accelerating the clinical adoption of machine learning will require identifying methods and clinical cohorts that address these caveats and applying them to clinically familiar problems, such as coronar…”
BackgroundCardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis
Ambale-Venkatesh, B., Yang, X., Wu, C. O., Liu, K., Hundley, W. G., McClelland, R., Gomes, A. S., Folsom, A. R., Shea, S., Guallar, E., et al. (2017) · Circulation Research · doi:10.1161/circresaha.117.311312 · Cited by 639
Emdin, C. A., Khera, A. V., Natarajan, P., Klarin, D., Zekavat, S. M., Hsiao, A. J., & Kathiresan, S. (2017) · JAMA · doi:10.1001/jama.2016.21042 · Cited by 378 · cited 2×
“16,36 ML4H EN-COX also identified key hematologic indices describing whitebloodcellcountanddifferential(neutrophilcount,monocyte count), red blood cell characteristics (red blood cell distribution width, mean corpuscular volume), and platelet quantity (platelet…”
BackgroundSelf-citationKhera, A. V., Chaffin, M., Zekavat, S. M., Collins, R. L., Roselli, C., Natarajan, P., Lichtman, J. H., D’Onofrio, G., Mattera, J., Dreyer, R., et al. (2019) · Circulation · doi:10.1161/circulationaha.118.035658 · Cited by 315 · cited 2×
“46 Continuousvariableswerescaledtoameanof0andvarianceof1.Categorical variables with n categories were split into n binary variables.”
BackgroundMethodSelf-citationDamen, J. A., Pajouheshnia, R., Heus, P., Moons, K. G. M., Reitsma, J. B., Scholten, R. J. P. M., Hooft, L., & Debray, T. P. A. (2019) · BMC Medicine · doi:10.1186/s12916-019-1340-7 · Cited by 250 · cited 1×
“7 14 As the number of candidate predictors of CAD increases from tens to thousands, the traditional approach using standard Cox regression models is prone to several limitations.”
Method
Cited by
Integrated multimodal artificial intelligence framework for healthcare applications
Soenksen, L. R., Ma, Y., Zeng, C., Boussioux, L., Villalobos Carballo, K., Na, L., Wiberg, H. M., Li, M. L., Fuentes, I., & Bertsimas, D. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00689-4 · Cited by 380
“Recently, AI/ML models leveraging multiple data modalities have been demonstrated for the domains of cardiology 7 – 9 , dermatology 10 , gastroenterology 11 , gynecology 12 , hematology 13 , immunology 14 , nephrology 15 , neurology 16,17 , oncology 18 – 20 , ophthalmology 21 , psychiatry 22 ,…”
Liu, T., Krentz, A., Lu, L., & Curcin, V. (2025) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztae080 · Cited by 177
Muse, E. D., & Topol, E. J. (2024) · Cell Metabolism · doi:10.1016/j.cmet.2024.02.002 · Cited by 50
Metadata
- Authors
- Agrawal, S., Klarqvist, M. D. R., Emdin, C., Patel, A. P., Paranjpe, M. D., Ellinor, P. T., Philippakis, A., Ng, K., Batra, P., & Khera, A. V.
- Venue
- Patterns
- Publisher
- Elsevier BV
- Published
- 2021-12
- Volume
- 2
- Issue
- 12
- Pages
- 100364
- ISSN
- 2666-3899 (ISSN-L)
- OpenAlex
- W3204068536
- Cited by
- 46
- References
- 14
- FWCI
- 6.67
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction. https://app.cochat.ai/papers/10.1016/j.patter.2021.100364
- The paper
- Agrawal, S., Klarqvist, M. D. R., Emdin, C., Patel, A. P., Paranjpe, M. D., Ellinor, P. T., Philippakis, A., Ng, K., Batra, P., & Khera, A. V. (2021). Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction. Patterns. https://doi.org/10.1016/j.patter.2021.100364
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.