EUVIMEDObjevte EUVIMED
KohortenstudieOpen access

Machine Learning–Derived Cardiovascular Aging Phenotypes From Cardiac Function and Stroke Risk in the UK Biobank: Cohort Study

Kang Yuan, Deyan Kong, Jinghui Zhong, Mengdi Xie, Rui Liu, Wen Sun, Xinfeng Liu

JMIR Aging · 2026-04-27 · 9 · e77017-e77017

DOI: 10.2196/77017 ↗

At a glance

Kohortenstudie in JMIR Aging, published online on 2026-04-27. Written by Kang Yuan and 6 co-authors. Institution: Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangs…. Major MEDLINE topics: Stroke, Machine Learning, Aging. 38 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Cardiovascular magnetic resonance (CMR) is widely used across various cardiac conditions and systematically assesses cardiac anatomical structures and functional dynamics. Machine learning (ML) can accurately predict outcomes and understand the inherent features of clinical data.

Objective

This study aimed to derive CMR phenotypes related to cardiovascular aging, investigate the relationship between these phenotypes and stroke risk, and relearn these phenotypes using supervised ML.

Methods

We enrolled 36,467 participants without stroke and extracted CMR parameters from the UK Biobank, with follow-up data extending until September 30, 2023. Using the generative topographic mapping technique, we identified latent grid nodes among participants and then derived phenotypes through agglomerative hierarchical clustering. We used supervised ML models to predict cardiac function phenotypes and used Cox proportional hazards models to assess the association between these phenotypes and long-term stroke risk.

Results

We enrolled 36,467 participants in the study. The mean age was 54.9 (SD 7.5) years, with 17,442 (47.8%) male participants. During a mean follow-up time of 14.7 (SD 1.1) years, 500 (1.4%) participants developed stroke and 664 (1.8%) participants died, respectively. After generative topographic mapping modeling, we identified 2 distinct phenotypes: phenotype 1, characterized by adverse cardiac function and an accumulation of cardiovascular risk factors, reflecting cardiovascular aging; and phenotype 2, associated with a lower risk of stroke (hazard ratio 0.695, 95% CI 0.559-0.864; P =.001), which remained significant after accounting for competing mortality (hazard ratio 0.578, 95% CI 0.484-0.691; P

Subjects

MeSH terms (MEDLINE)

StrokeMachine LearningAgingHumansMalePhenotypeUnited KingdomFemaleMiddle AgedCohort StudiesUK BiobankBiological Specimen BanksAgedMagnetic Resonance ImagingRisk Factors

Author keywords

UK Biobankagingcardiac functiongenerative topographic mappingmachine learningphenotypesstroke

Authors and institutions

  • Department of Neurology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu Province, 210002, China, 86 2584801861, 86 2584805169.
  • Department of Neurology, The Second Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, China.
  • Department of Neurology, Centre for Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei,…

Cite

APA

Yuan, K., Kong, D., Zhong, J., Xie, M., Liu, R., Sun, W., & Liu, X. (2026). Machine Learning–Derived Cardiovascular Aging Phenotypes From Cardiac Function and Stroke Risk in the UK Biobank: Cohort Study. JMIR Aging, 9, e77017-e77017. https://doi.org/10.2196/77017

Vancouver

Yuan K, Kong D, Zhong J, Xie M, Liu R, Sun W, et al. Machine Learning–Derived Cardiovascular Aging Phenotypes From Cardiac Function and Stroke Risk in the UK Biobank: Cohort Study. JMIR Aging. 2026;9:e77017-e77017. doi:10.2196/77017

BibTeX
@article{Yuan2026,
  author = {Yuan, Kang and Kong, Deyan and Zhong, Jinghui and Xie, Mengdi and Liu, Rui and Sun, Wen and Liu, Xinfeng},
  title = {Machine Learning–Derived Cardiovascular Aging Phenotypes From Cardiac Function and Stroke Risk in the UK Biobank: Cohort Study},
  journal = {JMIR Aging},
  year = {2026},
  volume = {9},
  pages = {e77017--e77017},
  doi = {10.2196/77017}
}
Start for free →