Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study
Open accessAbstract
BACKGROUND: Cardiovascular complications are major concerns for Chinese patients with type 2 diabetes. Accurately predicting these risks remains challenging due to limitations in traditional risk models. We aimed to develop a dynamic prediction model using machine learning and longitudinal trajectories of cardiovascular risk factors to improve prediction accuracy. METHODS: We included 16,378 patients from the Kailuan cohort, splitting them into training and testing datasets. Using baseline characteristics and changes over a four-year observation period, we developed the ML-CVD-C (Machine Learning Cardiovascular Disease in Chinese) score to predict 10-year cardiovascular risk, including cardiovascular death, nonfatal myocardial infarction, and stroke. We compared the discrimination and calibration of ML-CVD-C with models using only baseline variables (ML-CVD-C [base]), China-PAR (Prediction for ASCVD Risk in China), and PREVENT (Predict Risk of cardiovascular disease EVENTs). Risk stratification improvements were assessed through net reclassification improvement (NRI) and integrated discrimination improvement (IDI). Transition analysis examined the changes in risk stratification over time. RESULTS: The ML-CVD-C score achieved a C-index of 0.80 (95% CI: 0.78-0.82) in the testing cohort, significantly outperforming the ML-CVD-C (base) score, China-PAR, and PREVENT, which had C-index values of 0.62-0.65. ML-CVD-C also provided more accurate cardiovascular risk estimates, though all models tended to overestimate the prevalence of high-risk cases. Stratification by the ML-CVD-C score showed substantial improvement, with NRI gains of 57.7%, 44.1%, and 47.3%, and IDI gains of 10.1%, 7.9%, and 8.4% compared to the other three scores. Both the trajectory and machine learning algorithm contributed significantly to the enhancement of model performance. Transition analysis revealed that participants who remained in the same risk category or were reclassified to a lower category exhibited 22% and 86% reductions in cardiovascular risk compared to those reclassified to a higher risk category during the observation period. CONCLUSIONS: The ML-CVD-C model, incorporating dynamic cardiovascular risk trajectories and a machine learning algorithm, significantly improves risk prediction accuracy for Chinese patients with diabetes. This model may serve as a valuable tool for more personalized cardiovascular risk management in type 2 diabetes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Recent studies from Malaysia and China suggest that regionally developed machine learning models can improve performance in local cohorts, but local validation, calibration assessment, and broader external testing remain essential before wider implementation.
“At the same time, recent studies from Malaysia and China suggest that regionally developed machine learning models can improve performance in local cohorts, but these same studies also show why local validation, calibration assessment, and broader external testing remain essential before wider implementation (14, 15).”
From AI-driven cardiovascular risk prediction in patients with diabetes: bridging algorithmic innovation to equitable clinical application (2026) · cites this paper as [15]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
MissForest—Non-parametric missing value imputation for mixed-type data
Stekhoven, D. J., & Bühlmann, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/btr597 · Cited by 6,156 · see citing works
Epidemiology of Diabetes and Diabetes-Related Complications
Deshpande, A. D., Harris-Hayes, M., & Schootman, M. (2008) · Physical Therapy · doi:10.2522/ptj.20080020 · Cited by 1,773 · see citing works
Functional Data Analysis for Sparse Longitudinal Data
Yao, F., Müller, H.-G., & Wang, J.-L. (2005) · Journal of the American Statistical Association · doi:10.1198/016214504000001745 · Cited by 1,595 · see citing works
Development and validation of the American Heart Association’s PREVENT equations
Khan, S. S., Matsushita, K., Sang, Y., Ballew, S. H., Grams, M. E., Surapaneni, A., Blaha, M. J., Carson, A. P., Chang, A. R., Ciemins, E., et al. (2024) · Circulation · doi:10.1161/circulationaha.123.067626 · Cited by 1,234 · see citing works
Prevalence and Treatment of Diabetes in China, 2013-2018
Wang, L., Peng, W. H., Zhao, Z., Zhang, M., Shi, Z., Song, Z., Zhang, X., Li, C., Huang, Z., Sun, X., et al. (2021) · JAMA · doi:10.1001/jama.2021.22208 · Cited by 970 · see citing works
Self-citationPredicting the 10-Year Risks of Atherosclerotic Cardiovascular Disease in Chinese Population
Yang, X., Li, J., Hu, D., Chen, J., Li, Y., Huang, J., Liu, X., Liu, F., Cao, J., Shen, C., et al. (2016) · Circulation · doi:10.1161/circulationaha.116.022367 · Cited by 682 · see citing works
Wu, S., Huang, Z., Yang, X., Zhou, Y., Wang, A., Chen, L., Zhao, H., Ruan, C., Wu, Y., Xin, A., et al. (2012) · Circulation Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.111.963694 · Cited by 429 · see citing works
Self-citationSCORE2-Diabetes: 10-year cardiovascular risk estimation in type 2 diabetes in Europe
SCORE2-Diabetes Working Group and the ESC Cardiovascular Risk Collaboration, Pennells, L., Kaptoge, S., Østergaard, H. B., Read, S. H., Carinci, F., Franch-Nadal, J., Petitjean, C., Taylor, O., Hageman, S. H. J., et al. (2023) · European Heart Journal · doi:10.1093/eurheartj/ehad260 · Cited by 329 · see citing works
Contemporary model for cardiovascular risk prediction in people with type 2 diabetes
Kengne, A. P., Patel, A. A., Marre, M., Travert, F., Lièvre, M. M., Zoungas, S., Chalmers, J. P., Colagiuri, S., Grobbee, D. E., Hamet, P., et al. (2011) · European Journal of Cardiovascular Prevention & Rehabilitation · doi:10.1177/1741826710394270 · Cited by 183 · see citing works
Oshima, M., Neuen, B. L., Li, J., Perkovic, V., Charytan, D. M., de Zeeuw, D., Edwards, R., Greene, T., Levin, A., Mahaffey, K. W., et al. (2020) · Journal of the American Society of Nephrology · doi:10.1681/asn.2020050723 · Cited by 176 · see citing works
Buse, J. B., Bain, S. C., Mann, J. F. E., Nauck, M. A., Nissen, S. E., Pocock, S., Poulter, N. R., Pratley, R. E., Linder, M., Monk Fries, T., et al. (2020) · Diabetes Care · doi:10.2337/dc19-2251 · Cited by 175 · see citing works
Glycemic variability and cardiovascular disease in patients with type 2 diabetes
Martinez, M., Santamarina, J., Pavesi, A., Musso, C., & Umpierrez, G. E. (2021) · BMJ Open Diabetes Research & Care · doi:10.1136/bmjdrc-2020-002032 · Cited by 155 · see citing works
Dziopa, K., Asselbergs, F. W., Gratton, J., Chaturvedi, N., & Schmidt, A. F. (2022) · Diabetologia · doi:10.1007/s00125-021-05640-y · Cited by 99 · see citing works
Pei, J., Wang, X., Pei, Z., & Hu, X. (2023) · Cardiovascular Diabetology · doi:10.1186/s12933-023-02026-9 · Cited by 59 · see citing works
Pylypchuk, R. D., Wells, S., Kerr, A., Poppe, K., Harwood, M. L. N., Mehta, S., Grey, C., Wu, B., Selak, V., Drury, P., et al. (2021) · The Lancet · doi:10.1016/s0140-6736(21)00572-9 · Cited by 57 · see citing works
Cumulative Systolic Blood Pressure Load and Cardiovascular Risk in Patients With Diabetes
Wang, N., Harris, K., Hamet, P., Harrap, S. B., Mancia, G., Poulter, N. R., Williams, B., Zoungas, S., Woodward, M., Chalmers, J. P., et al. (2022) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2022.06.039 · Cited by 55 · see citing works
Xia, Q., Chen, Y., Yu, Z., Huang, Z., Yang, Y., Mao, A., & Qiu, W. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1186330 · Cited by 50 · see citing works
Tang, X., Zhang, D., He, L., Wu, N., Si, Y., Cao, Y., Huang, S., Li, N., Li, J., Dou, H., et al. (2019) · American Heart Journal · doi:10.1016/j.ahj.2019.01.009 · Cited by 32 · see citing works
Lindbohm, J. V., Sipilä, P. N., Mars, N., Knüppel, A., Pentti, J., Nyberg, S. T., Frank, P., Ahmadi‐Abhari, S., Brunner, E. J., Shipley, M. J., et al. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00079-0 · Cited by 32 · see citing works
Zou, X., Huang, Q., Luo, Y., Ren, Q., Han, X., Zhou, X., & Ji, L. (2022) · Diabetologia · doi:10.1007/s00125-022-05748-9 · Cited by 21 · see citing works
Self-citationDong, W., Wan, E. Y. F., Fong, D., Tan, K. C. B., Tsui, W. W. S., Hui, E. M., Chan, K. H., Fung, C. S. C., & Lam, C. L. K. (2024) · Diabetes Obesity and Metabolism · doi:10.1111/dom.15745 · Cited by 18 · see citing works
Khan, M. S., Segar, M. W., Usman, M., Patel, K. V., Spall, H. G. C. V., DeVore, A. D., Vaduganathan, M., Lam, C. S. P., Zannad, F. M., Verma, S., et al. (2023) · JACC Heart Failure · doi:10.1016/j.jchf.2023.03.025 · Cited by 15 · see citing works
Wang, M., Francis, F., Kunz, H., Zhang, X., Wan, C., Liu, Y., Taylor, P., Wild, S. H., & Wu, H. (2022) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2022.100072 · Cited by 15 · see citing works
Liang, J., Li, Q., Fu, Z., Liu, X., Shen, P., Sun, Y., Zhang, J., Lu, P., Lin, H., Tang, X., et al. (2023) · European Journal of Preventive Cardiology · doi:10.1093/eurjpc/zwad198 · Cited by 15 · see citing works
Ding, J., Luo, Y., Shi, H., Chen, R., Luo, S., Yang, X., Xiao, Z., Liang, B., Yan, Q., Xu, J., et al. (2023) · Journal of Diabetes Investigation · doi:10.1111/jdi.14069 · Cited by 9 · see citing works
Self-citationDong, W., Wan, E. Y. F., Bedford, L. E., Wu, T., Wong, C. K. H., Tang, E. H. M., & Lam, C. L. K. (2020) · Public Health · doi:10.1016/j.puhe.2020.06.020 · Cited by 8 · see citing works
Zhang, X., Yang, J., Ruan, H., Zheng, Y., Zhao, L., Li, L., Zhang, M., Duan, L., & He, S. (2022) · Experimental Gerontology · doi:10.1016/j.exger.2022.111952 · Cited by 7 · see citing works
Huang, Q., Zou, X., Gao, P., Han, X., Zhou, X., & Ji, L. (2023) · Journal of Global Health · doi:10.7189/jogh.13.04032 · Cited by 7 · see citing works
Self-citationChen, F., Wang, J., Chen, X., Yu, L., An, Y., Gong, Q., Chen, B., Xie, S., Zhang, L., Shuai, Y., et al. (2023) · Diabetology & Metabolic Syndrome · doi:10.1186/s13098-023-01039-4 · Cited by 1 · see citing works
P 30: Cardiovascular risk factors in type 2 diabetes along 3 years of follow-up
Arrieta, F., Piñera, M., Nogales, P., Iglesias, R., Tutor, E., Salinero, M., Abanades, J. C., Botella-Carretero, J. I., Calañas, A., Iglesias, P., et al. (2012) · Diabetes & Metabolism · doi:10.1016/s1262-3636(12)71610-5 · Cited by 1 · see citing works
Chen, W. Y., Liu, X. F., Shen, P., Chen, Q., Sun, Y., Wu, J., Lu, P.-J., Zhang, J. Y., Lin, H., Tang, X., et al. (2022) · PubMed · doi:10.3760/cma.j.cn112338-20211206-00952 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Dong, B., Chen, Y., Yang, X., Chen, Z., Zhang, H., Gao, Y., Zhao, E., & Zhang, C. (2025) · Cardiovascular Diabetology · doi:10.1186/s12933-025-02729-1 · Cited by 80 · see citing works
Digital twin paradigm in diabetes prediction and management
Olawade, D. B., Owhonda, R. C., Alabi, J. O., Egbon, E., Daniel, R. I. A., & Bello, O. J. (2025) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2025.113075 · Cited by 17 · see citing works
Zahedi, M., Das, S., Dabla, P. K., & Kandar, S. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108672 · Cited by 4 · see citing works
Nicolucci, A., Vespasiani, G., Mannino, D., Russo, G. T., Lucisano, G., Rossi, M. C., Ponzani, P., Cosmo, S. D., Cianni, G. D., Lencioni, C., et al. (2025) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2025.112900 · Cited by 4 · see citing works
Jiang, Z.-Z., Jiang, Y., Wang, Y., Zhou, Y., Peng, R.-L., Cai-ye, M., & Liu, X. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03247-6 · Cited by 4 · see citing works
Self-citationCao, Q., Xu, X., Hong, L., Yin, Y., Wu, S., Li, M., Xu, Y., Li, S., Xu, Y., Wei, H., et al. (2026) · European Heart Journal · doi:10.1093/eurheartj/ehag517 · Cited by 3 · see citing works
Self-citationChen, X., Li, Z. Y., Fan, X., Yan, Y., & Liu, S. (2025) · BMC Cardiovascular Disorders · doi:10.1186/s12872-025-04786-6 · Cited by 2 · see citing works
Liu, S., Liu, B., Zhang, Y., Qiu, X., Fu, W., & Yang, C. (2025) · Diabetes Obesity and Metabolism · doi:10.1111/dom.70277 · Cited by 1 · see citing works
Chen, J., Fan, C., Wang, Y., Lei, Y., Jiang, H., Gong, T., Tang, C., Hong, D., Cheng, C., Mo, P. C., et al. (2026) · Journal of Translational Medicine · doi:10.1186/s12967-026-07850-7 · Cited by 1 · see citing works
Self-citationWu, W., Yang, M., Qin, J., Gui, S., Zhang, Z., Zhang, Y., & Du, Y. (2026) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2026.1738641 · Cited by 1 · see citing works
Li, H., Xu, Z., Cen, Y., & Liu, X. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1831220
“…performance to equitable clinical application: a translational framework for machine learning-based cardiovascular risk prediction in patients with type 2 diabetes. why local validation, calibration assessment, and broader external testing remain essential before wider implementation (14, 15).”
Huang, Q., Zou, X., Boyko, E. J., Lian, Z., Zhou, X., Han, X., & Ji, L. (2026) · European Journal of Preventive Cardiology · doi:10.1093/eurjpc/zwag196
Self-citationLi, X., Li, Z., Ji, Y., Yan, Y., Chen, X., Gao, L., Wei, B., Zhang, C., Duan, R., & Liu, S. (2026) · Metabolism and Target Organ Damage · doi:10.20517/mtod.2026.60
Dai, Y., Su, H., Zhang, H., Chen, J., Xu, G.-X., & Wang, H.-X. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1898316
Advances in Cardiovascular Disease Risk Prediction in People with Diabetes
Li, Y., & Xue, J. (2026) · Journal of Biosciences and Medicines · doi:10.4236/jbm.2026.149011
- Authors
- Huang, Q., Zou, X., Lian, Z., Zhou, X., Han, X., Luo, Y., Chen, S., Wang, Y., Wu, S., & Ji, L.
- Affiliations
- Peking University People's Hospital (CN)
- Peking University (CN)
- Kailuan General Hospital (CN)
- Corresponding author
- Wu, Shouling
- Ji, Linong
- ORCID
- Venue
- Cardiovascular Diabetology
- Published
- 2025-02-07
- Volume
- 24
- Issue
- 1
- Pages
- 61-61
- ISSN
- 1475-2840 (ISSN-L)
- PMC
- PMC11806858
- OpenAlex
- W4407238561
- Cited by
- 15
- References
- 31
- Citations by year
- 2026: 8 · 2025: 7
- FWCI
- 10.23
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Cardiovascular Diabetology (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (T2341011)
- Beijing Nova Cross program (Z211100002121169)
- Special Fund for Young Scientists of National Science and Technology Major Project of China (2023ZD0508801)
- Topics
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes, Cardiovascular Risks, and Lipoproteins
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Health Promotion and Cardiovascular Prevention
- Keywords
- type 2 diabetes, cardiovascular risk prediction, machine learning, cardiovascular disease, myocardial infarction, stroke, cardiovascular mortality, risk reclassification, net reclassification improvement, integrated discrimination improvement, transition analysis, Chinese patients
- MeSH terms
- Machine Learning, Heart Disease Risk Factors, East Asian People, Aged, Cardiovascular Diseases, China, Decision Support Techniques, Diabetes Mellitus, Type 2, Female, Humans, Male, Middle Aged, Predictive Value of Tests, Prognosis, Risk Factors, Time Factors, Reproducibility of Results, Risk Assessment
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
