Abstract
To facilitate treatment decisions in people at risk of Cardiovascular Disease (CVD), several risk equations such as the Pooled Cohort Equations and Predicting Risk of Cardiovascular Disease Events (PREVENT) equations have been developed to estimate CVD risk for primary prevention patients. However, it is unclear whether these equations achieve high predictive accuracy and fairness in patients with type 2 diabetes (T2D), and whether a T2D-specific risk equation is needed. Accordingly, we developed a Weibull Accelerated Failure Time (AFT) survival model for predicting the 3-year CVD risk in 23,795 patients with T2D from the All of Us dataset, using sociodemographic information, physical measurements, medication, and CVD history. Among patients without CVD history, our Weibull AFT (vs. PREVENT) achieved a greater C-index (0.646 vs. 0.465), greater Concordance Fractions (0.610–0.674 vs. 0.541–0.600), and comparable Concordance Imparity (0.006 vs. 0.002) across sex and race/ethnicity (0.065 vs. 0.058) subgroups. Our findings highlight the need for a T2D-specific CVD risk equation and demonstrate the value of diverse datasets for developing fair and accurate predictive models.
Data availability
The dataset supporting the conclusions of this article is available from the All of Us Research Program. The data are not openly available. Access to the data requires registration, training, and compliance with the All of Us Research Program data usage policies. The underlying code for this study, including those used to extract and process the training/testing datasets and perform the analysis, is not publicly available but may be made available to qualified researchers on reasonable request from the corresponding author.
References
Woodruff, R. C. et al. Trends in cardiovascular disease mortality rates and excess deaths, 2010–2022. Am. J. Prev. Med. 66 (4), 582–589. https://doi.org/10.1016/j.amepre.2023.11.009 (2024).
Trends and Disparities in Cardiovascular Mortality Among U.S. Adults With and Without, Self-Reported & Diabetes 1988–2015 | Diabetes Care | American Diabetes Association. https://diabetesjournals.org/care/article/41/11/2306/36539/Trends-and-Disparities-in-Cardiovascular-Mortality (accessed 20 Nov 2024).
2013 ACC/AHA Guideline on the Assessment of Cardiovascular Risk. https://doi.org/10.1161/01.cir.0000437741.48606.98.
Karmali, K. N., Goff, D. C., Ning, H. & Lloyd-Jones, D. M. A systematic examination of the 2013 ACC/AHA pooled cohort risk assessment tool for atherosclerotic cardiovascular disease. J. Am. Coll. Cardiol. 64 (10), 959–968. https://doi.org/10.1016/j.jacc.2014.06.1186 (2014).
Shah, N. S. et al. Heterogeneous trends in burden of heart disease mortality by subtypes in the United States, 1999–2018: observational analysis of vital statistics. BMJ 370, m2688. https://doi.org/10.1136/bmj.m2688 (2020).
Tsao, C. W. et al. Heart disease and stroke statistics-2023 update: A report from the American Heart Association. Circulation 147 (8), e93–e621. https://doi.org/10.1161/CIR.0000000000001123 (2023).
Diaz, C. L., Shah, N. S., Lloyd-Jones, D. M. & Khan, S. S. State of the nation’s cardiovascular health and targeting health equity in the United States: A narrative review. JAMA Cardiol. 6 (8), 963–970. https://doi.org/10.1001/jamacardio.2021.1137 (2021).
Lloyd-Jones, D. M. et al. Status of cardiovascular health in US adults and children using the American Heart Association’s New Life’s Essential 8 Metrics: Prevalence estimates from the national health and nutrition examination survey (NHANES), 2013 through 2018. Circulation. 146 (11), 822–835. https://doi.org/10.1161/CIRCULATIONAHA.122.060911 (2022).
Bucholz, E. M., Rodday, A. M., Kolor, K., Khoury, M. J. & de Ferranti, S. D. Prevalence and predictors of cholesterol screening, awareness, and statin treatment among US adults with familial hypercholesterolemia or other forms of severe dyslipidemia (1999–2014). Circulation 137 (21), 2218–2230. https://doi.org/10.1161/CIRCULATIONAHA.117.032321 (2018).
Development and Validation of the American Heart. Association’s PREVENT Equations. https://doi.org/10.1161/CIRCULATIONAHA.123.067626
Novel Prediction Equations for Absolute Risk Assessment of Total Cardiovascular Disease Incorporating Cardiovascular-Kidney-Metabolic Health. A Scientific Statement From the American Heart Association. https://doi.org/10.1161/CIR.0000000000001191
New scientific research will test PREVENT risk calculator among diverse groups. American Heart Association. https://newsroom.heart.org/news/new-scientific-research-will-test-prevent-risk-calculator-among-diverse-groups (accessed 20 Nov 2024).
All of Us Research Hub. https://www.researchallofus.org/ (accessed 28 Aug 2024).
Data Snapshots – All of Us Research Hub. https://www.researchallofus.org/data-tools/data-snapshots/ (accessed 28 Aug 2024).
Goff, D. C. et al. 2013 ACC/AHA guideline on the assessment of cardiovascular risk. Circulation 129 (25_suppl_2), S49–S73. https://doi.org/10.1161/01.cir.0000437741.48606.98 (2014).
Austin, P. C., Lee, D. S. & Fine, J. P. Introduction to the analysis of survival data in the presence of competing risks. Circulation 133 (6), 601–609. https://doi.org/10.1161/CIRCULATIONAHA.115.017719 (2016).
Prinja, S., Gupta, N. & Verma, R. Censoring in clinical trials: Review of survival analysis techniques. Indian J. Community Med. Off. Publ. Indian Assoc. Prev. Soc. Med. 35 (2), 217–221. https://doi.org/10.4103/0970-0218.66859 (2010).
Saikia, R. & Barman, M. P. A review on accelerated failure time models.
Wei, L. J. The accelerated failure time model: A useful alternative to the cox regression model in survival analysis. Stat. Med. 11 (14–15), 1871–1879. https://doi.org/10.1002/sim.4780111409 (1992).
Fisher, A., Rudin, C. & Dominici, F. All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously.
Demler, O. V., Paynter, N. P. & Cook, N. R. Tests of calibration and goodness of fit in the survival setting. Stat. Med. 34 (10), 1659–1680. https://doi.org/10.1002/sim.6428 (2015).
Zhang, W. & Weiss, J. C. Longitudinal fairness with censorship. Proc. AAAI Conf. Artif. Intell. 36 (11), 12235–12243. https://doi.org/10.1609/aaai.v36i11.21484 (2022).
Zhang, W. Fairness with censorship: Bridging the gap between fairness research and real-world deployment. Proc. AAAI Conf. Artif. Intell. 38 (20), 20. https://doi.org/10.1609/aaai.v38i20.30301 (2024).
Coyle, M., Flaherty, G. & Jennings, C. A critical review of chronic kidney disease as a risk factor for coronary artery disease. IJC Heart Vasc. 35, 100822. https://doi.org/10.1016/j.ijcha.2021.100822 (2021).
Jankowski, J., Floege, J., Fliser, D., Böhm, M. & Marx, N. Cardiovascular Disease in Chronic Kidney Disease. Circulation. 16 https://doi.org/10.1161/CIRCULATIONAHA.120.050686 (2021).
Said, S. & Hernandez, G. T. The link between chronic kidney disease and cardiovascular disease. J. Nephropathol. 3 (3), 99–104. https://doi.org/10.12860/jnp.2014.19 (2014).
Saeed, D. et al. Navigating the crossroads: Understanding the link between chronic kidney disease and cardiovascular health. Cureus. 15(12), e51362. https://doi.org/10.7759/cureus.51362
Kotwal, S. S. & Perkovic, V. Kidney disease as a cardiovascular disease priority. Circulation. 24 https://doi.org/10.1161/CIRCULATIONAHA.124.068242 (2024).
Daly, C. Is early chronic kidney disease an important risk factor for cardiovascular disease? A background paper prepared for the UK consensus conference on early chronic kidney disease. Nephrol. Dial. Transplant.. 22(suppl_9), ix19–ix25. https://doi.org/10.1093/ndt/gfm445 (2007).
Quiroga, B. et al. From cardiorenal syndromes to cardionephrology: A reflection by nephrologists on renocardiac syndromes. Clin. Kidney J. 16 (1), 19–29. https://doi.org/10.1093/ckj/sfac113 (2023).
Schultz, W. M. et al. Socioeconomic status and cardiovascular outcomes: Challenges and interventions. Circulation 137 (20), 2166–2178. https://doi.org/10.1161/CIRCULATIONAHA.117.029652 (2018).
Deprivation, S. An important, largely unrecognized risk factor in primary prevention of cardiovascular disease. Circulation. https://www.ahajournals.org/doi/ (accessed 18 Sep) https://doi.org/10.1161/CIRCULATIONAHA.122.060042 (2024).
Yeager, R. et al. Association between residential greenness and cardiovascular disease risk. J. Am. Heart Assoc. 7 (24), e009117. https://doi.org/10.1161/JAHA.118.009117 (2018).
Xu, J. et al. Algorithmic fairness in computational medicine. eBioMedicine 84, 104250. https://doi.org/10.1016/j.ebiom.2022.104250 (2022).
Chen, R. J. et al. Algorithm fairness in artificial intelligence for medicine and healthcare. Nat. Biomed. Eng. 7 (6), 719–742. https://doi.org/10.1038/s41551-023-01056-8 (2023).
Varga, T. V. Algorithmic fairness in cardiovascular disease risk prediction: overcoming inequalities. Open. Heart. 10 (2), e002395. https://doi.org/10.1136/openhrt-2023-002395 (2023).
Paulus, J. K. & Kent, D. M. Predictably unequal: understanding and addressing concerns that algorithmic clinical prediction may increase health disparities. NPJ Digit. Med. 3 (1), 1–8. https://doi.org/10.1038/s41746-020-0304-9 (2020).
Saghafian, S., Kent, D. M. & Goel, S. A framework for considering the value of race and ethnicity in estimating disease risk. Ann. Intern. Med. Res. Rep. Methods.
Dwork, C., Hardt, M., Pitassi, T., Reingold, O. & Zemel, R. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference. ITCS ’12., 214–226. https://doi.org/10.1145/2090236.2090255 (Association for Computing Machinery, 2012).
Grgic-Hlacˇa, N., Zafar, M. B., Gummadi, K. P. & Weller, A. The case for process fairness in learning: Feature selection for fair decision making.
Basu, S., Sussman, J. B., Berkowitz, S. A., Hayward, R. A. & Yudkin, J. S. Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials. Lancet Diabetes Endocrinol. 5 (10), 788–798. https://doi.org/10.1016/S2213-8587(17)30221-8 (2017).
Basu, S. et al. Validation of risk equations for complications of type 2 diabetes (RECODe) using individual participant data from diverse longitudinal cohorts in the U.S. Diabetes Care. 41 (3), 586–595. https://doi.org/10.2337/dc17-2002 (2017).
Heart Disease and Stroke Statistics-2017 Update: A Report From the American Heart Association—PubMed. https://pubmed.ncbi.nlm.nih.gov/28122885/ (accessed 18 Sep 2024).
Bhatt, D. L. et al. Comparative determinants of 4-year cardiovascular event rates in stable outpatients at risk of or with atherothrombosis. JAMA 304 (12), 1350–1357. https://doi.org/10.1001/jama.2010.1322 (2010).
Yang, Y. et al. A responsible framework for assessing, selecting, and explaining machine learning models in cardiovascular disease outcomes among people with type 2 diabetes: Methodology and validation study. JMIR Med. Inf. 13, e66200. https://doi.org/10.2196/66200 (2025).
Kim, K. Risk stratification of cardiovascular disease according to age groups in new prevention guidelines: A review. J. Lipid Atheroscler. 12 (2), 96–105. https://doi.org/10.12997/jla.2023.12.2.96 (2023).
Khan, S. S. et al. Risk-based primary prevention of heart failure: A scientific statement from the American Heart Association. Circulation. 151 (20). https://doi.org/10.1161/CIR.0000000000001307 (2025).
Garcia, G. G. P., Steimle, L. N., Marrero, W. J. & Sussman, J. B. Interpretable policies and the price of interpretability in hypertension treatment planning. Manuf. Serv. Oper. Manag. 26 (1), 80–94. https://doi.org/10.1287/msom.2021.0373 (2024).
Liao, C. Y., Keyvanshokooh, E. & Garcia, G. G. Constraint-aware self-improving large language model for clinical role model generation. SSRN. https://doi.org/10.2139/ssrn.5642250 (2025).
Cao, J., Keyvanshokooh, E. & Liu, T. Safe reinforcement learning with contextual information: Theory and application to personalized comorbidity management. SSRN Electron. J. https://doi.org/10.2139/ssrn.4583667 (2023).
Kuusisto, J. & Laakso, M. Update on type 2 diabetes as a cardiovascular disease risk equivalent. Curr. Cardiol. Rep. 15 (2), 331. https://doi.org/10.1007/s11886-012-0331-5 (2013).
Pencina, M. J. et al. Apolipoprotein B improves risk assessment of future coronary heart disease in the Framingham Heart Study beyond LDL-C and non-HDL-C. Eur. J. Prev. Cardiol. 22 (10), 1321–1327. https://doi.org/10.1177/2047487315569411 (2015).
Acknowledgements
We gratefully acknowledge All of Us participants for their contributions, without whom this research would not have been possible. We also thank the National Institutes of Health’s All of Us Research Program for making available the participant data examined in this study.This research is, in part, funded by the National Institutes of Health (NIH) AIM-AHEAD Program Agreement NO. 1OT2OD032581. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the NIH.HS, MBW, and FJ received funding from the Georgia Center for Diabetes and Translation Research under Award No. NIH/NIDDK P30DK111024.
Funding
This research is, in part, funded by the National Institutes of Health (NIH) AIM-AHEAD Program Agreement NO. 1OT2OD032581. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the NIH. HS, MBW, and FJ received funding from the Georgia Center for Diabetes and Translation Research under Award No. NIH/NIDDK P30DK111024.
Author information
Authors and Affiliations
Contributions
Y.Y. and T.L. contributed equally to the data analysis, numerical analysis, tables and figures generation, manuscript writing. G.P.G. conceptualized the study methodology and directed the methodological approach. G.P.G., E.K., C.L., S.J.L. provided significant input on the methodology, analysis, technical interpretation of results, and manuscript writing. H.S., M.B.W., and F.J. contributed significantly on clinical interpretation and medical insights. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
All research in this manuscript has been performed in accordance with the Declaration of Helsinki and approved by the Institutional Review Board at the Georgia Institute of Technology (Protocol No. H22333). This study analyzes data from the All of Us Research Program, which uses a centralized, electronic informed consent (eConsent) process. It is modular (Primary Consent, HIPAA Authorization, and Genomics Consent) and uses multimedia tools like short videos to ensure participant understanding. Most importantly, it includes a “teach-back” quiz that participants must pass to confirm they understand the voluntary nature of the study. The details of this consent process are provided on their web page (https://allofus.nih.gov/article/all-us-consent-process).
Consent for publication
This manuscript has been read and its submission approved by all authors.
Competing interests
FJP reported receiving grants through the institution from Insulet, Tandem Diabetes Care, Ideal Medical Technologies, Novo Nordisk, and Dexcom; receiving consulting fees from Dexcom; receiving consulting fees to the institution from Insulet. All other authors have no competing interests to declare.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Yang, Y., Liu, T., Liao, CY. et al. Development and evaluation of cardiovascular disease risk prediction models for patients with type 2 diabetes. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45129-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45129-5
