Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study
Abstract 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 t...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Cardiovascular Diabetology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12933-025-02611-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863249559355392 |
|---|---|
| author | Qi Huang Xiantong Zou Zhouhui Lian Xianghai Zhou Xueyao Han Yingying Luo Shuohua Chen Yanxiu Wang Shouling Wu Linong Ji |
| author_facet | Qi Huang Xiantong Zou Zhouhui Lian Xianghai Zhou Xueyao Han Yingying Luo Shuohua Chen Yanxiu Wang Shouling Wu Linong Ji |
| author_sort | Qi Huang |
| collection | DOAJ |
| description | Abstract 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. |
| format | Article |
| id | doaj-art-1aadf0121def40a3a0941cd59bd14bf3 |
| institution | Kabale University |
| issn | 1475-2840 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Cardiovascular Diabetology |
| spelling | doaj-art-1aadf0121def40a3a0941cd59bd14bf32025-02-09T12:10:55ZengBMCCardiovascular Diabetology1475-28402025-02-0124111110.1186/s12933-025-02611-0Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort studyQi Huang0Xiantong Zou1Zhouhui Lian2Xianghai Zhou3Xueyao Han4Yingying Luo5Shuohua Chen6Yanxiu Wang7Shouling Wu8Linong Ji9Department of Endocrinology and Metabolism, Peking University People’s HospitalDepartment of Endocrinology and Metabolism, Peking University People’s HospitalWangxuan Institute of Computer Technology (WICT), Peking UniversityDepartment of Endocrinology and Metabolism, Peking University People’s HospitalDepartment of Endocrinology and Metabolism, Peking University People’s HospitalDepartment of Endocrinology and Metabolism, Peking University People’s HospitalDepartment of Cardiology, Kailuan General HospitalDepartment of Cardiology, Kailuan General HospitalDepartment of Cardiology, Kailuan General HospitalDepartment of Endocrinology and Metabolism, Peking University People’s HospitalAbstract 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.https://doi.org/10.1186/s12933-025-02611-0Machine learningRisk predictionType 2 diabetesTrajectories |
| spellingShingle | Qi Huang Xiantong Zou Zhouhui Lian Xianghai Zhou Xueyao Han Yingying Luo Shuohua Chen Yanxiu Wang Shouling Wu Linong Ji Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study Cardiovascular Diabetology Machine learning Risk prediction Type 2 diabetes Trajectories |
| title | Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study |
| title_full | Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study |
| title_fullStr | Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study |
| title_full_unstemmed | Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study |
| title_short | Predicting cardiovascular outcomes in Chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm: a cohort study |
| title_sort | predicting cardiovascular outcomes in chinese patients with type 2 diabetes by combining risk factor trajectories and machine learning algorithm a cohort study |
| topic | Machine learning Risk prediction Type 2 diabetes Trajectories |
| url | https://doi.org/10.1186/s12933-025-02611-0 |
| work_keys_str_mv | AT qihuang predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT xiantongzou predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT zhouhuilian predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT xianghaizhou predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT xueyaohan predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT yingyingluo predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT shuohuachen predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT yanxiuwang predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT shoulingwu predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy AT linongji predictingcardiovascularoutcomesinchinesepatientswithtype2diabetesbycombiningriskfactortrajectoriesandmachinelearningalgorithmacohortstudy |