Transformer-based models for predicting cardiovascular risk in Chinese adults: development and validation

作者：Qiuyu Cao, Xingkun Xu, Lin Hong, Yue Yin, Shengli Wu, Mian Li, Yu Xu, Shaoxin Li, Yuchen Xu, Huapeng Wei, Ruizhi Zheng, Yujing Zhu, Min Xu, Tiange Wang, Zhiyun Zhao, Yiming Mu, Lulu Chen, Tianshu Zeng, Lixin Shi, Qing Su, Xuefeng Yu, Li Yan, Guijun Qin, Qin Wan, Gang Chen, Xulei Tang, Zhengnan Gao, Ruying Hu, Zuojie Luo, Yingfen Qin, Li Chen, Xinguo Hou, Yanan Huo, Qiang Li, Guixia Wang, Yu Zhang, Chao Liu, Y Wang, Feixia Shen, Xuejiang Gu, Tao Yang, Huacong Deng, Yu Zhang, Jiajun Zhao, Guang Ning, Feiyue Huang, Weiqing Wang, Yufang Bi, Jieli Lu · 发表于：European Heart Journal · 年份：2026 · DOI：10.1093/eurheartj/ehag517 · 被引用次数：1 · 研究领域：Lipoproteins and Cardiovascular Health、Artificial Intelligence in Healthcare、Cardiovascular Health and Risk Factors

BACKGROUND AND AIMS: Traditional Cox proportional hazards models show suboptimal performance for cardiovascular disease (CVD) risk prediction in Chinese populations. Transformer-based deep learning models have demonstrated promise in clinical risk prediction. In this study, sex-specific transformer-based models (China-AIHeart) for 10-year CVD risk prediction among Chinese adults were developed and validated. METHODS: The derivation cohort included 156 790 participants [34.6% men; mean [SD] age, 56.7 [8.9] years) without CVD from the China Cardiometabolic Disease and Cancer Cohort. External validation was conducted in two independent Chinese cohorts (Xinjiang and CHARLS). Transformer-based time-to-event prediction models were developed, including a full model (22 predictors) and a simplified model (15 predictors). Performance was compared with Cox models using identical predictors and established risk scores (China-PAR, PREVENT-ASCVD, and SCORE2 Asia-Pacific equations). RESULTS: China-AIHeart demonstrated good discrimination (C-statistic [95% confidence interval, CI]: .767 [.754-.779] in men; .780 [.769-.791] in women), calibration (calibration χ2: 14.806 in men; 9.326 in women; Brier score: .104 in men; .077 in women), and net clinical benefit in predicting CVD risk. Predicted event rates closely matched observed risks across strata. Compared with Cox models with identical predictors, China-AIHeart showed improved discrimination (ΔC-statistic [95% CI]: .027 [.025-.028] in men...