Triangulating evidence for cardiometabolic Index: ROC cutoff, spline nonlinearity, and explainable machine learning for CVD high risk - Takeaways - MDSpire

Triangulating evidence for cardiometabolic Index: ROC cutoff, spline nonlinearity, and explainable machine learning for CVD high risk

  • By

  • Haoran Wang

  • Zhiwei Huang

  • Jing Bai

  • Haiqin Yuan

  • Qiaotao Xie

  • Bing He

  • Li Guo

  • Li Wu

  • Dongliang Liu

  • Guirang Zhao

  • Jirui Cai

  • Jin Wang

  • May 20, 2026

  • 0 min

Share

  • 1

    The cardiometabolic index (CMI) integrates waist-to-height ratio and triglycerides/HDL-C to assess cardiovascular disease risk.

  • 2

    In the ChinaHEART Luohe cohort, 21% of participants were classified as high risk for cardiovascular disease based on CMI.

  • 3

    CMI showed modest discrimination for cardiovascular risk status, with multivariable models improving the area under the curve to 0.642.

  • 4

    Higher CMI was significantly associated with increased odds of being classified as high cardiovascular disease risk.

  • 5

    Machine learning approaches confirmed the importance of CMI, ranking it third among features related to cardiovascular disease risk.

Original Source(s)

Triangulating evidence for cardiometabolic Index: ROC cutoff, spline nonlinearity, and explainable machine learning for CVD high risk

  • by Haoran Wang, Zhiwei Huang, Jing Bai, Haiqin Yuan, Qiaotao Xie, Bing He, Li Guo, Li Wu, Dongliang Liu, Guirang Zhao, Jirui Cai, Jin Wang

  • May 20, 2026

Related Content

Exposure to heavy metals and trace elements and risk of dyslipidemia: a nested case-control analysis in rural adults

Causes of Excess Deaths in the US Compared With Other High-Income Countries

School-Based Screening Detected Undiagnosed Hypertension

Novel program enabled large-scale blood pressure screening and identified elevated readings in community setting.