Relationship between cardiometabolic index and worsening renal function in T2DM : Insights from machine learning, growth mixture modelling, and development of a web‐based risk prediction tool
Primary result · WRFResult — go to the resultAdjusted hazard ratio 1.16 95% CI 1.09–1.24Authors' conclusion
Elevated CMI is positively associated with WRF in patients with T2DM, and its incorporation into predictive models may improve early identification of high-risk individuals.
Study context
- Population
- Participants with T2DM from the Action to Control Cardiovascular Risk in Diabetes trial
- Participants
- 10,094 participants
- Comparison
- Highest vs lowest cardiometabolic index (CMI) tertile
- Primary endpoint
- WRF: doubling of serum creatinine from baseline or eGFR decline >20 mL/min/1.73 m² during follow-up
Methodological detailsmachine learning, growth mixture modelling, external validation in single-centre Chinese cohort, Web-based risk prediction tool developed
- Machine learning
- Growth mixture modelling
- External validation in single-centre Chinese cohort
- Web-based risk prediction tool developed
Primary result
WRF
Adjusted hazard ratio
1.16
95% CI 1.09–1.24
Highest CMI tertilevs Lowest CMI tertile
aHR 1.16 (95% CI 1.09–1.24)
As reported in the abstract
Further findings
Prediction model performance
- Six variables in final model: CMI, estimated glomerular filtration rate (eGFR), age, FPG, urinary albumin, urinary creatinine
- All six models showed stable and favourable performance; XGBoost best
- SHAP: higher eGFR the most influential predictor
Subgroup interactions
- Significant interactions among female participants, older individuals and those in the standard glycemic control arm
CMI trajectories (growth mixture model (GMM))
- Three trajectory groups: 'low-stable', 'moderate-stable', 'high-increasing'; higher baseline CMI and 'high-increasing' membership associated with substantially elevated worsening renal function (WRF) risk
Original publication
Relationship between cardiometabolic index and worsening renal function in T2DM : Insights from machine learning, growth mixture modelling, and development of a web‐based risk prediction tool. Diabetes Obes Metab. Published 22 December 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →