Development and Validation of 10‐Year Prediction Models for Cardiovascular, Kidney and Metabolic Events Among Chinese Patients With Prediabetes in Hong Kong
Authors' conclusion
We developed interpretable prediction models for clinically actionable events among Chinese patients with prediabetes in Hong Kong to inform clinical strategies and resource allocation.
Study context
- Population
- Chinese adults with prediabetes in Hong Kong, identified in 2012 and followed through 2022adults with prediabetes identified in 2012
- Participants
- 129,834 adultsEvents: 19.4% of patients developed cardiovascular disease (CVD)
- Predictors
- Office-based non-laboratory model and three extended models with laboratory results, transformations, interactions and medications; key predictors included age, sex, smoking status, Charlson comorbidity index, body mass index, systolic blood pressure, lipid profiles, estimated glomerular filtration rate and medications
- Predicted outcome
- cardiovascular disease (CVD), hypertension, Type 2 diabetes mellitus (T2DM), chronic kidney disease (CKD), CVD subtypes and all-cause mortality
Methodological detailsdevelopment and validation of 10-year prediction models, backward stepwise Cox regression
- Development and validation of 10-year prediction models
- Backward stepwise Cox regression
Model performance
As reported in the abstract
10-year
C-index
CVD
0.702
Hypertension
0.697
T2DM
0.704
CKD
0.790
Mortality
0.816
CVD subtypes C-index range
0.673-0.830
Further findings
Machine learning models
- Four selected machine learning (ML) approaches showed comparable performance
Haemoglobin A1c (HbA1c)- vs fasting plasma glucose (FPG)-based models
- HbA1c- and FPG-based models showed comparable performance
Follow-up
- Median follow-up
- 10.4 years
Original publication
Development and Validation of 10‐Year Prediction Models for Cardiovascular, Kidney and Metabolic Events Among Chinese Patients With Prediabetes in Hong Kong. Diabetes Obes Metab. Published 9 November 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →