Related Experiment Video
Updated: Oct 12, 2025
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.7K
A Prediction Model for Prediabetes Risk in Middle-Aged and Elderly Populations: A Prospective Cohort Study in China
Jiahua Wu1, Jiaqiang Zhou1, Xueyao Yin1
1Department of Endocrinology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou 310016, China.
International Journal of Endocrinology
|November 22, 2021
Summary
Waist circumference, family history of diabetes, HbA1c, and fasting plasma glucose are key indicators for prediabetes risk. Combining these factors improves prediction accuracy for prediabetes in adults.
Area of Science:
- Endocrinology
- Metabolic Health
- Public Health
Background:
- Prediabetes poses a significant public health challenge, necessitating identification of risk indicators and predictive models.
- Understanding prediabetes risk factors is crucial for early intervention and prevention strategies, particularly in diverse populations like China.
Purpose of the Study:
- To identify key indicators associated with prediabetes risk.
- To develop and validate a predictive model for prediabetes incidence in a Chinese adult cohort.
Main Methods:
- A cohort of 551 adults aged 40-70 years with normal glucose tolerance and HbA1c at baseline were followed.
- Data collected included demographics, anthropometrics, and metabolic profiles.
- Cox proportional-hazards models and ROC curve analysis (AUC) were used to assess associations and predictive values.
Main Results:
- Prediabetes incidence was 19.96% over an average follow-up of 3.35 years.
- Independent risk factors identified: waist circumference (WC), family history of diabetes (FHD), HbA1c, and fasting plasma glucose (FPG).
- A predictive model combining WC, FHD, HbA1c, and FPG demonstrated strong discriminative ability (AUC: 0.702).
Conclusions:
- WC, FHD, HbA1c, and FPG are significant independent predictors of prediabetes risk.
- The combined use of these predictors substantially enhances the accuracy of prediabetes prediction.
