A nomogram prediction model for the 14-year risk of type 2 diabetes in healthy East China residents: a retrospective cohort study from 15,166 participants

Aims This paper aims to develop a simple and personalized prediction model for type 2 diabetes based on physical examination data to identify high-risk populations in East China.Methods A 14-year retrospective cohort study of 15,166 nondiabetic patients undergoing annual physical examinations was conducted. Multivariate logistic regression and least absolute shrinkage and selection operator (LASSO) models were constructed for univariate analysis, factor selection, and predictive model building. Calibration curves and receiver operating characteristic (ROC) curves were used to assess the calibration and prediction accuracy of the nomogram, and decision curve analysis (DCA) was used to assess the clinical validity of the nomogram.Results The 14-year incidence of type 2 diabetes in our study was 4.1%. We developed a nomogram that predict the risk of type 2 diabetes. The calibration curve shows that the nomogram has good calibration ability, and in internal validation, the area under our ROC curve (AUC) showed statistical accuracy (AUC = 0.865). Finally, DCA supports the clinical predictive value of this nomogram. Conclusion The nomogram of this study can serve as a simple, economical, and widely scalable tool to predict the individualized risk of type 2 diabetes in East China. Successful identification and intervention of high-risk individuals at an early stage can help to provide more effective treatment strategies from the perspectives of predictive, preventive, and personalized medicine.