Development and Validation of a Risk Prediction Model for Mild Cognitive Impairment in Older Chinese Adults with Chronic Diseases

Background: As the population continues to age, the prevalence of mild cognitive impairment (MCI) has increased steadily. Studies have shown that older adults with chronic diseases are more likely to develop MCI than are those without chronic conditions, suggesting that chronic diseases may play a significant role in the onset of MCI.Therefore, this study is designed to develop a predictive model for MCI among older individuals with chronic diseases in China and to identify the major factors influencing the occurrence of MCI. Method: This study used data from the 2018 China Health and Retirement Longitudinal Study (CHARLS). A total of 4,712 participants who met the inclusion and exclusion criteria were included, with the dataset randomly divided into training and validation sets at a 7:3 ratio. Thirty indicators, including sociodemographic factors, lifestyle, health status, and psychological status, were analyzed. By combining the results from the Least Absolute Shrinkage and Selection Operator (LASSO) regression and random forest, nine optimal predictors were selected, and a nomogram was constructed on the basis of these factors. The model's discrimination, calibration, clinical applicability, and generalizability were assessed via receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and internal validation. Results: Age, education level, child satisfaction, marital status, depressive symptoms, ADL score, income, memory, and the number of chronic diseases were identified as significant predictors of MCI in older adults with chronic diseases. In the training set, the area under the curve (AUC) was 0.865, and in the validation set, it was 0.860. The calibration curves for both groups were close to the diagonal, and the P values of the Hosmer-Lemeshow test were all greater than 0.05, indicating that the predicted results of the model were highly consistent with the actual outcomes. Decision curve analysis (DCA) confirmed the strong clinical applicability of the model. Conclusion: The nomogram prediction model developed in this study demonstrated good predictive performance and may serve as a useful tool to help identify older adults with chronic diseases who are at increased risk of MCI. These findings may inform future strategies for individualized risk assessment and early management.