Development of a neural network-based risk prediction model for mild cognitive impairment in older adults with functional disability.

BACKGROUND

Mild Cognitive Impairment (MCI) is a critical transitional stage between normal aging and Alzheimer's disease, and its early identification is essential for delaying disease progression.

METHODS

This study, based on data from the 2020 China Health and Retirement Longitudinal Study (CHARLS), focuses on older adults with functional disability as the target population. LASSO regression, combined with univariable and multivariable logistic regression, was employed to select feature variables for predictive modeling. Seven machine learning algorithms, including logistic regression, decision tree, random forest, support vector machine, gradient boosting decision tree, k-nearest neighbors, and neural network, were used to develop predictive models. Model performance was evaluated using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (ROC AUC).

RESULTS

The results indicated that residence location, alcohol consumption, life satisfaction, depressive symptoms, and education level are key factors influencing the risk of MCI among older adults with functional disability. Among the models, the neural network achieved the best overall performance (Accuracy: 0.71, Precision: 0.70, Recall: 0.74, F1 Score: 0.72, ROC AUC: 0.80) with stable results across both the training and test sets.

CONCLUSION

This study provides a scientific tool for the early screening of MCI in older adults with functional disability and offers an efficient and scalable predictive model for clinical applications and community health services.