Machine learning methods for anticipating the psychological distress in patients with alzheimer’s disease

Abstract

Recent studies proved that psychological distress is an accelerator of Alzheimer disease (AD). However, the factors that affect the psychological distress of AD patients are still unknown. The aim of this study was to predict the incidence and identify the risk factors of psychological distress in AD patients. Artificial neural networks and Machine learning models were used to predict the incidence of psychological distress in AD patients. Linear regression and decision tree models were used to identify the factors of psychological distress in AD patients. Among all models for predicting the incidence of psychological distress in AD patients, the artificial neural networks with 8 hidden neurons achieved the highest predictive accuracy of 81.92%. In the five machine learning models, the ADTree algorithm made the highest Predictive Accuracy of 77.94%. As for risk factor analysis, the Linear Regression and Decision Tree models reported similar sets of variables that affect the psychological distress of AD patients. Three variables were reported by Linear Regression to be in negative correlation with psychological distress: the use of professional care service, caregiver consuming cigarette, and caregiver consuming alcohol. The incidence of psychological distress in AD patients can be predicted by artificial neural networks with an accuracy of 81.92%. There are four main risk factors for psychological distress of AD patients: "Caregiver experiencing psychological distress", "Caregiver suffering from chronic disease or cancer", "Care recipient's health status being serious or getting worse", and "Lack of professional care service". These findings are potentially helpful for the prediction, prevention and intervention of psychological distress in AD patients.