Analyzing the Prevalence of Depression and Its Influencing Factors in Elderly Patients With Obstructive Sleep Apnea: A Machine Learning Approach

Objective: Depressive symptoms are prevalent and detrimental in elderly patients with obstructive sleep apnea (OSA). Understanding the factors influencing these symptoms is crucial. This study aims to use machine learning algorithms to identify the contributing factors in this population. Method: The National Health and Nutrition Examination Survey database provided the data for this study. The study includes elderly patients who are eligible for diagnostic evaluation for OSA. Logistic regression was used to screen their influencing factors, and random forest (RF), extreme gradient boosting (XGB), artificial neural network (ANN), and support vector machine (SVM) were utilized to 4 algorithms were used to construct depressive symptoms classification models, and the best model performance was selected for feature importance ranking. Influential factors included demographics (age, gender, education, etc.), chronic disease status (diabetes, hypertension, etc.), and laboratory findings (white blood cells, C-reactive protein, cholesterol, etc.). Result: Ultimately, we chose 1538 elderly OSA patients for the study, out of which 528 (34.4%) suffered from depressive symptoms. Logistic regression initially identified 17 influencing factors and then constructed classification models based on those 17 using RF, XGB, ANN, and SVM. We selected the best-performing SVM model area under the curve (AUC) = 0.746 based on the AUC values of 0.73, 0.735, 0.742, and 0.746 for the 4 models. We ranked the variables in order of importance: General health status, sleep disorders, gender, frequency of urinary incontinence, liver disease, physical activity limitations, education, moisture, eosinophils, erythrocyte distribution width, and hearing loss. Conclusion: Elderly OSA patients experience a high incidence of depressive symptoms, influenced by various objective and subjective factors. The situation is troubling, and healthcare institutions and policymakers must prioritize their mental health. We should implement targeted initiatives to improve the mental health of high-risk groups in multiple dimensions.