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.

Risk factors for mild cognitive impairment in patients with age-related hearing loss: a meta-analysis.

OBJECTIVES: One of the most common sensory impairments in the elderly is age-related hearing loss, and individuals with this condition have a higher risk of mild cognitive impairment than the overall aged population. The purpose of this study was to conduct a systematic review of the literature in order to evaluate the evidence supporting the hypothesis that mild cognitive impairment may be developed in patients with age-related hearing loss. METHODS: The PRISMA principles were followed when searching the databases of the China Knowledge Network, Wanfang, China Biomedical Literature Database, Pub Med, Cochrane Library, Embase, and Web of Science. Two investigators independently carried out the quality assessment, data extraction, and literature review of the eligible studies. Stata 17.0 was used to finish the statistical analysis and descriptive results. RESULTS: A total of 13 articles containing 2,222,036 individuals who were evaluated for demographic traits, factors associated with age-related hearing loss, vascular neurologic factors, and psychological factors were included after 2166 search records were found in the database. In patients with age-related hearing loss, eleven factors were found to be risk factors for the development of mild cognitive impairment: age (OR = 1.63; 95% CI 1.09-2.43), male (OR = 1.29; 95% CI 1.14-1.47), degree of hearing loss (OR = 1.35; 95% CI 1.03-1.75), not wearing hearing aids (OR = 1.56; 95% CI 1.37-1.79), cerebrovascular disease (OR = 1.41; 95% CI 1.17-1.69), cardiovascular disease (OR = 1.29; 95% CI 1.07-1.55), diabetes mellitus (OR = 1.28; 95% CI 1.20-1.35), head injury (OR = 1.22; 95% CI 1.13-1.33), alcohol consumption (OR = 1.28; 95% CI 1.14-1.43), and tobacco use (OR = 1.19; 95% CI 1.14-1.25), and depression (OR = 1.63; 95% CI 1.47-1.81). CONCLUSION: Caregivers can customize care strategies to decrease the occurrence of mild cognitive impairment in elderly deaf patients by considering demographic traits, factors associated with age-related hearing loss, vascular-neurologic factors, and psychological factors.

Development of a Machine Learning Algorithm to Forecast the Likelihood of Postoperative Neurological Complications in Patients With Parotid Tumors.

Objective: The objective of this study was to create and verify a machine learning-driven predictive model to forecast the likelihood of facial nerve impairment in patients with parotid tumors following surgery. Methods: We retrospectively collected data from patients with parotid tumors between 2013 and 2023 to develop a prediction model for postoperative facial nerve dysfunction using 5 ML techniques: Logistic Regression (Logit), Random Forest (RF), XGBoost (XGB), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Predictor variables were screened using binomial-LASSO regression. Results: The study had a total of 403 participants, out of which 56 individuals encountered facial nerve damage after the surgery. By employing binomial-LASSO regression, we have successfully identified 8 crucial predictive variables: tumor kind, tumor pain, surgeon's experience, tumor volume, basophil percentage, red blood cell count, partial thromboplastin time, and prothrombin time. The models utilizing ANN and Logit achieved higher area under the curve (AUC) values, namely 0.829, which was significantly better than the SVM model that had an AUC of 0.724. There were no noticeable disparities in the AUC values between the ANN and Logit models, as well as between these models and other techniques like RF and XGB. Conclusion: Using machine learning, our prediction model accurately predicts the likelihood that patients with parotid tumors may experience facial nerve damage following surgery. By using this model, doctors can assess patients' risks more accurately before to surgery, and it may also help optimize postoperative treatment techniques. It is anticipated that this tool would enhance patients' quality of life and therapeutic outcomes.