BMC psychiatry · 2025
Investigating the role of depression in obstructive sleep apnea and predicting risk factors for OSA in depressed patients: machine learning-assisted evidence from NHANES.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Cheng Xiangyang, Liu Fang, Zhang Xiao, Liu Ye, Guo Jiaxi, Zhong Xuelai, Tian Dongdong, Pei Aijie, Xiang Xuwu, Yao Yongxing, Su Diansan
Аннотация
OBJECTIVE: The relationship between depression and obstructive sleep apnea (OSA) remains controversial. Therefore, this study aims to explore their association and utilize machine learning models to predict OSA among individuals with depression within the United States population.
METHODS: Cross-sectional data from the American National Health and Nutrition Examination Survey were analyzed. The sample included 14,492 participants. Weighted logistic regression analysis was performed to examine the association between OSA and depression.Additionally, interaction effect analyses were conducted to assess potential interactions between each subgroup and the depressed population.Multiple machine learning models were constructed within the depressed population to predict the risk of OSA among individuals with depression, employing the Shapley Additive Explanations(SHAP) interpretability method for analysis.
RESULTS: A total of 14,492 participants were collected. The full-adjusted model OR for Depression and OSA was (OR,1.31;95%CI(1.08, 1.60); P < 0.005).The positive association between depression and OSA was revealed in all models.The interaction analysis revealed no subgroups exhibited statistical significance. The Neural Network was identified as the best-performing model, achieving the highest Youden's Index, AUC, and Kappa scores. SHAP analysis highlighted the most significant predictors of OSA: BMI, Age, Marital status, Hypertension, Caffeine intake, Sex, Alcohol status, and Fat intake.
CONCLUSION: In conclusion, our research indicates that depression is associated with OSA, highlighting the importance of early detection and management of depressive symptoms in individuals at risk of OSA.ML models were developed to predict OSA and were interpreted using SHAP. This method identified key factors associated with OSA, encompassing demographic, dietary, and health-related dimensions.
METHODS: Cross-sectional data from the American National Health and Nutrition Examination Survey were analyzed. The sample included 14,492 participants. Weighted logistic regression analysis was performed to examine the association between OSA and depression.Additionally, interaction effect analyses were conducted to assess potential interactions between each subgroup and the depressed population.Multiple machine learning models were constructed within the depressed population to predict the risk of OSA among individuals with depression, employing the Shapley Additive Explanations(SHAP) interpretability method for analysis.
RESULTS: A total of 14,492 participants were collected. The full-adjusted model OR for Depression and OSA was (OR,1.31;95%CI(1.08, 1.60); P < 0.005).The positive association between depression and OSA was revealed in all models.The interaction analysis revealed no subgroups exhibited statistical significance. The Neural Network was identified as the best-performing model, achieving the highest Youden's Index, AUC, and Kappa scores. SHAP analysis highlighted the most significant predictors of OSA: BMI, Age, Marital status, Hypertension, Caffeine intake, Sex, Alcohol status, and Fat intake.
CONCLUSION: In conclusion, our research indicates that depression is associated with OSA, highlighting the importance of early detection and management of depressive symptoms in individuals at risk of OSA.ML models were developed to predict OSA and were interpreted using SHAP. This method identified key factors associated with OSA, encompassing demographic, dietary, and health-related dimensions.