What is the clinical evidence from this study?

Study design: Cross-Sectional. Population: Obstructive Sleep Apnea and Depression (n=14492). Intervention: Depression vs. No depression. Primary outcome: Obstructive Sleep Apnea (OSA) (OR 1.31, 95% CI 1.08-1.60, p=< 0.005).

What does this research mean for the field?

Depression is significantly associated with an increased risk of obstructive sleep apnea, independent of multiple confounding factors. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

October 10, 2025BMC Psychiatry1 citationsOpen Access

Investigating the role of depression in obstructive sleep apnea and predicting risk factors for OSA in depressed patients: machine learning-assisted evidence from NHANES

Q: What are the key findings of this study?

Depression was significantly associated with an increased risk of obstructive sleep apnea (OR 1.31) after adjusting for multiple confounding factors.

Q: What does this research mean for the field?

Depression is significantly associated with an increased risk of obstructive sleep apnea, independent of multiple confounding factors. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

XCXiangyang ChengShanghai Jiao Tong University FLFang LiuFoshan University XZXiao Chi ZhangThomas Jefferson University

Key Result

Depression was significantly associated with an increased risk of obstructive sleep apnea (OR 1.31) after adjusting for multiple confounding factors.

Study Design

Type

Cross-Sectional (n=14,492)

Structured PICO

Population

14,492 participants from the US National Health and Nutrition Examination Survey were analyzed cross-sectionally to evaluate the association between depression and obstructive sleep apnea.

Outcome

Association between depression and obstructive sleep apnea (OSA)

Depression is independently associated with an increased risk of obstructive sleep apnea, and machine learning models can effectively predict OSA risk in depressed patients.

Main Result

Odds Ratio: 1.31 (95% CI 1.08–1.6)

p-value: p=< 0.005

Limitations

Cross-sectional data precludes the establishment of causal relationships.
Diagnosis of depression and OSA based on self-reported information may introduce misclassification bias.
Insomnia could partially mediate or obscure the depression-OSA link.
Modest sample size of depressed participants may increase overfitting risk for ML models.
External validation in larger cohorts is needed.

Abstract

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.

问 AI

Bookmark

View Full Paper