The XGBoost machine learning model achieved an AUC of 0.854 for predicting carotid atherosclerosis in elderly patients with obstructive sleep apnea, outperforming traditional logistic regression.
Observational (n=1,196)
Yes
A machine learning model using XGBoost accurately predicts carotid atherosclerosis in elderly OSA patients, highlighting nocturnal hypoxemic burden (T90) as a stronger predictor than the traditional apnea-hypopnea index.
Absolute Event Rate: 0.854% vs 0.722%
Background: Carotid atherosclerosis (CAS) is a critical cardiovascular complication in elderly patients with obstructive sleep apnea (OSA). Current risk assessment tools inadequately capture OSA-specific pathophysiological mechanisms for CAS prediction in this high-risk population. Methods: This multicenter retrospective study included 1196 elderly patients (≥60 years) with polysomnography-confirmed OSA from six tertiary hospitals in China. CAS was diagnosed by carotid ultrasound. LASSO (Least Absolute Shrinkage and Selection Operator) regression identified optimal predictive features from 18 candidate variables. Four machine learning algorithms were developed and validated using 5-fold cross-validation. Model interpretability was achieved through SHapley Additive exPlanations (SHAP) analysis. Results: Among participants, 273 (22.8%) had CAS. LASSO regression selected eight optimal features. XGBoost achieved the best performance with test AUC of 0.854, accuracy of 79.8%, sensitivity of 81.2%, and specificity of 78.5%. SHAP analysis revealed systolic blood pressure (importance: 0.3148) and percentage of sleep time with oxygen saturation <90% (T90, importance: 0.2660) as the most influential predictors, surpassing traditional apnea-hypopnea index. Other significant predictors included alcohol consumption, mean oxygen saturation, body mass index, age, platelet count, and smoking status. Conclusion: This study developed the first machine learning-based CAS prediction model for elderly OSA patients, achieving clinically relevant performance (AUC=0.854). The prominence of T90 over conventional apnea-hypopnea index suggests nocturnal hypoxemic burden is more important than respiratory event frequency for cardiovascular risk stratification in this population.
Cai et al. (Mon,) conducted a observational in Obstructive sleep apnea and carotid atherosclerosis (n=1,196). XGBoost machine learning model vs. Logistic regression was evaluated on Area Under the ROC Curve (AUC) for predicting carotid atherosclerosis on the test set. The XGBoost machine learning model achieved an AUC of 0.854 for predicting carotid atherosclerosis in elderly patients with obstructive sleep apnea, outperforming traditional logistic regression.