What is the clinical evidence from this study?

Study design: Cohort. Population: Coexisting hypertension and obstructive sleep apnea (n=708). Intervention: Machine learning models integrating multidimensional metabolic and clinical data vs. None (observational prognostic study). Primary outcome: Major Adverse Cardiovascular and Cerebrovascular Events (MACCEs), including cardiac mortality, acute coronary syndrome, and stroke (XGBoost model AUC 0.898, 95% CI 95% CI: 0.822–0.973).

What does this research mean for the field?

The XGBoost machine learning model effectively predicts long-term major adverse cardiovascular and cerebrovascular events (MACCE) risk with high accuracy (AUC 0.898) in patients with coexisting hypertension and obstructive sleep apnea. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to evaluate long-term risks of cardiovascular and cerebrovascular events in patients with hypertension and obstructive sleep apnea using machine-learning metabolic frameworks.

February 27, 2026Open Access

Multiple machine-learning-driven metabolic frameworks for long-term prognostic risk assessment in patients with coexisting hypertension and obstructive sleep apnea:insights from a multicenter cohort study

Resultado clave

The XGBoost machine learning model predicted long-term MACCE risk with an AUC of 0.898 (95% CI: 0.822–0.973) among patients with coexisting hypertension and obstructive sleep apnea after median 47 months follow-up.

Puntos clave

The study aims to evaluate long-term risks of cardiovascular and cerebrovascular events in patients with hypertension and obstructive sleep apnea using machine-learning metabolic frameworks.
Included 708 patients with hypertension and OSA from January 2017 to December 2021
Collected data on various obesity indices and metabolic measurements
Constructed nine machine learning models to predict major adverse cardiovascular and cerebrovascular events (MACCEs)
Selected XGBoost model for its superior performance based on AUC analysis
XGBoost model showed an AUC of 0.898, indicating strong predictive ability
Key predictors of MACCE risk included male sex, age, TyG, TyG-BMI, HbA1c, and others
The study supports enhanced prediction and detection of high-risk patients for timely intervention

Diseño del estudio

Tipo

Cohort (n=708)

Multicéntrico

Sí

PICO estructurado

Do machine learning-driven metabolic frameworks improve the prediction of long-term MACCE risk in patients with coexisting hypertension and obstructive sleep apnea?

Población

708 patients with coexisting hypertension and obstructive sleep apnea (OSA), median age 54, 68.64% male, from two geographically distinct institutions in China.

Intervención

Machine learning-driven metabolic frameworks (specifically XGBoost, LightGBM, Random Forest, Decision Tree, Gradient Boosting, Multi-Layer Perceptron, SVM, KNN, and GNB) incorporating multidimensional obesity and metabolic indices (TyG-BMI, TyG-NC, TyG-WC, TyG-NHtR, TyG-WHtR) for risk prediction.

Comparador

Cox proportional hazards regression model utilizing backward stepwise selection (used as a benchmark comparator).

Resultado

Major Adverse Cardiovascular and Cerebrovascular Events (MACCEs), a composite of cardiac mortality, acute coronary syndrome, and stroke.composite

Machine learning models, particularly XGBoost, incorporating multidimensional metabolic and obesity indices provide superior long-term prognostic risk assessment for MACCEs in patients with hypertension and OSA.

Resultado numérico

Estimación del efecto: XGBoost model AUC 0.898 (95% CI 95% CI: 0.822–0.973)

Limitaciones

Retrospective study design with potential selection bias and unmeasured confounders.
Missing data and potential inaccuracies in electronic health records.
Lack of advanced imaging-based omics data to characterize obesity phenotypes.
Sample size may be insufficient for detailed subgroup analyses.

Resumen

Background Predictive obesity indices are often based on the body mass index (BMI). Although BMI is widely used, it does not provide a direct measure of obesity. We aimed to utilize multiple machine learning-driven metabolic frameworks to investigate the long-term risk of major adverse cardiovascular and cerebrovascular events (MACCEs) in individuals with hypertension and obstructive sleep apnea (OSA). Methods This study included 708 patients with hypertension and OSA between January 2017 and December 2021. The measurements of height, weight, neck circumference (NC), waist circumference (WC), neck-circumference-to-height ratio (NHtR), and waist-to-height ratio (WHtR) were collected to calculate the triglyceride-glucose (TyG)-BMI, as well as TyG-NC, TyG-WC, TyG-NHtR, and TyG-WHtR indices. Results All patients were allocated to the training cohort (n = 446) and independent validation cohort (n = 262). The Boruta plot presented for identifying key predictors is as follows: male sex, age, TyG, TyG-BMI, HbA1c, FPG, triglyceride, creatinine, fibrinogen and AHI. We constructed nine machine learning models-XGBoost, Light Gradient Boosting Machine, Random Forest, Decision Tree, Gradient Boosting, Multi-Layer Perceptron, Support Vector Machine, K-Nearest Neighbors, and Gaussian Naive Bayes-to predict MACCEs. The XGBoost model was selected due to its superior performance evidenced by an AUC of 0.898 (95% CI: 0.822–0.973) and net clinical benefit. SHAP analysis further clarified variable contributions to MACCE risk. Conclusion This study employed various machine-learning techniques and multidimensional data assessment, allowing for enhanced prediction of metabolic results and supporting the timely detection of high-risk patients with OSA and hypertension in need of focused preventive measures. Clinical Trial Registration https://www.chictr.org.cn/bin/project/edit?pid=206415 , identifier ChiCTR2300075727.

Me gusta

Guardar

Ver artículo completo