# A predictive model for metabolic syndrome in a community-based population with sleep apnea: a secondary prevention screening tool using simple and accessible indicators

## TL;DR

This study creates a model to predict metabolic syndrome in people with sleep apnea using simple indicators like BMI, age, and gender, enabling early risk assessment without complex tests.

## Contribution

A novel machine learning model for metabolic syndrome prediction using accessible lifestyle indicators in sleep apnea patients is developed and validated.

## Key findings

- The logistic regression model achieved an AUC of 0.814, showing strong predictive ability for metabolic syndrome.
- Key predictors included BMI, age, and gender, with consistent performance confirmed through calibration and external validation.
- The model enables self-assessment of metabolic syndrome risk using simple indicators, improving early identification and prognosis.

## Abstract

To establish a secondary prevention screening model for predicting metabolic syndrome (MetS) based on community obstructive sleep apnea (OSA) screening, using simple and easily accessible indicators, to help early identification of high-risk individuals and improve prognosis and reduce mortality.

This study enrolled adults newly diagnosed with OSA from community settings in China, collecting comprehensive demographic and lifestyle data. To identify key predictive variables, least absolute shrinkage and selection operator (LASSO) regression was employed for feature selection. Nine machine learning algorithms, such as logistic regression, random forest, and support vector machine (SVM), were then used to build predictive models, with each undergoing rigorous training, hyperparameter tuning, and evaluation on stratified training, validation, and test datasets. Model performance was evaluated using multiple metrics, including the area under the receiver operating characteristic curve (AUC-ROC), accuracy, sensitivity, specificity, F1 score, calibration curves, and clinical decision curve analysis (DCA). To improve interpretability, Shapley additive explanations (SHAP) analysis was applied to quantify each predictor's contribution to the model's output.

Among the nine machine learning algorithms evaluated, the logistic regression model exhibited superior performance. The finalized model achieved an AUC of 0.814 on the test dataset, demonstrating strong discriminative ability. Key performance metrics included a sensitivity of 0.794, specificity of 0.647, accuracy of 0.693, and an F1 score of 0.617. Feature importance analysis highlighted body mass index (BMI), age, and gender as the most significant predictors of MetS. Calibration curves and clinical DCA further confirmed the model's reliability, showing close alignment between predicted probabilities and observed outcomes, thus affirming its clinical utility. External validation reinforced the model's robustness, yielding an AUC of 0.818, with consistent discrimination and well-calibrated predictions.

This study successfully developed a MetS prediction model based on community environment. The model relies solely on simple, easily obtainable self-reported indicators and demonstrates good predictive performance. This model, as a primary screening tool, enables residents to assess their MetS risk status independently, without relying on complex biochemical tests or the assistance of specialized medical personnel.

Flowchart illustrating the prediction model for community-based populations with sleep apnea. It progresses from OSA screening with lifestyle data collection to optimal model selection using machine learning and clinical risk prediction, and ends with a web-based calculator for metabolic syndrome risk self-assessment. Indicators include insulin resistance, obesity, hypertension, high triglycerides, and low HDL cholesterol. The chart also features training, validation, and test sets, as well as model performance comparison. Simple lifestyle indicators are shown with illustrations of smoking, alcohol, diet, and sleep habits.