Machine Learning-Driven Metabolic Syndrome Prediction: An International Cohort Validation Study.

Background/

Objectives

This study aimed to develop and validate a machine learning (ML)-based metabolic syndrome (MetS) risk prediction model.

Methods

We examined data from 6155 participants of the China Health and Retirement Longitudinal Study (CHARLS) in 2011. The LASSO regression feature selection identified the best MetS predictors. Nine ML-based algorithms were adopted to build predictive models. The model performance was validated using cohort data from the Korea National Health and Nutrition Examination Survey (KNHANES) (n = 5297), the United Kingdom (UK) Biobank (n = 218,781), and the National Health and Nutrition Examination Survey (NHANES) (n = 2549).

Results

The multilayer perceptron (MLP)-based model performed best in the CHARLS cohort (AUC = 0.8908; PRAUC = 0.8073), the logistic model in the KNHANES cohort (AUC = 0.9101, PRAUC = 0.8116), the xgboost model in the UK Biobank cohort (AUC = 0.8556, PRAUC = 0.6246), and the MLP model in the NHANES cohort (AUC = 0.9055, PRAUC = 0.8264).

Conclusions

Our MLP-based model has the potential to serve as a clinical application for detecting MetS in different populations.