Machine learning ensemble meets clinical practice: developing a real-world risk prediction model for metabolic syndrome using super learner and scorecard approaches

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Super learner AUC 0.816 (development), 0.810 (validation); Scorecard AUC 0.793 (development), 0.788 (validation)

• Primary Outcome: Area under ROC curve for metabolic syndrome risk prediction

• Nnt Or Sensitivity: Sensitivity and specificity not reported; five-level risk stratification system developed

• Confidence Interval: Development: 0.814-0.817 (super learner), 0.791-0.794 (scorecard); Validation: 0.808-0.813 (super learner), 0.785-0.791 (scorecard)

Clinical Application

Risk scorecard appears practical for clinical use with ten predictors, though specific variables not detailed in abstract Limited direct applicability due to Chinese population derivation; would require validation in Australian cohorts before implementation. Could inform RACGP cardiovascular risk assessment guidelines if validated locally Adults undergoing routine health screening, particularly in Asian populations

Abstract

INTRODUCTION: Metabolic syndrome (MetS) refers to a cluster of metabolic abnormalities that significantly increase the risk of developing cardiovascular diseases (CVDs). Traditional binary definitions of MetS fall short in capturing its severity spectrum, limiting personalized risk stratification. OBJECTIVES: We aimed to develop a super learner model and multilevel risk scorecard to improve MetS risk prediction and support early cardiovascular risk identification. METHODS: This study included a total of 460,256 health examination records from Zhejiang, China (2018-2023), with 344,925 used for model development and 115,331 used for external validation. A super learner model combining multiple machine learning algorithms was constructed to predict MetS risk. Key predictors identified through feature selection were used to develop a logistic regression-based MetS risk scorecard, stratifying individuals into five risk levels for practical and interpretable applications. RESULTS: The super learner model achieved area under the receiver operating characteristics (AUCs) of 0.816 (95 % confidence interval [CI]: 0.814-0.817) and 0.810 (95 % CI: 0.808-0.813) in the development and external validation cohorts, respectively. The risk scorecard, which incorporates ten predictors, demonstrated comparable performance, with AUCs of 0.793 (95 % CI: 0.791-0.794) and 0.788 (95 % CI: 0.785-0.791) in the respective cohorts. Based on the risk scorecard, individuals were stratified into five categories: very low, low, normal, high, and very high risk levels. CONCLUSION: The super learner model provides a highly accurate tool for MetS risk prediction, whereas the risk scorecard offers a practical and interpretable solution for clinical and personal use. These models enable precise risk assessment to guide prevention and improve outcomes.

References

1. 1.Li, S., Zhang, Y., Fu, K., Fang, K., Zheng, L., Lin, Y., & Wu, J. (2026). Machine learning ensemble meets clinical practice: developing a real-world risk prediction model for metabolic syndrome using super learner and scorecard approaches. Journal of Advanced Research. https://doi.org/10.1016/S2468-2667(19)30248-8