Background: Metabolic syndrome (MetS) increases the risk of cardiovascular disease, type 2 diabetes and other chronic conditions. Early identification of individuals at high risk may enable targeted prevention strategies and reduce disease progression. Perinatal exposures, including obstetric, behavioural, and demographic factors, as well as biological ageing markers such as epigenetic ageing and telomere length, have been identified as potential predictors of later MetS risk.

Method: Using data from 664 Gen2  participants (aged 22 years) in the Raine Study, we developed and internally validated a prognostic model based on perinatal risk factors (Model 1) to predict MetS. We further evaluated the incremental predictive value of biological ageing markers. Predictors were selected using least absolute shrinkage and selection operator regression with 10-fold cross-validation. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) and calibration measures. Internal validation was performed using bootstrapping, and clinical utility was evaluated through decision curve analysis.

Result: MetS prevalence at age 22 years was 9.6%. Model 1 included maternal age, pre‑pregnancy BMI, smoking during pregnancy, and preterm birth (AUC = 0.72). Extended models, each incorporating biological ageing markers such as DunedinPACE, Hannum age acceleration, and telomere length, yielded AUCs of 0.72, 0.73, and 0.73, respectively. All models demonstrated good calibration, and bootstrap validation indicated minimal overfitting. Decision curve analysis showed that Model 1 yielded greater net benefit than treat‑all or treat-none strategies.

Conclusion: Routinely available perinatal variables provide a practical and potentially cost‑effective tool for early MetS risk stratification. The addition of biological ageing markers resulted in only marginal improvements in predictive performance. External validation is required before clinical implementation.