NUST Institutions Library Catalogue

The prediction and management of metabolic syndrome (MetS) is crucial due to its chronic
nature and global health challenge. This study aims for early and accurate MetS diagnosis
for timely prevention by managing associated risk factors. It utilizes machine learning
(ML) and deep learning (DL) techniques while considering demographic and ethnic
variability. Notably, there is a lack of MetS prediction research in the Pakistani population,
which has unique genetic and lifestyle diversity. This study addresses this gap using a
dataset of 502 individuals from five Pakistani cities (MetS prevalence = 43.4%), with 24
features from anthropometric, clinical, lifestyle, and family history data. It is the first study
evaluating fifteen classifiers (12 ML and 3 DL models) through five-fold cross-validation.
AdaBoost outperformed with 93.4% accuracy, an Area under Curve (AUC) of 0.97, and pvalue < 0.05. Feature importance analysis (Permutation and SHAP) identified fasting blood
glucose, systolic blood pressure, triglycerides, and obesity as key biomarkers for MetS.
Odds ratio analysis across gender and age groups (95% CI) showed that Body Mass Index
(BMI), blood pressure, and glucose levels were strongly associated with MetS in aging
males, while glucose and HDL were more influential in older females. This study provides
population-specific insights into MetS risk, enhancing early prediction accuracy and
enabling targeted interventions for high-risk individuals.