Prevalence of Pre-Diabetes and Its Associated Risk Factors as Predictors of Type 2 Diabetes Risk among Obese Individuals in Benin City, Edo State, Nigeria

Background Prediabetes represents a critical transitional stage between normoglycaemia and type 2 diabetes mellitus, particularly among obese adults, yet it remains underdiagnosed in sub-Saharan Africa. Evidence on its prevalence and predictors in Nigeria is limited, constraining early prevention strategies. This study examined the prevalence of prediabetes and its associated risk factors among obese individuals in Benin City, Edo State, Nigeria, and developed a context-specific predictive framework. Methods A cross-sectional analytical design was employed among obese adults residing in Benin City. Data on demographic, behavioural, anthropometric, and clinical characteristics were analysed using descriptive statistics, multivariate logistic regression with average marginal effects, and diagnostic tests including variance inflation factors and the Hosmer–Lemeshow test. Model discrimination and accuracy were assessed using the area under the receiver operating characteristic curve. A Random Forest classifier was applied as a machine-learning robustness check to validate predictor importance. Results The study population was predominantly female and middle-aged. Prediabetes prevalence was substantial among obese participants. Multivariate analysis showed that increasing age, family history of diabetes, and smoking were significant predictors of prediabetes. Average marginal effects indicated meaningful increases in predicted prediabetes probability associated with family history and smoking. Diagnostic tests confirmed the absence of multicollinearity and adequate model fit, while the regression model demonstrated acceptable discrimination. The machine-learning model corroborated regression findings, identifying age and obesity-related measures as influential predictors. Conclusion Prediabetes is common among obese adults in Benin City and is driven by a combination of life-course, behavioural, and familial risk factors. Integrating regression-based inference with machine-learning validation provides a pragmatic and policy-relevant approach for early risk stratification. Targeted screening and preventive interventions focusing on high-risk obese individuals are essential to curb progression to type 2 diabetes nationally.