Using a Logistic Model to Study the Most Important Factors Which Affecting Type 1 and Type 2 Diabetes in Al-Abyar city, Libya (2025)

Abstract

Diabetes mellitus represents one of the most prevalent and critical chronic diseases, often resulting in severe health complications and increased mortality rates. This study aimed to analyze the key clinical and demographic determinants that differentiate between Type 1 and Type 2 diabetes by employing a binary logistic regression model to estimate the likelihood of developing diabetes. The study used primary data collected from a purposive sample of 250 patients of different age groups and both genders at the Diabetes and Endocrinology Clinic in Al-Abyar City for the year (2025) and the Maximum Likelihood (ML) method in parameter estimation and data processing through SPSS. The results showed that the logistic model has a high Goodness-of-Fit and that the estimated parameters are statistically significant. The results concluded that the prediction of diabetes type is mainly dependent on the association of three main determinants: gender (females) was the most significant risk factor with an odds ratio (OR) of 2.492, genetic factor (OR = 2.321), and body mass index (BMI) with a probability rate of 1.770. Overall, the interaction between biological characteristics and physical patterns constitutes the strongest predictive framework for explaining the variation in the likelihood of infection within the study sample. The model achieved a total classification accuracy of 79.5%.