Authors: Deepak Tomar, Kismat Chhillar
Abstract: Diabetes mellitus has emerged as a major global health concern, necessitating early detection and effective predictive mechanisms to support timely medical intervention. Machine learning techniques have increasingly been employed in healthcare analytics to improve diagnostic accuracy and assist clinicians in decision making. Among these techniques, the Support Vector Machine (SVM) algorithm has demonstrated strong performance in classification problems involving medical datasets. This study explores the application of SVM for predicting the likelihood of diabetes using patient health indicators such as body mass index, blood glucose level, age, and family medical history. By analyzing patterns within clinical data, the model classifies individuals into diabetic and non-diabetic categories. The predictive capability of SVM allows the identification of individuals who may be at risk of developing diabetes, thereby enabling preventive healthcare measures. Empirical findings from related studies indicate that SVM-based models can achieve high predictive accuracy, making them a reliable approach for diabetes prediction and early risk assessment in medical decision support systems.
DOI: https://doi.org/10.5281/zenodo.18899892
