Abstract

According to the World Health Organization (WHO), approximately 537 million individuals are currently living with diabetes, with projections suggesting an annual increase of 3%. Efficient techniques for determining the types of diabetes are crucial for effective treatment of this chronic condition. Artificial intelligence-based algorithms offer promising avenues for such classification tasks. In a recent study, Support Vector Machine (SVM) algorithms were employed to classify diabetes into distinct categories using various functions such as linear, polynomial, and sigmoid functions. The dataset was split into training and test sets for prediction analysis, with the SVM classifier applied to both datasets. The proposed system effectively segregates data for processing, training the model to accurately distinguish between Type 1 and Type 2 diabetes.