Research Article
Diabetes Prediction System Using Machine Learning
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358040, author={Sridevi Sakhamuri and Muthayala Yashwanth and Yadlapalli Badhri Narayana and Padala Jyothika Vidya}, title={Diabetes Prediction System Using Machine Learning}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={diabetes prediction machine learning artificial neural networks support vector machine medical diagnosis fuzzy logic health-informatics uci dataset}, doi={10.4108/eai.28-4-2025.2358040} }- Sridevi Sakhamuri
Muthayala Yashwanth
Yadlapalli Badhri Narayana
Padala Jyothika Vidya
Year: 2025
Diabetes Prediction System Using Machine Learning
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358040
Abstract
In the medical field, it is important to predict conditions early to help patients. Diabetes is one of the most dangerous diseases worldwide. In modern lifestyles, sugar and fat are common in our diets, which has increased the risk of diabetes. To predict the disease, it is extremely important to understand its symptoms. Currently, machine learning algorithms are very useful for disease detection. This paper presents a model using a hybrid machine learning approach for diabetes prediction. The framework combines two models: Support Vector Machine (SVM) and Artificial Neural Network (ANN). These models analyze the dataset to determine whether a diabetes diagnosis is positive or negative. The dataset used in this research is divided into training data and testing data in a 70:30 ratio. The outputs of these models are used as input for a fuzzy logic model, which finally decides whether the diagnosis is positive or negative. The fused models are stored in a cloud system for future use. Based on a patient’s real-time medical records, the fused model predicts whether the patient is diabetic or not. The proposed hybrid ML model achieved an accuracy of 94.87%, which is higher than previously published methods.
