Diabetes Prediction System Using Machine Learning

Abstract

Healthcare is one of the most significant application domains of Machine Learning, where early disease prediction can help improve patient outcomes and support clinical decision-making. This dissertation presents a Diabetes Prediction and Analysis System Using Machine Learning that predicts the likelihood of a disease based on various patient health parameters and medical records. The system utilizes a healthcare dataset containing attributes such as glucose level, blood pressure, body mass index (BMI), insulin level, age, and other relevant medical factors. The collected data is pre-processed through missing value handling, feature normalization, and data partitioning to enhance prediction performance. Multiple Machine Learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Decision Tree, and Random Forest, are employed to develop predictive models. The performance of these models is evaluated using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Comparative analysis is carried out to identify the most suitable algorithm for disease prediction. The implementation of the proposed system is carried out in MATLAB, utilizing its Machine Learning and data analysis tools for model training, testing, performance evaluation, and result visualization. Experimental results demonstrate that Machine Learning techniques can effectively predict disease occurrence with high accuracy, thereby assisting healthcare professionals in early diagnosis and treatment planning. The proposed system provides an efficient and reliable approach for disease prediction and analysis, contributing to improved healthcare management and decision support.