Machine Learning-Based Diabetes Prediction Using Support Vector Machine in Python

Diabetes mellitus is a rapidly growing global health concern that necessitates early detection for effective management. The integration of machine learning techniques into medical diagnostics offers promising solutions for improving disease prediction accuracy. This study presents the development of a Python-based Support Vector Machine (SVM) model for predicting diabetes using the widely recognized PIMA Indians Diabetes Dataset. The dataset, containing patient health metrics such as glucose level, BMI, and age, was preprocessed and standardized prior to model training.The SVM algorithm was chosen due to its robustness in handling binary classification problems and its ability to construct optimal hyperplanes for precise class separation. Using Python's scikit-learn library, the SVM model was trained, tested, and evaluated using standard performance metrics including accuracy, precision, recall, and F1-score. Results indicate that the SVM model achieved an overall prediction accuracy of approximately 80%, demonstrating its effectiveness in classifying diabetic and non-diabetic cases. The findings confirm the potential of SVM as a reliable machine learning technique for medical diagnosis tasks.This research highlights the practical implementation of SVM in Python for healthcare applications and supports its adoption as a diagnostic tool in clinical decision support systems for diabetes prediction. Keywords: Diabetes Mellitus, Machine Learning, Support Vector Machine, SVM, Python, Disease Prediction, Medical Diagnosis, PIMA Indians Diabetes Dataset, Healthcare AI, Classification Model