International Journal of Science, Engineering and TechnologyMachine Learning-Based Prediction of Diabetes Using Medical Data Analysis and Classification Algorithms for Early Detection
Authors- Radhakrishnan C, Abishek B, Joandsouza A, Karnesh P
Abstract- -Diabetes mellitus is a harmful disease characterized by abnormal blood glucose levels resulting from insulin resistance. If not diagnosed early, it can lead to complications in organs such as the kidneys, nerves, and eyes. With the advent of technological advancements, people are moving toward personalized healthcare. Machine learning (ML), a rapidly evolving field in predictive analysis, is increasingly applied in healthcare to identify diseases and symptoms at early stages. This work aims to develop a machine learning model for the early prediction of diabetes using classification algorithms, considering significant features related to diabetes. The proposed model provides results comparable to clinical outcomes, assisting in personalized patient diagnoses. Four machine learning algorithms—Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF)—are utilized for early diabetes prediction. The experimental analysis uses the Pima Indian Diabetes Database (PIDD) from the UCI Machine Learning Repository. The performance of these algorithms is evaluated using statistical measures such as sensitivity (recall), precision, specificity, F-score, and accuracy. Accuracy measures the correct and incorrect classification of instances. The experimental results demonstrate that the Random Forest (RF) algorithm achieves the highest accuracy of 87.66%, outperforming other algorithms.
