Predicting Early Stage Disease Diagnosis Using Machine Learning Algorithms

• Published in: 2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 1177 - 1183
• Main Authors: M, Sivaraman, M, Thyagarajan, J, Sumitha
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20-09-2023
• Subjects: Classification algorithms; Data Mining; Decision Tree; Decision trees; Diabetes; Glucose; Health Care; K-Nearest Neighbor; Machine Learning; Machine learning algorithms; Prediction algorithms
• DOI: 10.1109/ICOSEC58147.2023.10276227

The glucose levels in the blood are crucial to how well the normal body functions. Food supplies the human body with energy. In the human body, blood glucose aids in this process. Diabetes develops when the body's blood glucose level rises significantly. Data mining and knowledge discovery are crucial for diagnosing and forecasting diseases in the health sector. Patient records and illness information are contained in the health industry's information. These databases are mined for data using data-mining techniques to forecast the disease. The goal is to examine the efficacy of KNN, DT and hybrid algorithms for population-wide forecasts of hyperglycemia. KNN, decision trees, and hybrid approaches are all used in this work. The hybrid techniques employ the KNN algorithm and decision tree. The results demonstrated that the Hybrid approach performs better the KNN and DT algorithms.