OPTIMIZING DIABETES PREDICTION WITH MACHINE LEARNING ON AWS CLOUD INFRASTRUCTURE

Authors:

Meenakshi budarapu, A V MURALI KRISHNA

Page No: 173-178

Abstract:

Abstract Machine learning (ML) has transformed various industries, particularly healthcare. Leveraging ML techniques for predictive analysis on large datasets enables critical advancements in diagnosis and treatment planning. This study explores the application of ML algorithms for diabetes prediction using patient health records. Six ML algorithms—Artificial Neural Networks (ANN), XGBoost, AdaBoost, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Tree (DT)—were implemented on the Pima Indian Diabetes Database. Comparative analysis demonstrated the performance and effectiveness of these techniques. Additionally, a user-friendly application was developed to allow healthcare providers to input data and obtain accurate predictions. By optimizing algorithms and integrating them into a cloud-based framework, this study seeks to empower healthcare professionals with reliable diagnostic tools.

Description:

.

Volume & Issue

Volume-13,ISSUE-12

Keywords

Key Words: Machine Learning (ML),Diabetes ,Prediction, Predictive Analysis, Healthcare ,Patient Health Records,