Development of an Artificial Intelligence-Based Web Application for Disease Risk Analysis Using Medical Record Data

Abstract

The rapid digital transformation of healthcare systems has generated extensive volumes of electronic medical record (EMR) data, creating significant opportunities for advanced computational analysis. Artificial Intelligence (AI), particularly machine learning (ML), has emerged as a transformative approach for extracting predictive insights from healthcare datasets to improve clinical decision-making and preventive medicine. This study presents the design, development, and evaluation of an AI-based web application for disease risk analysis utilizing patient medical records. The proposed system integrates web technologies with machine learning algorithms to analyze patient demographics, medical history, laboratory findings, and lifestyle indicators to predict disease susceptibility. A structured Software Development Life Cycle (SDLC) framework was adopted, encompassing system planning, data preprocessing, algorithm training, application deployment, and performance evaluation. Multiple classification models, including Logistic Regression, Decision Tree, and Random Forest, were implemented and compared. Experimental results indicate that the Random Forest model achieved the highest predictive accuracy, demonstrating strong potential for real-time disease risk stratification.