Paper Key : IRJ************226
Author: Rajini V
Date Published: 17 Nov 2024
Abstract
Heart disease remains a leading cause of mortality globally, emphasizing the need for predictive tools to support early diagnosis and intervention. This study employs a data science approach to predict heart disease using machine learning techniques, particularly a Random Forest classifier. The dataset undergoes preprocessing, including encoding of categorical features and scaling of numerical data, to enhance model performance. The model is evaluated based on accuracy, classification metrics, and feature importance. Additionally, an interactive user input mechanism is developed to allow real-time predictions based on user-provided health parameters. The results demonstrate the model's effectiveness in identifying potential cases of heart disease, highlighting key features influencing predictions. This work underscores the role of data-driven solutions in advancing healthcare and provides a framework for scalable, user-friendly diagnostic tools.
DOI Requested