Ensemble Machine Learning Framework for Heart Disease Risk Prediction

View at publisher Summarise with VIRAT
Authors: S. Kanishk, M. Monisha, K. Poongodi
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Heart disease prediction is a key aspect of contemporary medical practice, allowing early detection and treatment of heart disease based on data-driven insights. Here is a study about the proposition of a complete machine learning framework that can predict heart disease risk using clinical data. This involves a thorough data preprocessing step, which consists of cleaning the data, encoding categorical variables, and normalizing numerical attributes so that they are consistent and reliable. The two ensemble algorithms, XG-Boost and Cat-Boost, are implemented and compared to assess their classification performance. Moreover, Randomized Search Cross-Validation is performed on each model to determine the best hyper-parameters through comprehensive metrics including accuracy, precision, recall, F1-score, and ROC-AUC among others to assess the model performance. The predictive model with the highest accuracy is then made available through Stream-lit, a user-friendly and interactive web platform where one can enter a patient's data and instantly get the predicted results. The deployment also presents visual explanations such as graphs of feature importance and model performance dashboards that are meant for transparency and usability. The combination of machine learning with the easy-to-use Stream-lit interface not only improves the access but also the support for real-time clinical decision-making. The proposed system is proof of the capability of intelligent prediction tools to drive healthcare improvement by means of efficient, interpretable, and easily deployable technology solutions.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Data Mining and Machine Learning Applications COVID-19 diagnosis using AI

Publication details

Journal / source
International Conference on Image Processing and Capsule Networks (ICIPCN)
Pages
385–390
Publication date
27 January 2026
Language
EN