Cardio Health Prognostics: A Machine Learning Model for Heart Disease Prediction

DOI

10.2991/978-94-6463-858-5_60How to use a DOI?

Keywords

Heart disease; machine learning; predictive modelling; cardiovascular risk; feature importance; data preprocessing; logistic regression; random forest; XGBoost; hyperparameter tuning; class imbalance; SMOTE; Gradio; healthcare AI; medical diagnosis

Abstract

Heart disease continues to be among the leading causes of disease and mortality globally, and thus early diagnosis and risk stratification are critical. Conventional diagnostic methods tend to rely on clinical assessment and invasive procedures, which can lead to delays in prompt medical intervention. This study presents a machine learning predictive model that classifies individuals into low-risk and high-risk categories using major clinical predictors. The data used in this research contain critical characteristics like age, gender, type of chest pain, blood pressure, cholesterol, fasting blood sugar, electrocardiographic results, maximum heart rate, and angina induced by exercise.

Missing value handling, one-hot encoding for categorical features, and class imbalance handling through Synthetic Minority Over-sampling Technique (SMOTE) are the pre-processing steps. Various machine learning algorithms such as logistic regression, random forest, and XGBoost are trained and tested. Hyperparameter optimization is done by using RandomizedSearchCV and GridSearchCV to improve the performance of models, and among them, the best accuracy rate of 99.53 percent is obtained with random forest. A feature importance analysis indicates that cholesterol, age, and maximum heart rate are all highly important in predicting risk for heart disease.

To make the model user-friendly, a Gradio-based interactive web application is created where users can input clinical parameters and get real-time risk predictions. The system also gives personalized suggestions such as diet tips, exercise regimens, medicine advice, and the best heart hospitals in India to promote preventive healthcare practices. This research emphasizes the efficiency of machine learning in forecasting cardiovascular disease risk, allowing for early diagnosis and prompt medical intervention. Future improvements involve increasing the dataset, adding deep learning models, and incorporating real-time patient monitoring to enhance predictive accuracy and clinical utility.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - P. Srujith Reddy
AU  - J. Rajendar
AU  - M. Satya Sai
AU  - I. Varun
AU  - J Malla Reddy
PY  - 2025
DA  - 2025/11/04
TI  - Cardio Health Prognostics: A Machine Learning Model for Heart Disease Prediction
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 696
EP  - 714
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_60
DO  - 10.2991/978-94-6463-858-5_60
ID  - Reddy2025
ER  -