Using Machine Learning and Deep Learning for Enhanced Prediction and Early Detection of Heart Disease Risk

R. Kamali, K. Hemalatha, A. Vaishnavi Dali, P. Naresh Kumar, A. Gomathi, N. Aishwarya Rani

2025

Abstract

Heart disease is still some the primary causes of mortality worldwide. Proper detection and accurate risk prediction are critical to effective prevention and therapy. Typical risk evaluation for heart disease models frequently uses simple statistical methodologies or regression analysis, which might not be able to grasp the intricate and non-linear interactions between many cardiovascular risk variables. As the difficulty of healthcare data develops, established methods are becoming unable to provide reliable forecasts. However, ML and DL techniques have demonstrated considerable promise in dealing with complex data and discovering detailed patterns that human specialists may ignore. These techniques are mostly helpful for predicting heart disease because age, heart rate, and levels of cholesterol, and lifestyle decisions all interact in complex, nonlinear ways. This study investigates how sophisticated ML and DL methods are decision trees, random forests, neural networks, and cutting-edge algorithms similar CNNs and LSTM networks, might increase prediction accuracy. The suggested method predicts the likelihood to acquire heart disease using a change of modern ML and DL approaches. Below, we briefly detail each strategy and how they are used to the prediction job. Decision trees are a simple but efficient method for machine learning that divides data into subsets according to feature values, making decision routes simple to see and comprehend. To increase accuracy and decrease overfitting, random forests, an ensemble technique, construct several integrating the predictions of decision trees. This approach is effective for predicting cardiac disease since it can handle both continuous and categorical data.

Paper Citation

in Harvard Style

Kamali R., Hemalatha K., Dali A., Kumar P., Gomathi A. and Rani N. (2025). Using Machine Learning and Deep Learning for Enhanced Prediction and Early Detection of Heart Disease Risk. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 396-401. DOI: 10.5220/0013913900004919

in Bibtex Style

@conference{icrdicct`2525,
author={R. Kamali and K. Hemalatha and A. Dali and P. Kumar and A. Gomathi and N. Rani},
title={Using Machine Learning and Deep Learning for Enhanced Prediction and Early Detection of Heart Disease Risk},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={396-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013913900004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Using Machine Learning and Deep Learning for Enhanced Prediction and Early Detection of Heart Disease Risk
SN - 978-989-758-777-1
AU - Kamali R.
AU - Hemalatha K.
AU - Dali A.
AU - Kumar P.
AU - Gomathi A.
AU - Rani N.
PY - 2025
SP - 396
EP - 401
DO - 10.5220/0013913900004919
PB - SciTePress