Hybrid Deep-learning Approach for Heart Disease Prediction using CNN and LSTM

TITLE	Hybrid Deep-learning Approach for Heart Disease Prediction using CNN and LSTM
ABSTRACT	Cardiovascular diseases (CVDs) are the main reason for death is due to this particular cause. worldwide, suffering from heart disease alone leads to more than 17.9 million deaths worldwide each year. Early, precise, and accessible diagnostic methods are crucial for reducing mortality rates, and to address these needs, we propose a web-based system for predicting heart disease that integrates applying both ML methods and advanced deep learning approaches to analyse structured clinical data. The system incorporates K-Nearest Neighbours, Random Forest, Logistic Regression, Long Short-Term Memory architectures, and machine support, including Convolutional Neural Networks. Experimental evaluation demonstrated that the Random Forest model achieved 88 % accuracy, 0.91 ROC-AUC, 0.87 F1-Score, while the integration of CNN and LSTM improved recall to 0.88, enhancing early detection capabilities. The proposed platform supports both real-time and batch predictions through a user-friendly interface, making it suitable for deployment in both clinical and resource- limited environments. This work demonstrates the feasibility of deploying AI-driven predictive systems for proactive cardiovascular risk assessment.
AUTHOR	Sudeep S, Soumya, Shridhar V Department of MCA, CMR Institute of Technology, Bengaluru, India
PUBLICATION DATE	2025-09-05
VOLUME	12
DOI	DOI:10.15680/IJARETY.2025.1204064
PDF	64_Hybrid Deep-learning Approach for Heart Disease Prediction using CNN and LSTM.pdf
KEYWORDS

Article

Email

[email protected]