HEART ATTACK RISK PREDICTION SYSTEM USING CNN-LSTM

Abstract: Heart Attack is one of the leading causes of mortality worldwide and poses a significant challenge to modern healthcare systems. Early detection and accurate prediction of heart disease can help reduce complications, improve treatment outcomes, and save lives. With the rapid growth of medical data and advancements in artificial intelligence, machine learning and deep learning techniques have become effective tools for disease prediction. This paper presents a hybrid CNN-LSTM based Heart Attack Risk Prediction System that utilizes Convolutional Neural Networks (CNN) and a hybrid CNN-LSTM model for predicting the presence of heart disease. The dataset is pre-processed using data cleaning, normalization, scaling, and feature selection techniques to improve data quality and model performance. The proposed system is developed with a user-friendly interface that enables efficient data input and prediction analysis. Experimental results show that the hybrid CNN-LSTM model outperforms individual models by effectively learning feature relationships and dependencies among clinical attributes. The CNN model achieved an accuracy of 93.12%, whereas the CNN-LSTM model achieved a superior accuracy of 98.47%. The results demonstrate the effectiveness of the proposed approach in providing accurate and reliable heart disease prediction. The developed system can assist healthcare professionals in early diagnosis and decision-making, thereby contributing to improved patient care and preventive healthcare.

Keywords: Heart Disease Prediction, Deep Learning, CNN-LSTM, Machine Learning, Healthcare Analytics.