Heart Failure Prediction Using CNN

Heart Failure Prediction Using CNN

Author Name : Abinav S, Adhul V, Nawaz MA, Dr. J. Maria Shyla

DOI: https://doi.org/10.56025/IJARESM.2025.1304251817

ABSTRACT Heart failure is a complex and multifactorial clinical syndrome characterized by the inability of the heart to pump blood efficiently, leading to significant morbidity and mortality worldwide. Early detection and prediction of heart failure are crucial for effective management and treatment, enabling healthcare providers to initiate timely interventions and improve patient outcomes. Recent advancements in deep learning have shown promise in predicting heart failure using various data sources, including electrocardiograms (ECGs), echocardiograms, and electronic health records (EHRs). This study proposes a novel approach to heart failure prediction using Convolutional Neural Networks (CNNs) and ECG data. A large dataset of ECG signals from patients with and without heart failure was collected and preprocessed. A CNN model was designed to extract features from ECG signals and predict heart failure. The model was trained and tested on the dataset, with performance evaluated using metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC ROC) The proposed CNN model demonstrated high accuracy in predicting heart failure, with an AUC-ROC of 0.92. The model outperformed traditional machine learning approaches, including support vector machines (SVMs) and random forests, and showed promise for clinical application. The results suggest that CNNs can effectively extract features from ECG signals and predict heart failure with high accuracy.