Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{170473,
        author = {Monish S and Hemalatha M and Devapriyan A and Viswa V},
        title = {Deep Learning Framework for Risk Prediction and Classification of Heart Sound},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1357-1364},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170473},
        abstract = {Cardiovascular diseases (CVDs), such as heart attacks and strokes, continue to be major global health concerns, often stemming from blood vessel blockages that hinder critical blood flow. These blockages are frequently caused by fatty deposits accumulating along the walls of blood vessels. Traditional approaches to detecting cardiovascular irregularities, like auscultation (listening to heart sounds with a stethoscope), may not reliably capture subtle dysfunctions. To improve diagnostic precision, we introduce a hybrid model combining Convolutional Neural Networks (CNNs) and Bidirectional Gated Recurrent Units (BIGRUs) to analyze heart sound data. CNNs are proficient at extracting spatial features, while BIGRUs excel in processing temporal sequences, making this hybrid approach well-suited for sequential heart sound evaluation. This integrated model aims to improve prediction accuracy for cardiovascular conditions by identifying patterns that may be overlooked by conventional algorithms, such as Random Forests or Decision Trees. Comparative results indicate that the hybrid model offers promising advancements in diagnostic accuracy, potentially enabling earlier identification and intervention for cardiovascular health management.},
        keywords = {Cardiovascular Disease Prediction, Heart Sound Analysis, Deep Learning, Convolutional Neural Network, Bidirectional Gated Recurrent Unit, Diagnostic Tool, Temporal Sequence Analysis.},
        month = {December},
        }