Automatic diagnosis of multiple cardiac diseases from PCG signals using convolutional neural network
Related Experiment Video
Updated: Dec 9, 2025
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
Published on: February 21, 2025
Neeraj Baghel1, Malay Kishore Dutta1, Radim Burget2
1Centre for Advanced Studies, Dr. A.P.J. Abdul Kalam Technical University, India.
Insights
This study introduces an AI-powered machine learning tool for diagnosing multiple cardiac diseases using heart sound analysis. The convolutional neural network model achieved 98.60% accuracy, offering a robust solution for remote healthcare.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Medicine
- Cardiology
Background:
- Cardiovascular diseases require early diagnosis, which is challenging in remote areas due to a shortage of medical professionals.
- Artificial intelligence (AI) offers potential solutions for automated cardiac disease diagnosis.
Purpose of the Study:
- To develop an automated machine learning classification method for diagnosing multiple cardiac diseases from phonocardiogram (heart sound) signals.
- To address the need for accessible cardiac diagnostics in underserved regions.
Main Methods:
- A convolutional neural network (CNN) model was employed for its accuracy and robustness in analyzing heart sounds.
- Data augmentation techniques were utilized to enhance model performance in noisy environments and enable multi-classification.
Main Results:
- The CNN model demonstrated high diagnostic accuracy, achieving up to 98.60% on the test set.
- Validation was performed using n-fold cross-validation on both original and augmented heart sound datasets.
Conclusions:
- The developed AI model is portable to various computing devices, enabling its use as a standalone diagnostic tool.
- The non-invasive, efficient, and robust method is suitable for real-time applications in primary healthcare settings, especially in remote areas.
Background And Objectives:
Cardiovascular diseases are critical diseases and need to be diagnosed as early as possible. There is a lack of medical professionals in remote areas to diagnose these diseases. Artificial intelligence-based automatic diagnostic tools can help to diagnose cardiac diseases. This work presents an automatic classification method using machine learning to diagnose multiple cardiac diseases from phonocardiogram signals.
Methods:
The proposed system involves a convolutional neural network (CNN) model because of its high accuracy and robustness to automatically diagnose the cardiac disorders from the heart sounds. To improve the accuracy in a noisy environment and make the method robust, the proposed method has used data augmentation techniques for training and multi-classification of multiple cardiac diseases.
Results:
The model has been validated both heart sound data and augmented data using n-fold cross-validation. Results of all fold have been shown reported in this work. The model has achieved accuracy on the test set up to 98.60% to diagnose multiple cardiac diseases.
Conclusions:
The proposed model can be ported to any computing devices like computers, single board computing processors, android handheld devices etc. To make a stand-alone diagnostic tool that may be of help in remote primary health care centres. The proposed method is non-invasive, efficient, robust, and has low time complexity making it suitable for real-time applications.
