Artificial intelligence allows detection of heart problems using only sound

This paper explores a new way to detect heart disease by using sound. Just like a doctor listens to your heart with a stethoscope, this research uses computer technology to analyze heart sounds. The researchers used advanced computer methods, known as machine learning and deep learning, to study these sounds and find patterns that might indicate a heart problem. They tested their approach using real heart sound recordings from a big database. One of their computer models was really good at this, correctly identifying heart issues about 96% of the time. This is important because it offers a simpler, non-invasive way to check for heart disease, which could be very helpful for doctors and patients. This technique is both promising and necessary given the global prevalence of  cardiovascular issues. Such developments offer new avenues for improving medical diagnosis and patient care, demonstrating the potential impact of integrating audio signal processing and advanced computational techniques in healthcare.

Authors: Sidra Abbas (Department of Computer Science, COMSATS University Islamabad), Stephen Ojo (Department of Electrical and Computer Engineering, College of Engineering Anderson, Anderson), Abdullah Al Hejaili (Computer Science Department, Faculty of Computers and Information Technology, University of Tabuk), Gabriel Avelino Sampedro (Faculty of Information and Communication Studies, University of the Philippines Open University/Center for Computational Imaging and Visual Innovations, De La Salle University), Ahmad Almadhor (Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University), Monji Mohamed Zaidi (Department of Electrical Engineering, College of Engineering, King Khalid University) and Natalia Kryvinska (Information Systems Department, Faculty of Management, Comenius University in Bratislava)

Read the full paper: https://doi.org/10.1038/s41598-024-53778-7