Citation

Salehuddin Haqe, Nurul Azwaani and Ramasamy, R Kanesaraj and Thanjappan, Sivasutha and Md Jamal, Shamsuriani and Amri Hamzah, Faizal and Rajendran, Venushini (2026) A Raspberry Pi-based digital stethoscope: Advancing real-time heart and lung sound diagnostics with IoT and machine learning integration. Sound & Vibration, 60 (4). ISSN 1541-0161

Text 1707-Article Text-21068-1-10-20260724.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Digital transformation is reshaping auscultation by moving the stethoscope from a purely acoustic instrument to an intelligent, data-driven diagnostic platform. This review critically examines Raspberry Pi 3-based digital stethoscope technologies for heart and lung sound monitoring, with an emphasis on system architecture, sensor integration, signal acquisition, real-time processing, storage, playback, and connectivity. The paper synthesizes current designs and implementation strategies, highlighting how low-cost embedded platforms can improve the repeatability, accessibility, and objectivity of cardiopulmonary assessment compared with conventional acoustic stethoscopes. Particular attention is given to technical performance factors, including filtering, signal-to-noise ratio, latency, audio distortion, noise suppression, and time-frequency analysis, which are essential for detecting clinically significant acoustic features such as heart murmurs, crackles, and wheezes. The review also identifies key limitations affecting clinical translation, including power consumption, device portability, casing size, environmental noise, hardware constraints, and the need for robust validation in real-world settings. Future directions include optimized embedded processing, wireless and IoT-enabled tele-auscultation, cloud-assisted data management, and machine learning models for automated classification and decision support. Overall, Raspberry Pi 3-based digital stethoscopes represent a promising pathway toward affordable, scalable, and clinically meaningful cardiopulmonary monitoring, particularly for point-of-care, remote, and resource-limited healthcare environments. By integrating acoustic sensing, edge computing, and intelligent analytics, these systems can strengthen diagnostic workflows and support the next generation of connected digital healthcare.

Item Type:	Article
Uncontrolled Keywords:	digital stethoscope, Raspberry Pi 3, heart sound monitoring, lung sound recording, real-time signal processing, medical diagnostics, IoT in healthcare, acoustic signal detection
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	03 Sep 2026 07:06
Last Modified:	03 Sep 2026 07:06
URII:	http://shdl.mmu.edu.my/id/eprint/16635

Downloads

Edit (login required)