AI-Enhanced Stethoscope for Real Time Cardiopulmonary Diagnostics and Telemedicine Integration
This paper presents a novel intelligent stethoscope for real-time diagnosis of heart and lung conditions and integrated, innovative telemedicine functionality. The transportable accessory has a wireless charging case that functions without interruptions. Users can use a comfortable and intuitive web version on a computer, along with the heart rate values and the detailed diagnostic report that appears immediately, highlighting the efficiency and speed of the stethoscope. These reports include the discovery and provide AI-recommended possibilities for the existing or developing disease, which is helpful in timely and accurate decision-making. The device achieved a sensitivity of 94% and an accuracy of 93%, demonstrating its high reliability and diagnostic precision. This research is curated to solve the significant drawbacks of current diagnostic systems that are not smart, portable, and incapable of interfacing with current telemedicine applications. Conventional stethoscopes leave much room for interpretation of the sounds produced by the heart and other organs, as such diagnoses largely depend on the clinician's skill, which may set a severe problem in areas with few, if any, professionals. In addition, the lack of automation in reporting and real-time analytical capability delays diagnosis and treatment. This stethoscope adds value to telemedicine services, boosts diagnostic accuracy, and eases pressure on healthcare institutions by integrating advanced diagnostics with telemedicine functions. Remotely diagnosing patients has always been more challenging and effective than it is; the device's hardware and AI layout, UI, reports, and telemedicine all illustrate this and play a key role in advancing the health sector.
Authors
- Sumeet Gupta (ORCID: https://orcid.org/0000-0002-1150-3258)
- Naheed Siddiqui
- S. S. Jadhav
- Manish Dhatrak
Institutions
- Sanjivani Super Speciality Hospitals (IN)
Publication Details
- Published
- 2025-04-17
- DOI
- https://doi.org/10.1109/incacct65424.2025.11011421
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00