Singapore, Oct. 19 -- Respiratory disease in children is a major global concern. Although stethoscopes help clinicians detect abnormal lung sounds, access to auscultation may be limited by the need for in-person visits.

Smartphones could enable home-based respiratory screening, but applying AI models trained on electronic stethoscope recordings to smartphone audio remains challenging due to differences in sound capture.

A research team from the Department of Applied Artificial Intelligence (AI), Seoul National University of Science and Technology in South Korea, has developed a domain-adaptive deep learning framework specifically designed for smartphone deployment.

The researchers collected paired stethoscope-smartphone recordings from...