Seoul National University of Science and Technology Researchers Show How Smartphones Can Help Detect Lung Problems in Children

Researchers have developed a domain-adaptive deep learning framework for smartphone-based detection of abnormal lung sounds

SEOUL, South Korea, Oct. 16, 2026 /PRNewswire/ -- 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 led by Associate Professor Seong-Eun Kim, including first author Seunggyu Jeong, a Ph.D. student, from the Department of Applied Artificial Intelligence, Seoul National University of Science and Technology in South Korea, has developed a domain-adaptive deep learning framework specifically designed for smartphone deployment. "To a neural network, the smartphone and electronic stethoscope effectively speak different languages," explains Dr. Kim. "Instead of simply pooling the data from the two devices, our approach offers reliable domain-adaptation, where the model learns from reliable labelled-electronic stethoscope recordings while adapting to the smartphone domain." Their study was published in the IEEE Journal of Biomedical and Health Informatics on July 30, 2026.

The researchers collected paired stethoscope-smartphone recordings from 611 children aged 0–6 years, including 147 with paired smartphone recordings. Lung sounds were recorded at the same four anatomical sites. Such paired datasets are rare. Additionally, an independent external dataset of smartphone-only recordings from 48 children was collected for validation.

To achieve effective domain adaptation during training, the researchers applied two complementary strategies. First, the smartphone audio was preprocessed using a 1 kHz low-pass filter and down sampled from 48 kHz to 4 kHz. "This brings the smartphone frequency profile closer to the stethoscope," notes Dr. Kim. Second, the model integrates a directional MixStyle module that injects feature statistics from the smartphone domain into the stethoscope domain, making stethoscope data appear more "smartphone-like". This module was then integrated into an Audio Spectrogram Transformer (AST) backbone, an audio classification deep learning architecture.

When tested on smartphone recordings in the primary dataset, the proposed model achieved an F1 score of 0.802 and an AUROC of 0.911 for detecting abnormal lung sounds. The smartphone-only model achieved an F1 score of 0.732, while naïve pooling of stethoscope and smartphone recordings achieved 0.708. These findings show that simply combining data from different devices does not necessarily improve performance when their acoustic characteristics differ.

On the independent external smartphone cohort, the stethoscope-only model achieved an F1 score of just 0.034 and an AUROC of 0.388, highlighting the challenge of applying models trained on one recording device to another.

The model maintained performance on an independent smartphone cohort, achieving an F1 score of 0.744 and an AUROC of 0.862, outperforming other tested approaches. These findings highlight its potential for smartphone-based respiratory screening, pending further real-world validation.

"Our framework provides a proof-of-concept for scalable and cost-effective pediatric respiratory screening," remarks Dr. Kim. "It could help parents home screen children between visits while keeping clinicians in the loop. Moreover, such technology could improve remote clinic consultations and aid community healthcare workers in frontline triage in remote areas."

Signal-level alignment may enable more accessible respiratory screening and monitoring using smartphones, but further validation across larger, diverse cohorts and real-world settings is needed.

Reference

About the institute Seoul National University of Science and Technology (SEOULTECH)

Website: https://en.seoultech.ac.kr/

Contact:
Seo-Hee Yoon
82-2 - 970 – 9166
[email protected]

SOURCE Seoul National University of Science and Technology