Adapted AI improves smartphone detection of abnormal lung sounds in children

by Seoul National University of Science and Technology

edited by Swati Mestri, reviewed by Robert Egan

Swati Mestri

Scientific Editor

Meet our editorial team
Behind our editorial process

Robert Egan

Senior Editor

Meet our editorial team
Behind our editorial process Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

trusted source

proofread

The GIST Add to Preferred Sources

Respiratory disease in children is a major global concern. Clinicians traditionally rely on stethoscopes to detect abnormal lung sounds, but access to auscultation can be limited by the need for in-person visits.

Smartphones, with their built-in microphones and widespread availability, could support home-based respiratory screening. However, applying AI models trained on electronic stethoscope recordings to smartphone audio remains challenging because of a substantial domain mismatch caused by differences in how the devices capture sound.

To address this mismatch, a research team in the Department of Applied Artificial Intelligence at Seoul National University of Science and Technology in South Korea has developed a domain-adaptive deep learning framework specifically designed for smartphone deployment. The team is led by associate professor Seong-Eun Kim and includes first author Seunggyu Jeong, a doctoral student.

"To a neural network, the smartphone and electronic stethoscope effectively speak different languages," explains Kim. "Instead of simply pooling the data from the two devices, our approach offers reliable domain adaptation, where the model learns from reliable labeled electronic stethoscope recordings while adapting to the smartphone domain."

Their study is published in the IEEE Journal of Biomedical and Health Informatics.

Paired recordings guide device adaptation

The researchers first collected paired stethoscope-smartphone recordings. For the primary data set, they acquired electronic stethoscope lung sound recordings for 611 children, ages 0–6. Of these, 147 also provided paired smartphone recordings. With both devices, lung sounds were recorded at the same four anatomical sites. Such paired data sets are rare.

Additionally, the researchers collected an independent external data set consisting of smartphone-only recordings from 48 children 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 downsampled from 48 kHz to 4 kHz. "This brings the smartphone frequency profile closer to the stethoscope," notes 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.

Adapted model outperforms pooled training

When tested on smartphone recordings in the primary data set, 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 naive 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 0.034 and an AUROC of 0.388, highlighting the challenge of applying models trained on one recording device to another.

The proposed model maintained performance on the independent external smartphone cohort, achieving an F1 score of 0.744 and an AUROC of 0.862 and outperforming the other smartphone-domain approaches tested. These findings support the potential of the framework as an assistive tool for smartphone-based respiratory screening, although further real-world validation is needed before clinical deployment.

Home screening still needs broader validation

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

The study demonstrates how signal-level alignment can reduce acoustic discrepancies between electronic stethoscopes and smartphones, providing a potential pathway toward more accessible respiratory screening and monitoring. Further validation with larger, multisite cohorts, real-world home recordings and multiple smartphone models will be needed.

More information

Seunggyu Jeong et al., Smartphone-Based Detection of Abnormal Lung Sounds Using Domain-Adaptive Deep Learning, IEEE Journal of Biomedical and Health Informatics (2026). DOI: 10.1109/jbhi.2026.3718492

Clinical categories

PediatricsChildren's healthPulmonary medicineCommon illnesses & Prevention Provided by Seoul National University of Science and Technology Who's behind this story?

Swati Mestri

Swati Mestri holds a bachelor's degree in Electronics Engineering and has worked as a content editor since 2019. She has experience editing research documents across technology, health care, and materials science, and has a particular interest in technology and space. Full profile →

Robert Egan

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: Adapted AI improves smartphone detection of abnormal lung sounds in children (2026, October 16) retrieved 16 October 2026 from https://medicalxpress.com/news/2026-10-ai-smartphone-abnormal-lung-children.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.