Identification of adventitious lung sounds in children with respiratory illnesses in Bangladesh using artificial intelligence and digital auscultation

Integrated management of childhood illness (IMCI) guidelines have high sensitivity but low specificity for pneumonia diagnosis. Artificial intelligence (AI)-enabled digital stethoscopes capable of analysing lung sounds may improve IMCI diagnostic performance. We evaluated the performance of an AI algorithm trained to identify normal and adventitious lung sounds in children. Non-physician health workers recorded lung sounds from four chest positions using a digital stethoscope in under-five-year-old children with suspected pneumonia at community clinics in Bangladesh. A trained paediatrician listening panel classified chest position recordings as normal, abnormal (crackles and/or wheeze), or uninterpretable. The AI algorithm similarly classified chest position recordings except for the uninterpretable category. AI algorithm and listening panel comparisons were made at the child-level, and included chest positions considered interpretable, uninterpretable, and high- and low-confidence by the panel. Of 990 enrolled children, 867 (87.6%) had at least 3 interpretable chest position recordings by the panel and were analysed. Compared to the panel, the AI algorithm’s sensitivity and specificity for detecting abnormal sounds were 61.8% and 60.7% among all children, and 63.5% and 66.8% in IMCI pneumonia cases. Overall, the AI algorithm achieved moderate classification performance. Classification performance will benefit from further AI algorithm training to categorize recordings as uninterpretable.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-10-16
DOI
https://doi.org/10.1038/s41598-026-76222-4
Primary Topic
Phonocardiography and Auscultation Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Identification of adventitious lung sounds in children with respiratory illnesses in Bangladesh using artificial intelligence and digital auscultation

Ismat Jahan, Eric D. McCollum, Ahad Mahmud Khan, Leah Githinji et al.
Scientific Reports
Phonocardiography and Auscultation Techniques
article

Identification of adventitious lung sounds in children with respiratory illnesses in Bangladesh using artificial intelligence and digital auscultation

Ismat Jahan, Eric D. McCollum, Ahad Mahmud Khan, Leah Githinji, J. N. Maki, Mohammad Shahidullah, Nabidul Haque Chowdhury, Salahuddin Ahmed, Steve Cunningham, Abdullah Hel Baqui, Ian Mitra McLane, Harish Nair, Dipak Kumar Mitra, Md. Ashraful Islam, Mohammad Wahiduzzaman, Muhammad Khaled Hasan, Md Shafiqul Islam, Md Ziaur Rahman Chowdhury, Rezwana Tabassum, Nighat Sultana
article en

Abstract

Integrated management of childhood illness (IMCI) guidelines have high sensitivity but low specificity for pneumonia diagnosis. Artificial intelligence (AI)-enabled digital stethoscopes capable of analysing lung sounds may improve IMCI diagnostic performance. We evaluated the performance of an AI algorithm trained to identify normal and adventitious lung sounds in children. Non-physician health workers recorded lung sounds from four chest positions using a digital stethoscope in under-five-year-old children with suspected pneumonia at community clinics in Bangladesh. A trained paediatrician listening panel classified chest position recordings as normal, abnormal (crackles and/or wheeze), or uninterpretable. The AI algorithm similarly classified chest position recordings except for the uninterpretable category. AI algorithm and listening panel comparisons were made at the child-level, and included chest positions considered interpretable, uninterpretable, and high- and low-confidence by the panel. Of 990 enrolled children, 867 (87.6%) had at least 3 interpretable chest position recordings by the panel and were analysed. Compared to the panel, the AI algorithm’s sensitivity and specificity for detecting abnormal sounds were 61.8% and 60.7% among all children, and 63.5% and 66.8% in IMCI pneumonia cases. Overall, the AI algorithm achieved moderate classification performance. Classification performance will benefit from further AI algorithm training to categorize recordings as uninterpretable.

Scientific Reports
Johns Hopkins University (US), North South University (BD), Bangladesh Medical University (BD), Sylhet MAG Osmani Medical College (BD), Bangladesh Shishu (Children) Hospital & Institute (BD), University Teaching Hospital (ZM), Centre for Inflammation Research (GB), University of Edinburgh (GB), Nelson Mandela University (ZA)
Government of the United Kingdom, National Institute for Health and Care Research, Ministry of Health and Family Welfare
Good health and well-being
Openalex Percentile: Top 13%
Phonocardiography and Auscultation Techniques
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.