{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T17:21:22Z","timestamp":1792862482074,"version":"4.5.0"},"reference-count":72,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"\n Background<\/jats:title>\n Pediatric respiratory diseases, including asthma and pneumonia, are major causes of morbidity and mortality in children. Auscultation of lung sounds is a key diagnostic tool but is prone to subjective variability. The integration of artificial intelligence (AI) and machine learning (ML) with electronic stethoscopes offers a promising approach for automated and objective lung sound.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This systematic review and meta-analysis assess the performance of ML models in pediatric lung sound analysis. The study evaluates the methodologies, model performance, and database characteristics while identifying limitations and future directions for clinical implementation.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A systematic search was conducted in Medline via PubMed, Embase, Web of Science, OVID, and IEEE Xplore for studies published between January 1, 1990, and December 16, 2024. Inclusion criteria are as follows: studies developing ML models for pediatric lung sound classification with a defined database, physician-labeled reference standard, and reported performance metrics. Exclusion criteria are as follows: studies focusing on adults, cardiac auscultation, validation of existing models, or lacking performance metrics. Risk of bias was assessed using a modified Quality Assessment of Diagnostic Accuracy Studies (version 2) framework. Data were extracted on study design, dataset, ML methods, feature extraction, and classification tasks. Bivariate meta-analysis was performed for binary classification tasks, including wheezing and abnormal lung sound detection.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n A total of 41 studies met the inclusion criteria. The most common classification task was binary detection of abnormal lung sounds, particularly wheezing. Pooled sensitivity and specificity for wheeze detection were 0.902 (95% CI 0.726-0.970) and 0.955 (95% CI 0.762-0.993), respectively. For abnormal lung sound detection, pooled sensitivity was 0.907 (95% CI 0.816-0.956) and specificity 0.877 (95% CI 0.813-0.921). The most frequently used feature extraction methods were Mel-spectrogram, Mel-frequency cepstral coefficients, and short-time Fourier transform. Convolutional neural networks were the predominant ML model, often combined with recurrent neural networks or residual network architectures. However, high heterogeneity in dataset size, annotation methods, and evaluation criteria were observed. Most studies relied on small, single-center datasets, limiting generalizability.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n ML models show high accuracy in pediatric lung sound analysis, but face limitations due to dataset heterogeneity, lack of standard guidelines, and limited external validation. Future research should focus on standardized protocols and the development of large-scale, multicenter datasets to improve model robustness and clinical implementation.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/66491","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T16:00:26Z","timestamp":1744992026000},"page":"e66491","source":"Crossref","is-referenced-by-count":19,"title":["Artificial Intelligence Models for Pediatric Lung Sound Analysis: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0522-7736","authenticated-orcid":false,"given":"Ji Soo","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4058-9457","authenticated-orcid":false,"given":"Sa-Yoon","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4534-7342","authenticated-orcid":false,"given":"Jae Won","family":"Moon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4586-5062","authenticated-orcid":false,"given":"Kwangsoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7817-8728","authenticated-orcid":false,"given":"Dong In","family":"Suh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)31593-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(12)61901-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1136\/bmjresp-2017-000250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/apa.14686"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00408-014-9608-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-96724-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106500"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01907-2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.19163"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2005.02.022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00544-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10101155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WESCAN.1995.493973"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1006\/cbmr.1999.1522"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2012.6346630"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"KhanSIJawarkarNPAhmedVCell phone based remote early detection of respiratory disorders for rural children using modified stethoscope2012International Conference on Communication Systems and Network Technologies2012 May 11-13Rajkot, Gujarat, India","DOI":"10.1109\/CSNT.2012.199"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.07.033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.05.002"},{"key":"ref20","first-page":"176","volume":"10","author":"Milicevic, M","year":"2016","journal-title":"Int J Biol Biomed Eng"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"KhanSIAhmedVJawarkarNPApplication of signal processing techniques for preliminary detection of adventitious lung sounds in paediatric population using electronic stethoscope2017International Conference on Big Data Analytics and Computational Intelligence (ICBDAC)2017 March 23-25Chirala, Andhra Pradesh, India","DOI":"10.1109\/ICBDACI.2017.8070859"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2017.2717280"},{"key":"ref23","first-page":"2S","volume":"147","author":"Mohamed-Rida, B","year":"2018","journal-title":"Swiss Med Wkly"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"GoudaAShehabySDiaaNAbougabalMClassification techniques for diagnosing respiratory sounds in infants and children2019IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)2019 January 07-09Las Vegas, NV, USA","DOI":"10.1109\/CCWC.2019.8666608"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00431-019-03363-2"},{"key":"ref26","doi-asserted-by":"crossref","unstructured":"LiuLLiWJiangCBreath sounds recognition and classification for respiration system diseases2019ICC 2019 - 2019 IEEE International Conference on Communications (ICC)2019 May 20-24Shanghai, China","DOI":"10.1109\/ICC.2019.8761292"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"LiuRCaiSZhangKHuNDetection of adventitious respiratory sounds based on convolutional neural network2019International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)2019 November 21-24Shanghai, China","DOI":"10.1109\/ICIIBMS46890.2019.8991459"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2147\/MDER.S221029"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102266"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3111507"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"LiuLLiWJiangCTime-varying respiratory feature recognition and classification for respiration health and disease screening in children2021IEEE International Conference on Systems, Man, and Cybernetics (SMC)2021 October 17-20Melbourne, Australia","DOI":"10.1109\/SMC52423.2021.9659096"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1080\/03091902.2021.1992520"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.17691\/stm2022.14.5.05"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-25953-1"},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"MaWDengXYangYFangWAn effective lung sound classification system for respiratory disease diagnosis using DenseNet CNN model with sound pre-processing engine2022IEEE Biomedical Circuits and Systems Conference (BioCAS)2022 October 13-15Taipei, Taiwan","DOI":"10.1109\/BioCAS54905.2022.9948568"},{"key":"ref36","doi-asserted-by":"crossref","unstructured":"NguyenTNArjouneYSchroederJCPillaiDTeachSPatelSMachine learning for automated wheeze detection in children2022IEEE International Conference on Big Data (Big Data)2022 December 17-20Osaka, Japan","DOI":"10.1109\/BigData55660.2022.10021111"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2022.3204910"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"LiJWangXWangXQiaoSZhouYImproving the resnet-based respiratory sound classification systems with focal loss2022IEEE Biomedical Circuits and Systems Conference (BioCAS)2022 October 13-15Taipei, Taiwan","DOI":"10.1109\/BioCAS54905.2022.9948543"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"ZhangLZhuYTuSXuLA feature polymerized based two-level ensemble model for respiratory sound classification2022IEEE Biomedical Circuits and Systems Conference (BioCAS)2022 October 13-15Taipei, Taiwan","DOI":"10.1109\/BioCAS54905.2022.9948561"},{"key":"ref40","doi-asserted-by":"crossref","unstructured":"BabuNKumariJMathewJSatijaUMondalAMulticlass categorisation of respiratory sound signals using neural network2022IEEE Biomedical Circuits and Systems Conference (BioCAS)2022 October 13Taipei, Taiwan","DOI":"10.1109\/BioCAS54905.2022.9948675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00838-3"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"HuJLeowCTaoSGohWGaoYSupervised contrastive pretrained resnet with mixup to enhance respiratory sound classification on imbalanced and limited dataset2023IEEE Biomedical Circuits and Systems Conference (BioCAS)2023 October 19Toronto, ON, Canada","DOI":"10.1109\/BioCAS58349.2023.10389029"},{"key":"ref43","doi-asserted-by":"crossref","unstructured":"HuangDWangLLuHWangWA contrastive embedding-based domain adaptation method for lung sound recognition in children community-acquired pneumonia2023ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)2023 June 04-10Rhodes Island, Greece","DOI":"10.1109\/ICASSP49357.2023.10096794"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2023.3239372"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"NgoDPhamLPhanHTranMJarchiDA deep learning architecture with spatio-temporal focusing for detecting respiratory anomalies2023IEEE Biomedical Circuits and Systems Conference (BioCAS)2023 October 19-21Toronto, ON, Canada","DOI":"10.1109\/BioCAS58349.2023.10388598"},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"NgoDPhamLPhanHTranMJarchiDKolozali\u015eAn inception-residual-based architecture with multi-objective loss for detecting respiratory anomalies2023IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)2023 September 27-29Poitiers, France","DOI":"10.1109\/MMSP59012.2023.10337717"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3299341"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-27399-5"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"PessoaDPetmezasGPapageorgiouVRochaBStefanopoulosLKilintzisVPediatric respiratory sound classification using a dual input deep learning architecture2024IEEE Biomedical Circuits and Systems Conference (BioCAS)2023 October 19-21Toronto, ON, Canada","DOI":"10.1109\/BioCAS58349.2023.10388733"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106170"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"ChowdhurySDoulahABMSURasheduzzamanMRafaTSPediatric pneumonia diagnosis: integration of a self-assembled digital stethoscope with raspberry Pi and 1D CNN model2024International Conference on Advances in Computing, Communication, Electrical, and Smart Systems (iCACCESS)2024 March 08-09Dhaka, Bangladesh","DOI":"10.1109\/iCACCESS61735.2024.10499564"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/OJEMB.2024.3402139"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2024.3428637"},{"key":"ref54","doi-asserted-by":"crossref","unstructured":"YehCChiuSDengXFangWA novel AI-Inspired method and system implementation for detecting and classifying pediatric respiratory sound events2024IEEE Biomedical Circuits and Systems Conference (BioCAS)2024 October 24Xi'an, China","DOI":"10.1109\/BioCAS61083.2024.10798164"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ab03ea"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaa1690"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012799"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-047709"},{"key":"ref59","author":"Boashash, B","year":"2015","journal-title":"Time-frequency signal analysis and processing: a comprehensive reference"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09672-4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3361943"},{"key":"ref62","doi-asserted-by":"crossref","unstructured":"HeKZhangXRenSSunJDeep residual learning for image recognition2016IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016 June 27Las Vegas, NV, USA770778","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","unstructured":"GramaLTunsLRusuCOn the Optimization of SVM kernel parameters for improving audio classification accuracy201714th International Conference on Engineering of Modern Electric Systems (EMES)2017 June 01Oradea, Romania"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3991\/ijoe.v20i10.49585"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1186\/s40779-023-00479-3"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1186\/s12890-022-01896-1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2196\/53662"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01517-0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01772-9"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-021-00131-7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-022-08215-8"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e66491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:59:30Z","timestamp":1785851970000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e66491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":72,"URL":"https:\/\/doi.org\/10.2196\/66491","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.66491","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,18]]}}}