{"id":23191,"date":"2026-10-21T10:14:38","date_gmt":"2026-10-21T10:14:38","guid":{"rendered":"https:\/\/8657085.xyz\/?p=23191"},"modified":"2026-10-21T10:14:38","modified_gmt":"2026-10-21T10:14:38","slug":"could-a-smartphone-listen-for-childhood-lung-problems-ai-narrows-the-gap","status":"publish","type":"post","link":"https:\/\/8657085.xyz\/?p=23191","title":{"rendered":"Could a smartphone listen for childhood lung problems? AI narrows the gap"},"content":{"rendered":"<p> <div style=\"display: grid; grid-template-columns: 300px 160px; gap: 2px; width: 460px; background: #eee; padding: 2px;\">\r\n\r\n  <!-- \u6574\u884c\u5bbd\u5e7f\u544a -->\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876674\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 90px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876676\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u7ad6\u6392 -->\r\n  <div style=\"height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876672\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"height: 500px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876680\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u6469\u5929\u697c\uff08\u548c\u5de6\u4fa7\u5b8c\u5168\u5bf9\u9f50\uff09 -->\r\n  <div style=\"grid-row: 3\/5; height: 750px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876678\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  \r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e6\" data-zoneid=\"5876682\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n<\/div><br \/>\n<\/p>\n<div style=\"padding-right:0;padding-left:0\">\n<p class=\"wp-block-paragraph\">What if an ordinary smartphone could help screen children for respiratory problems, without parents needing access to an electronic stethoscope? Researchers at Seoul National University of Science and Technology (SeoulTech) have developed an artificial intelligence (AI) framework designed to identify abnormal lung sounds in recordings made with smartphones.<\/p>\n<p class=\"wp-block-paragraph\">The development addresses an important obstacle facing smartphone-based respiratory screening. An AI system trained using high-quality electronic-stethoscope recordings cannot necessarily be expected to work equally well when presented with sounds captured through a consumer smartphone microphone.<\/p>\n<p class=\"wp-block-paragraph\">The researchers\u2019 answer is <strong>domain-adaptive deep learning<\/strong>, in which the model is specifically trained to negotiate differences between the two recording environments.<\/p>\n<p class=\"wp-block-paragraph\">The study, <em>Smartphone-Based Detection of Abnormal Lung Sounds Using Domain-Adaptive Deep Learning<\/em>, by Seunggyu Jeong, Sungwoo Nam, Seongkwan Jung and Seong-Eun Kim, was published in the peer-reviewed <em>IEEE Journal of Biomedical and Health Informatics<\/em> on 30 July 2026.<\/p>\n<h2 id=\"h-teaching-ai-two-acoustic-languages\" class=\"wp-block-heading\"><strong>Teaching AI two acoustic languages<\/strong><\/h2>\n<p class=\"wp-block-paragraph\">The problem addressed by the researchers is known in machine learning as a <strong>domain mismatch<\/strong> or <strong>domain shift<\/strong>. Essentially, an abnormal respiratory sound recorded by an electronic stethoscope can have different characteristics when captured by a smartphone microphone.<\/p>\n<p class=\"wp-block-paragraph\">For an AI system, this difference matters. \u201cTo a neural network, the smartphone and electronic stethoscope effectively speak different languages,\u201d explains Associate Professor Seong-Eun Kim.<\/p>\n<p class=\"wp-block-paragraph\">\u201cInstead of simply pooling the data from the two devices, our approach offers reliable domain-adaption, where the model learns from reliable labelled-electronic stethoscope recordings while adapting to the smartphone domain.\u201d<\/p>\n<p class=\"wp-block-paragraph\">This creates an important distinction between the SeoulTech approach and simply increasing the quantity of training material by combining recordings from different devices. Instead, the researchers sought to teach the model how to transfer useful information learnt from one acoustic environment into another.<\/p>\n<h2 id=\"h-children-provide-paired-recordings\" class=\"wp-block-heading\"><strong>Children provide paired recordings<\/strong><\/h2>\n<p class=\"wp-block-paragraph\">To investigate whether such an approach works, the researchers collected electronic-stethoscope lung-sound recordings from 611 children aged between birth and six years.<\/p>\n<p class=\"wp-block-paragraph\">Of these, 147 also provided paired smartphone recordings. For both recording methods, lung sounds were collected from the same four anatomical locations. This gave the scientists the relatively unusual resource of corresponding smartphone and electronic-stethoscope recordings. An additional independent dataset consisted of smartphone-only recordings obtained from 48 children.<\/p>\n<p class=\"wp-block-paragraph\">The separate cohort was especially important because performance on independent data provides a more demanding test of an AI technique than assessing it solely against data closely related to that used during its development. The team\u2019s approach involves two complementary adaptation strategies. First, smartphone audio was processed using a <strong>1 kHz low-pass filter<\/strong> and downsampled from <strong>48 kHz to 4 kHz<\/strong>.<\/p>\n<p class=\"wp-block-paragraph\">\u201cThis brings the smartphone frequency profile closer to the stethoscope,\u201d Kim explains.<\/p>\n<p class=\"wp-block-paragraph\">The researchers then tackled the problem at the level of the AI model itself. They incorporated a <strong>directional MixStyle module<\/strong> that injects feature statistics associated with the smartphone domain into the stethoscope domain.<\/p>\n<p class=\"wp-block-paragraph\">In simplified terms, the process makes information derived from stethoscope recordings appear more \u201csmartphone-like\u201d to the algorithm. The scientists integrated this technique into a transformer-based neural-network architecture developed for audio classification. Consequently, the model can take advantage of labelled electronic-stethoscope information while simultaneously learning representations better suited to its intended smartphone environment.<\/p>\n<p class=\"wp-block-paragraph\"><strong>Independent test delivers encouraging results<\/strong><\/p>\n<p class=\"wp-block-paragraph\">Testing produced some striking differences between approaches. Using smartphone recordings from the primary dataset, the proposed domain-adaptive model achieved an <strong>F1 score of 0.802 and AUROC of 0.911<\/strong> for abnormal lung-sound detection. The smartphone-only model, by comparison, achieved an F1 score of 0.732. Simply pooling stethoscope and smartphone data produced an F1 score of 0.708.<\/p>\n<p class=\"wp-block-paragraph\">The findings therefore suggest that placing data from different recording technologies together does not automatically improve an AI model when the acoustic properties of those sources differ substantially. The importance of domain adaptation became still clearer when the researchers turned to the independent smartphone dataset. A stethoscope-only model performed poorly when exposed to these smartphone recordings, achieving an <strong>F1 score of just 0.034 and AUROC of 0.388<\/strong>.<\/p>\n<p class=\"wp-block-paragraph\">The domain-adaptive model, in contrast, returned an <strong>F1 score of 0.744 and AUROC of 0.862<\/strong> on this independent cohort of 48 children, outperforming the other smartphone-domain approaches evaluated in the study. The result is promising, but it does not demonstrate that a smartphone can replace examination by a healthcare professional. Nor does an encouraging result from 48 children establish how reliably a system would perform across much larger and more diverse populations.<\/p>\n<p class=\"wp-block-paragraph\">Instead, the research provides evidence that the technological barrier created by different types of recording hardware may be addressable. There is an obvious practical appeal to using a smartphone for the initial collection of respiratory sounds.<\/p>\n<p class=\"wp-block-paragraph\">Unlike an electronic stethoscope, the smartphone is already a commonplace consumer device. If sufficiently validated, the approach could therefore offer possibilities for <strong>home respiratory screening, remote consultations and community healthcare<\/strong>.<\/p>\n<p class=\"wp-block-paragraph\">\u201cOur framework provides a proof-of-concept for scalable and cost-effective pediatric respiratory screening,\u201d Kim says.<\/p>\n<p class=\"wp-block-paragraph\">\u201cIt 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.\u201d<\/p>\n<p class=\"wp-block-paragraph\">The study has implications extending beyond paediatric respiratory medicine.<\/p>\n<p class=\"wp-block-paragraph\">Medical AI systems are often developed using data obtained under relatively controlled conditions and with particular pieces of equipment. Moving those algorithms into homes and other everyday environments means confronting changes in sensors, equipment and recording conditions.<\/p>\n<\/div>\n<p><!-- \u603b\u5bb9\u5668\uff1a\u6700\u5927\u5bbd908px Grid\u7d27\u51d1\u5e03\u5c40 -->\r\n<div style=\"display: grid; grid-template-columns: 728px 160px; gap:2px; width:908px; background:#eee; padding:2px;\">\r\n\r\n  <!-- \u901a\u680f\u9876\u90e8\uff1a\u6700\u5927\u6a2a\u5e45 908x258 \u8de8\u6574\u884c -->\r\n  <div style=\"grid-column:1\/-1; height:258px; background:#ff6b6b; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114307\" data-width=\"908\" data-height=\"258\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114307});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u7b2c\u4e8c\u901a\u680f\uff1a728\u00d790 \u901a\u680f -->\r\n  <div style=\"grid-column:1\/-1; height:90px; background:#4ecdc4; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114300\" data-width=\"728\" data-height=\"90\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114300});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u4e3b\u680f\uff1a\u591a\u5e7f\u544a\u5806\u53e0 -->\r\n  <div style=\"display:grid; gap:2px;\">\r\n    <div style=\"height:60px; background:#45b7d1; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114308\" data-width=\"468\" data-height=\"60\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114308});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ffe066; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114299\" data-width=\"300\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114299});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ff9ecd; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114305\" data-width=\"250\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114305});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:139px; background:#c792ea; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114302\" data-width=\"133\" data-height=\"139\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114302});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:125px; background:#91e7ac; display:grid; place-items:center;\">\r\n\t\r\n<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114303\" data-width=\"125\" data-height=\"125\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114303});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u7ad6\u680f\uff1a160\u00d7600 \u6574\u5217\u9ad8\u5e7f\u544a -->\r\n  <div style=\"grid-row:3\/8; height:600px;  display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114301\" data-width=\"160\" data-height=\"600\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114301});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n<\/div><br \/>\n<br \/> Could a smartphone listen for childhood lung problems? AI narrows the gap<br \/>\n<br \/>#smartphone #listen #childhood #lung #problems #narrows #gap<\/p>\n","protected":false},"excerpt":{"rendered":"<p>What if an ordinary smartphone could help screen children for respiratory problems, without parents needing&#8230;<\/p>\n","protected":false},"author":1,"featured_media":23192,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[9733,3639,10260,16914,16915,3933,2755],"class_list":["post-23191","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-stories","tag-childhood","tag-gap","tag-listen","tag-lung","tag-narrows","tag-problems","tag-smartphone"],"featured_image_urls":{"full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",768,576,false],"thumbnail":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd-150x150.jpg",150,150,true],"medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd-300x225.jpg",300,225,true],"medium_large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",640,480,false],"large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",640,480,false],"1536x1536":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",768,576,false],"2048x2048":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",768,576,false],"covernews-slider-full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",768,576,false],"covernews-slider-center":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd-768x500.jpg",768,500,true],"covernews-featured":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd.jpg",768,576,false],"covernews-medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd-540x340.jpg",540,340,true],"covernews-medium-square":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/84ebd3d5beaac273858ada60da3a5afd4ecc7efd-400x250.jpg",400,250,true]},"author_info":{"display_name":"admin","author_link":"https:\/\/8657085.xyz\/?author=1"},"category_info":"<a href=\"https:\/\/8657085.xyz\/?cat=7\" rel=\"category\">Stories<\/a>","tag_info":"Stories","comment_count":"0","_links":{"self":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/23191","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=23191"}],"version-history":[{"count":0,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/23191\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/media\/23192"}],"wp:attachment":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=23191"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=23191"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=23191"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}