{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T14:55:24Z","timestamp":1764168924080,"version":"3.46.0"},"reference-count":20,"publisher":"IOP Publishing","issue":"6","license":[{"start":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:00:00Z","timestamp":1764115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T00:00:00Z","timestamp":1764115200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2025,11,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Auscultations are commonly used to analyze lung conditions through signal processing and classification techniques. However, the efficiency of these models is often limited by factors like signal quality, sensor performance, and dataset size. Current models rely on approximations, making it difficult to pinpoint exact causes of lung conditions. To improve accuracy and interpretability, this study proposes a composite transfer learning model with explainable AI called TLMACEA. The model first converts auscultation data into 2D spectral and spatial feature vectors, which are then processed using an ensemble convolutional neural network (CNN) to identify initial lung conditions. These results are cross verified with clinical data such as lung function tests, patient demographics, smoking history, and symptoms (e.g., cough, wheezing). The data is processed through an ensemble classification layer combining random forest, support vector machine, linear regression, and Na\u00efve Bayes models for effective lung condition prediction. The model\u2019s performance was evaluated on over 100 patients and compared to existing models. Results showed that TLMACEA outperformed state-of-the-art models, with 8.5% higher accuracy, 6.2% better precision, 7.9% improved recall, and 10.4% lower delay. The model\u2019s ensemble classification achieved 99.5% accuracy, making it suitable for real-time clinical use. The explainable AI layer also demonstrated over 98% precision, ensuring the clinical utility of the recommendations generated.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae1f21","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T22:48:00Z","timestamp":1763074080000},"page":"065056","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TLMACEA: design of a transfer learning model for correlative analysis of auscultation and clinical parameters via explainable AI-based recommender"],"prefix":"10.1088","volume":"11","author":[{"given":"Divya","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bikesh Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6013-5917","authenticated-orcid":true,"given":"Ankur","family":"Jaiswal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neha","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saket","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anil","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"key":"bpexae1f21bib1","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/s40436-019-00254-5","type":"journal-article","article-title":"Machine auscultation: enabling machine diagnostics using convolutional neural networks and large-scale machine audio data","volume":"7","author":"Yang","year":"2019","journal-title":"Adv. Manuf."},{"key":"bpexae1f21bib2","doi-asserted-by":"publisher","first-page":"5388","DOI":"10.1109\/EMBC.2016.7591945","type":"conference-proceedings","article-title":"Comparison between users of a new methodology for heart sound auscultation","author":"Castro","year":"2016"},{"key":"bpexae1f21bib3","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/590845","type":"journal-article","article-title":"The prevalence and clinical correlates of an auscultatory gap in systemic sclerosis patients","volume":"1","author":"Frech","year":"2012","journal-title":"International Journal ofRheumatology"},{"key":"bpexae1f21bib4","doi-asserted-by":"publisher","first-page":"7347","DOI":"10.1038\/s41598-020-64405-6","type":"journal-article","article-title":"The diagnostic accuracy of lung auscultation in adult patients with acute pulmonary pathologies: a meta-analysis","volume":"10","author":"Arts","year":"2020","journal-title":"Sci. Rep."},{"key":"bpexae1f21bib5","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1109\/TBME.2015.2422698","type":"journal-article","article-title":"Adaptive noise suppression of pediatric lung auscultations with real applications to noisy clinical settings in developing countries","volume":"62","author":"Emmanouilidou","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib6","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1109\/JBHI.2021.3056916","type":"journal-article","article-title":"Design and comparative performance of a robust lung auscultation system for noisy clinical settings","volume":"25","author":"McLane","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexae1f21bib7","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/TBME.2006.886660","type":"journal-article","article-title":"Automated pediatric cardiac auscultation","volume":"54","author":"de Vos","year":"2007","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib8","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/JBHI.2014.2349156","type":"journal-article","article-title":"On the blind recovery of cardiac and respiratory sounds","volume":"19","author":"Shah","year":"2015","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexae1f21bib9","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/JBHI.2020.3000057","type":"journal-article","article-title":"Upper esophageal sphincter opening segmentation with convolutional recurrent neural networks in high resolution cervical auscultation","volume":"25","author":"Khalifa","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexae1f21bib10","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/JBHI.2021.3106565","type":"journal-article","article-title":"Improving non-invasive aspiration detection with auxiliary classifier wasserstein generative adversarial networks","volume":"26","author":"Shu","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexae1f21bib11","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TBME.2019.2913913","type":"journal-article","article-title":"Design and evaluation of a diaphragm for electrocardiography in electronic stethoscopes","volume":"67","author":"Martins","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib12","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1109\/10.649999","type":"journal-article","article-title":"Separation of discontinuous adventitious sounds from vesicular sounds using a wavelet-based filter","volume":"44","author":"Hadjileontiadis","year":"1997","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib13","doi-asserted-by":"publisher","first-page":"4204","DOI":"10.1109\/LRA.2022.3149576","type":"journal-article","article-title":"Automated heart and lung auscultation in robotic physical examinations","volume":"7","author":"Zhu","year":"2022","journal-title":"IEEE Robotics and Automation Letters"},{"key":"bpexae1f21bib14","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2020.3027802","type":"journal-article","article-title":"Early detection of acute chest syndrome through electronic recording and analysis of auscultatory percussion","volume":"8","author":"Allen","year":"2020","journal-title":"IEEE Journal of Translational Engineering in Health and Medicine"},{"key":"bpexae1f21bib15","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/TBME.2003.820359","type":"journal-article","article-title":"Time-frequency detection and analysis of wheezes during forced exhalation","volume":"51","author":"Homs-Corbera","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib16","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1109\/TBME.1981.324768","type":"journal-article","article-title":"Digital spectrum analysis of respiratory sound","volume":"28","author":"Chowdhury","year":"1981","journal-title":"IEEE Transactions on Biomedical Engineering, vol. BME"},{"key":"bpexae1f21bib17","doi-asserted-by":"publisher","first-page":"3203","DOI":"10.1109\/JBHI.2020.3016831","type":"journal-article","article-title":"Blind monaural source separation on heart and lung sounds based on periodic-coded deep autoencoder","volume":"24","author":"Tsai","year":"2020","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"bpexae1f21bib18","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1109\/TBME.1984.325301","type":"journal-article","article-title":"Analysis and automatic classification of breath sounds","volume":"BME-31","author":"Cohen","year":"1984","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib19","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TBME.1984.325302","type":"journal-article","article-title":"Heart-sound processing by average and variance calculation\u2013 physiologic basic and clinical implications","volume":"BME-31","author":"Beyar","year":"1984","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae1f21bib20","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1109\/TBME.2006.873548","type":"journal-article","article-title":"Detection of cough signals in continuous audio recordings using hidden Markov models","volume":"53","author":"Matos","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T14:52:17Z","timestamp":1764168737000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae1f21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":20,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,11,26]]},"published-print":{"date-parts":[[2025,11,28]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae1f21","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,11,26]]},"assertion":[{"value":"TLMACEA: design of a transfer learning model for correlative analysis of auscultation and clinical parameters via explainable AI-based recommender","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-02-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-26","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}