{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T06:19:26Z","timestamp":1787552366115,"version":"build-2736575974"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004728","name":"VIT University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004728","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The classification of respiratory sounds remains a challenging task in clinical research, limited by severe dataset imbalance and strict privacy regulations. Traditional machine learning methods are centralized and jeopardize data privacy and have difficulty in identifying minority classes, which makes them unsuitable for real-world clinical use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this paper, a novel federated learning framework for multi-class respiratory disease classification is proposed based on the fusion of a Hybrid Support Vector Machine-K-Nearest Neighbor (SVMKNN) classifier with Adaptive Federated Aggregation (AFA), Synthetic Minority Oversampling Technique (SMOTE) balancing, and a Gaussian differential privacy (DP) mechanism. The suggested framework runs using five non-independently and identically distributed (non-IID) client nodes partitioned using Dirichlet distribution (\u03b1\u2009=\u20091.0) and able to perform privacy-preserving collaborative training without sharing raw data. We extract a rich multi-modal acoustic feature representation from respiratory recordings using Mel-Frequency Cepstral Coefficients (MFCCs), first and second order delta-MFCCs, Mel spectrograms, chroma features, spectral contrast, and a set of seven scalar acoustic descriptors. The resulting high-dimensional feature vector is compressed using Principal Component Analysis (PCA) to retain 95% cumulative variance. The hybrid classifier combines the discriminative boundary learning of SVM with the local density estimation of KNN through a weighted probability ensemble (\u03b1\u2009=\u20090.6), resulting in better generalization in federated, class-imbalanced settings. A major methodological innovation is the restriction of the differential privacy noise to the aggregation phase, so that all reported metrics are based on clean, noise-free model outputs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>The suggested framework obtains an accuracy of 97.55, a weighted F1-score of 97.64, Matthews Correlation Coefficient (MCC) of 90.89, and Cohen's Kappa of 90.77.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ablation studies confirm that federated hybrid learning with AFA and SMOTE outperforms standalone SVM, standalone KNN, and centralized hybrid baselines for all evaluation metrics, proving the clinical viability of the proposed framework for distributed hospital networks and telemedicine platforms.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1902226","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T05:30:35Z","timestamp":1787549435000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive federated learning with differential privacy for multi-class respiratory disease recognition from lung sound recordings"],"prefix":"10.3389","volume":"8","author":[{"given":"Syed Riyazul","family":"Haq","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuruva","family":"Lakshmanna","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"B1","year":""},{"key":"B2","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/S2213-2600(20)30157-0","article-title":"Chronic respiratory diseases: a global view","volume":"8","author":"Labaki","year":"2020","journal-title":"Lancet Respir Med"},{"key":"B3","first-page":"597","article-title":"Definition of terms for applications of respiratory sounds","volume":"10","author":"Sovijarvi","year":"2000","journal-title":"Eur Respir Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"251","DOI":"10.4046\/trd.2023.0065","article-title":"Evolution of the stethoscope: advances with the adoption of machine learning and development of wearable devices","volume":"86","author":"Kim","year":"2023","journal-title":"Tuberc Respir Dis"},{"key":"B5","author":"Perna","year":""},{"key":"B6","doi-asserted-by":"publisher","first-page":"13132","DOI":"10.3390\/s150613132","article-title":"Using k-nearest neighbor classification to diagnose abnormal lung sounds","volume":"15","author":"Chen","year":"2015","journal-title":"Sensors"},{"key":"B7","doi-asserted-by":"publisher","first-page":"82871","DOI":"10.1007\/s11042-024-18703-0","article-title":"A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds","volume":"83","author":"Alghamdi","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"B8","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1186\/1471-2105-15-223","article-title":"A comparative study of the SVM and K-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals","volume":"15","author":"Palaniappan","year":"2014","journal-title":"BMC Bioinf"},{"key":"B9","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B10","author":"McMahan","year":""},{"key":"B11","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/msp.2020.2975749","article-title":"Federated learning: challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process Mag"},{"key":"B12","author":"Li","year":""},{"key":"B13","author":"Kone\u010dn\u00fd","year":""},{"key":"B14","author":"Jayaram","year":""},{"key":"B15","author":"Zhao","year":""},{"key":"B16","doi-asserted-by":"publisher","first-page":"17","DOI":"10.29012\/jpc.v7i3.405","article-title":"Calibrating noise to sensitivity in private data analysis","volume":"7","author":"Dwork","year":"2017","journal-title":"J Priv Confidentiality"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.1038\/s41598-022-05539-7","article-title":"Federated learning and differential privacy for medical image analysis","volume":"12","author":"Adnan","year":"2022","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e369","DOI":"10.7717\/peerj-cs.369","article-title":"Deep learning based respiratory sound analysis for detection of chronic obstructive pulmonary disease","volume":"7","author":"Srivastava","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s40779-023-00479-3","article-title":"Deep learning-based lung sound analysis for intelligent stethoscope","volume":"10","author":"Huang","year":"2023","journal-title":"Mil Med Res"},{"key":"B20","doi-asserted-by":"publisher","first-page":"035001","DOI":"10.1088\/1361-6579\/ab03ea","article-title":"An open access database for the evaluation of respiratory sound classification algorithms","volume":"40","author":"Rocha","year":"2019","journal-title":"Physiol Meas"},{"key":"B21","author":"Gairola","year":""},{"key":"B22","author":"Ma","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"7374","DOI":"10.1109\/JIOT.2023.3329061","article-title":"Federated learning for medical applications: a taxonomy, current trends, challenges, and future research directions","volume":"11","author":"Rauniyar","year":"2023","journal-title":"IEEE Internet Things J"},{"key":"B24","doi-asserted-by":"publisher","first-page":"16937","DOI":"10.48550\/arXiv.2003.14053","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B25","author":"Yin","year":""},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found Trends Mach Learn"},{"key":"B27","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1162\/99608f92.cfc5dd25","article-title":"Deep learning with Gaussian differential privacy","volume":"2020","author":"Bu","year":"2020","journal-title":"Harv Data Sci Rev"},{"key":"B28","author":"Anil","year":""},{"key":"B29","doi-asserted-by":"publisher","first-page":"17455","DOI":"10.48550\/arXiv.1905.03871","article-title":"Differentially private learning with adaptive clipping","volume":"34","author":"Andrew","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans Inf Forensic Secur"},{"key":"B31","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/JSTSP.2022.3161786","article-title":"Loss-privacy tradeoff in federated edge learning","volume":"16","author":"Liu","year":"2022","journal-title":"IEEE J Sel Top Signal Process"},{"key":"B32","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/rssb.12454","article-title":"Gaussian differential privacy","volume":"84","author":"Dong","year":"2022","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bbe.2020.11.003","article-title":"Automatic identification of respiratory diseases from stethoscopic lung sound signals using ensemble classifiers","volume":"41","author":"Fraiwan","year":"2021","journal-title":"Biocybern Biomed Eng"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.3906\/elk-2004-68","article-title":"Chronic obstructive pulmonary disease severity analysis using deep learning on multi-channel lung sounds","volume":"28","author":"Altan","year":"2020","journal-title":"Turk J Electr Eng Comput Sci"},{"key":"B35","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.bspc.2018.05.014","article-title":"Deep learning with 3D-second order difference plot on respiratory sounds","volume":"45","author":"Altan","year":"2018","journal-title":"Biomed Signal Process Control"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.1109\/JBHI.2019.2931395","article-title":"Deep learning on computerized analysis of chronic obstructive pulmonary disease","volume":"24","author":"Altan","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.3390\/s22031232","article-title":"Automated lung sound classification using a hybrid CNN-LSTM network and focal loss function","volume":"22","author":"Petmezas","year":"2022","journal-title":"Sensors"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2872","DOI":"10.1109\/TBME.2022.3156293","article-title":"Lung sound classification using co-tuning and stochastic normalization","volume":"69","author":"Nguyen","year":"2022","journal-title":"IEEE Trans Biomed Eng"},{"key":"B39","author":"Hsieh","year":""},{"key":"B40","author":"Li","year":""},{"key":"B41","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B42","author":"Wang","year":""},{"key":"B43","author":"Li","year":""},{"key":"B44","author":"Abadi","year":""},{"key":"B45","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found Trends Theor Comput Sci"},{"key":"B46","author":"Zhao","year":""}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1902226\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T05:30:37Z","timestamp":1787549437000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1902226\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":46,"alternative-id":["10.3389\/fdgth.2026.1902226"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1902226","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"article-number":"1902226"}}