{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T14:59:10Z","timestamp":1789138750642,"version":"build-2803163510"},"reference-count":35,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Coughing is a common clinical symptom and a protective respiratory reflex closely associated with various respiratory system diseases. The acoustic characteristics of cough sounds are influenced by underlying pathological factors, with distinct acoustic signatures corresponding to different etiologies. Through rigorous analysis of these sounds, rapid identification and preliminary diagnosis of related conditions may be achieved. This approach holds great potential for broad application in mobile health and ubiquitous health platforms.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to explore the application of acoustic analysis of cough sounds in the diagnosis of respiratory diseases to enhance the diagnostic efficiency of health care professionals.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n In this study, we conducted extensive data collection, including voluntary cough audio recordings from patients diagnosed with respiratory diseases (eg, chronic obstructive pulmonary disease, lung cancer, COVID-19, and pneumonia) and from healthy participants. A total of 2610 audio samples were collected. We incorporated a channel attention mechanism (CAM) into the final convolutional block of each residual block in the ResNet18 neural network, thereby constructing the CAM-ResNet18 neural network model. The recorded cough audio samples were converted into spectrograms to form the input dataset for model training. The CAM-ResNet18 model was trained on the training set of this dataset, with iterative parameter adjustments until convergence was achieved. Finally, spectrograms from the test set were fed into the pretrained model for accurate classification of the cough-related conditions.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Experimental results on the collected audio dataset demonstrate that the proposed CAM-ResNet18 model achieves an accuracy of 83.9% and an average\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 82.52% in classifying 5 types of cough sounds. In comparison, the traditional ResNet18 model achieves an accuracy of 78.16% and an average\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 78.29%, indicating a clear performance improvement with the integration of the CAM.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The experimental results validate the effectiveness of the proposed method, highlighting its significant potential for application in clinical diagnosis.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/77295","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T19:15:07Z","timestamp":1758914107000},"page":"e77295-e77295","source":"Crossref","is-referenced-by-count":1,"title":["Cough Audio Recognition for Early Detection of Respiratory Diseases: Algorithm Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8736-2578","authenticated-orcid":false,"given":"Wensheng","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0229-3175","authenticated-orcid":false,"given":"Jiahao","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1631-551X","authenticated-orcid":false,"given":"Na","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1554-7685","authenticated-orcid":false,"given":"Wenying","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7354-3450","authenticated-orcid":false,"given":"Jimin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1037-620X","authenticated-orcid":false,"given":"Ziping","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0147-297X","authenticated-orcid":false,"given":"Shigui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100378","article-title":"AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app","volume":"20","author":"Imran","journal-title":"Inform Med Unlocked"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2019.04.013","article-title":"A novel methodology for automated differential diagnosis of mild cognitive impairment and the Alzheimer\u2019s disease using EEG signals","volume":"322","author":"Amezquita-Sanchez","journal-title":"J Neurosci Methods"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s00431-020-03709-1","article-title":"Typical RSV cough: myth or reality? A diagnostic accuracy study","volume":"180","author":"Binnekamp","journal-title":"Eur J Pediatr"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2021.736018","article-title":"Diagnostic errors are common in acute pediatric respiratory disease: a prospective, single-blinded multicenter diagnostic accuracy study in Australian emergency departments","volume":"9","author":"Porter","journal-title":"Front Pediatr"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2018.12.001","article-title":"A novel machine learning approach for early detection of hepatocellular carcinoma patients","volume":"54","author":"Ksi\u0105\u017cek","journal-title":"Cogn Syst Res"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.09.017","article-title":"Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals","volume":"100","author":"Acharya","journal-title":"Comput Biol Med"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103792","article-title":"Automated detection of COVID-19 cases using deep neural networks with X-ray images","volume":"121","author":"Ozturk","journal-title":"Comput Biol Med"},{"key":"R8","doi-asserted-by":"crossref","unstructured":"Eyben F . Real-Time Speech and Music Classification by Large Audio Feature Space Extraction. Springer; 2015. [doi: 10.1007\/978-3-319-27299-3]","DOI":"10.1007\/978-3-319-27299-3"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/KEM.474-476.349","article-title":"Combining speech enhancement and cepstral mean normalization for LPC cepstral coefficients","volume":"474","author":"Yang","journal-title":"Key Eng Mater"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Dubey RK Kumar A . Non-intrusive objective speech quality assessment using a combination of MFCC, PLP and LSF features. Presented at: 2013 International Conference on Signal Processing and Communication (ICSC); Dec 12-14, 2013; Noida, India. [doi: 10.1109\/ICSPCom.2013.6719801]","DOI":"10.1109\/ICSPCom.2013.6719801"},{"key":"R11","doi-asserted-by":"crossref","unstructured":"Sreeram ASK Ravishankar U Sripada NR Mamidgi B . Investigating the potential of MFCC features in classifying respiratory diseases. Presented at: 2020 7th International Conference on Internet of Things: Systems, Management and Security (IOTSMS); Dec 14-16, 2020; Paris, France. [doi: 10.1109\/IOTSMS52051.2020.9340166]","DOI":"10.1109\/IOTSMS52051.2020.9340166"},{"key":"R12","doi-asserted-by":"crossref","unstructured":"Chambres G Hanna P Desainte-Catherine M . Automatic detection of patient with respiratory diseases using lung sound analysis. Presented at: 2018 International Conference on Content-Based Multimedia Indexing (CBMI); Sep 4-6, 2018; La Rochelle, France. [doi: 10.1109\/CBMI.2018.8516489]","DOI":"10.1109\/CBMI.2018.8516489"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13640-017-0213-2","article-title":"Classification of lung sounds using convolutional neural networks","volume":"2017","author":"Aykanat","journal-title":"J Image Video Proc"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Yue L Xu W . Automatic classification of childhood asthma and pneumonia based on cough sound analysis. Presented at: 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE); Nov 5-7, 2021; Hangzhou, China. [doi: 10.1109\/ICAICE54393.2021.00152]","DOI":"10.1109\/ICAICE54393.2021.00152"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104572","article-title":"COVID-19 cough classification using machine learning and global smartphone recordings","volume":"135","author":"Pahar","journal-title":"Comput Biol Med"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/s42979-020-00422-6","article-title":"Robust detection of COVID-19 in cough sounds","volume":"2","author":"Mouawad","journal-title":"SN COMPUT SCI"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3205591","article-title":"Classification of cough sounds using spectrogram methods and a parallel-stream one-dimensional deep convolutional neural network","volume":"10","author":"Huang","journal-title":"IEEE Access"},{"key":"R18","doi-asserted-by":"crossref","unstructured":"Bales C Nabeel M John CN et al. Can machine learning be used to recognize and diagnose coughs? Presented at: 2020 International Conference on e-Health and Bioengineering (EHB); Oct 29-30, 2020; Iasi, Romania. [doi: 10.1109\/EHB50910.2020.9280115]","DOI":"10.1109\/EHB50910.2020.9280115"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Bansal V Pahwa G Kannan N . Cough classification for COVID-19 based on audio MFCC features using convolutional neural networks. Presented at: 2020 IEEE International Conference on Computing, Power and Communication Technologies (GUCON); Oct 2-4, 2020; Greater Noida, India. [doi: 10.1109\/GUCON48875.2020.9231094]","DOI":"10.1109\/GUCON48875.2020.9231094"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1183\/18106838.0302.164","article-title":"Chronic cough: diagnosis, treatment and psychological consequences","volume":"3","author":"Morice","journal-title":"Breathe (Sheff)"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S Sun J . Deep residual learning for image recognition. Presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Jun 27-30, 2016; Las Vegas, NV, USA. [doi: 10.1109\/CVPR.2016.90]","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","journal-title":"Commun ACM"},{"issue":"2","key":"R23","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/TBME.2018.2849502","article-title":"Automatic croup diagnosis using cough sound recognition","volume":"66","author":"Sharan","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1186\/s12931-019-1046-6","article-title":"A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children","volume":"20","author":"Porter","journal-title":"Respir Res"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Chatrzarrin H Arcelus A Goubran R Knoefel F . Feature extraction for the differentiation of dry and wet cough sounds. Presented at: 2011 IEEE International Symposium on Medical Measurements and Applications; May 30-31, 2011; Bari, Italy. [doi: 10.1109\/MeMeA.2011.5966670]","DOI":"10.1109\/MeMeA.2011.5966670"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105020","article-title":"COVID-19 cough sound symptoms classification from scalogram image representation using deep learning models","volume":"139","author":"Loey","journal-title":"Comput Biol Med"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Rocha BM Pessoa D Marques A Carvalho P Paiva RP . Personalized detection of explosive cough events in patients with pulmonary disease. Presented at: 2020 IEEE 20th Mediterranean Electrotechnical Conference ( MELECON); Jun 16-18, 2020; Palermo, Italy. [doi: 10.1109\/MELECON48756.2020.9140556]","DOI":"10.1109\/MELECON48756.2020.9140556"},{"issue":"6","key":"R28","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1016\/j.jaip.2021.02.014","article-title":"Artificial intelligence\/machine learning in respiratory medicine and potential role in asthma and COPD diagnosis","volume":"9","author":"Kaplan","journal-title":"J Allergy Clin Immunol Pract"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00937-4","article-title":"The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms","volume":"8","author":"Orlandic","journal-title":"Sci Data"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Fakhry A Jiang X Xiao J Chaudhari G Han A Khanzada A . Virufy: a multi-branch deep learning network for automated detection of COVID-19. arXiv. Preprint posted online on Mar 2, 2021. [doi: 10.21437\/Interspeech.2021-378]","DOI":"10.21437\/Interspeech.2021-378"},{"key":"R31","unstructured":"Zhang Z Wang M . Convolutional neural network with convolutional block attention module for finger vein recognition. arXiv. Preprint posted online on Feb 14, 2022. [doi: 10.48550\/arXiv.2202.06673]"},{"key":"R32","doi-asserted-by":"crossref","unstructured":"Taud H Mas J . Geomatic approaches for modeling land change scenarios. In: Multilayer Perceptron (MLP). Springer; 2018:451-455. [doi: 10.1007\/978-3-319-60801-3_27]","DOI":"10.1007\/978-3-319-60801-3_27"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.011","article-title":"Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function","volume":"309","author":"Hu","journal-title":"Neurocomputing"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2021.101091","article-title":"DeepOCT: an explainable deep learning architecture to analyze macular edema on OCT images","volume":"34","author":"Altan","journal-title":"Eng Sci Technol Int J"},{"issue":"5","key":"R35","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","journal-title":"IEEE J Biomed Health Inform"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e77295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:09:24Z","timestamp":1782842964000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e77295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.2196\/77295","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]},"article-number":"v14i1e77295"}}