{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:20:51Z","timestamp":1790875251201,"version":"4.1.0"},"reference-count":39,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Israeli Ministry of Science & Technology","award":["3-16500"],"award-info":[{"award-number":["3-16500"]}]},{"name":"Russian Foundation for Basic Research","award":["19-515-06001"],"award-info":[{"award-number":["19-515-06001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Methods of computer-assisted diagnostics that utilize deep learning techniques on recordings of respiratory sounds have been developed to diagnose bronchial asthma. In the course of the study an anonymous database containing audio files of respiratory sound recordings of patients suffering from different respiratory diseases and healthy volunteers has been accumulated and used to train the software and control its operation. The database consists of 1,238 records of respiratory sounds of patients and 133 records of volunteers. The age of tested persons was from 18 months to 47 years. The sound recordings were captured during calm breathing at four points: in the oral cavity, above the trachea, at the chest, the second intercostal space on the right side, and at the point on the back. The developed software provides binary classifications (diagnostics) of the type: \u201csick\/healthy\u201d and \u201casthmatic patient\/non-asthmatic patient and healthy\u201d. For small test samples of 50 (control group) to 50 records (comparison group), the diagnostic sensitivity metric of the first classifier was 88%, its specificity metric \u201386% and accuracy metric \u201387%. The metrics for the classifier \u201casthmatic patient\/non-asthmatic patient and healthy\u201d were 92%, 82%, and 87%, respectively. The last model applied to analyze 941 records in asthmatic patients indicated the correct asthma diagnosis in 93% of cases. The proposed method is distinguished by the fact that the trained model enables diagnostics of bronchial asthma (including differential diagnostics) with high accuracy irrespective of the patient gender and age, stage of the disease, as well as the point of sound recording. The proposed method can be used as an additional screening method for preclinical bronchial asthma diagnostics and serve as a basis for developing methods of computer assisted patient condition monitoring including remote monitoring and real-time estimation of treatment effectiveness.<\/jats:p>","DOI":"10.7717\/peerj-cs.1173","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T08:38:47Z","timestamp":1673339927000},"page":"e1173","source":"Crossref","is-referenced-by-count":15,"title":["Application of deep learning for bronchial asthma diagnostics using respiratory sound recordings"],"prefix":"10.7717","volume":"9","author":[{"given":"Theodore","family":"Aptekarev","sequence":"first","affiliation":[{"name":"Physics Department, Ben-Gurion University of the Negev, Be\u2019er Sheva, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir","family":"Sokolovsky","sequence":"additional","affiliation":[{"name":"Physics Department, Ben-Gurion University of the Negev, Be\u2019er Sheva, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evgeny","family":"Furman","sequence":"additional","affiliation":[{"name":"Department of Faculty and Hospital Pediatrics, Perm State Medical University named after Academician E. A. Wagner, Perm, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalia","family":"Kalinina","sequence":"additional","affiliation":[{"name":"Department of Faculty and Hospital Pediatrics, Perm State Medical University named after Academician E. A. Wagner, Perm, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Furman","sequence":"additional","affiliation":[{"name":"Physics Department, Ben-Gurion University of the Negev, Be\u2019er Sheva, Israel"},{"name":"Education Department, Tel-Hai College, Tel-Hai, Upper Galilee, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2023,1,10]]},"reference":[{"issue":"1","key":"10.7717\/peerj-cs.1173\/ref-1","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1097\/MCP.0000000000000341","article-title":"The role of imaging in the assessment of severe asthma","volume":"23","author":"Ash","year":"2017","journal-title":"Current Opinion in Pulmonary Medicine"},{"key":"10.7717\/peerj-cs.1173\/ref-2","first-page":"1076","article-title":"Separation of crackles from vesicular sounds using wavelet packet transform","volume":"2","author":"Bahoura","year":"2006","journal-title":"Acoustics, Speech and Signal Processing ICASSP"},{"key":"10.7717\/peerj-cs.1173\/ref-3","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1183\/09031936.00002108","article-title":"Definition, assessment and treatment of wheezing disorders in preschool children: an evidence-based approach. ERS Task Force Report","volume":"32","author":"Brand","year":"2008","journal-title":"European Respiratory Journal"},{"key":"10.7717\/peerj-cs.1173\/ref-4","doi-asserted-by":"crossref","first-page":"55","DOI":"10.20535\/RADAP.2018.73.55-62","article-title":"Using of the machine learning methods to identify bronchopulmonary system diseases with the use of lung sounds","volume":"73","author":"Chekhovych","year":"2018","journal-title":"Visnyk NTUU KPI Seriia \u2013Radioteknika Radioaparaturalobuduvannia"},{"key":"10.7717\/peerj-cs.1173\/ref-5","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1038\/s41586-021-03922-4","article-title":"Biologically informed deep neural network for prostate cancer discovery","volume":"348","author":"Elmarakeby","year":"2021","journal-title":"Nature"},{"issue":"3","key":"10.7717\/peerj-cs.1173\/ref-6","doi-asserted-by":"publisher","first-page":"97","DOI":"10.17816\/pmj38397-109","article-title":"Capabilities of computer-assisted assay of breath sounds in patients with COVID-19","volume":"38","author":"Furman","year":"2021","journal-title":"Perm Medical Journal"},{"issue":"1","key":"10.7717\/peerj-cs.1173\/ref-7","first-page":"53","article-title":"Respiratory sound analysis for bronchial asthma diagnostics","volume":"10","author":"Furman","year":"2020","journal-title":"IOSR Journal of Engineering"},{"issue":"5","key":"10.7717\/peerj-cs.1173\/ref-8","first-page":"77","article-title":"Comparative efficiency of computer-assisted assay of energetic characteristic of respiratory sound spectrum in three points to diagnose bronchoobstructive syndrome in children with bronchial asthma","volume":"32","author":"Furman","year":"2015","journal-title":"Perm Medical Journal"},{"issue":"1","key":"10.7717\/peerj-cs.1173\/ref-9","first-page":"83","article-title":"Computer-assisted assay of respiratory sounds in children suffering from bronchial asthma","volume":"6","author":"Furman","year":"2014","journal-title":"Clinical Medicine"},{"issue":"5","key":"10.7717\/peerj-cs.1173\/ref-10","doi-asserted-by":"publisher","first-page":"2004173","DOI":"10.1183\/13993003.04173-2020","article-title":"European Respiratory Society clinical practice guidelines for the diagnosis of asthma in children aged 5\u201316 years","volume":"58","author":"Gaillard","year":"2021","journal-title":"European Respiratory Journal"},{"key":"10.7717\/peerj-cs.1173\/ref-11","doi-asserted-by":"publisher","DOI":"10.1101\/2021.11.18.21266503","article-title":"Artificial intelligence in the respiratory sounds analysis and computer diagnostics of bronchial asthma","author":"Gelman","year":"2021","journal-title":"medRxiv"},{"key":"10.7717\/peerj-cs.1173\/ref-12","article-title":"Global initiative for asthma: global strategy for asthma management and prevention","author":"GINA","year":"2022"},{"issue":"8","key":"10.7717\/peerj-cs.1173\/ref-13","doi-asserted-by":"publisher","first-page":"e0220606","DOI":"10.1371\/journal.pone.0220606","article-title":"The accuracy of lung auscultation in the practice of physicians and medical students","volume":"14","author":"Hafke-Dys","year":"2019","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj-cs.1173\/ref-14","doi-asserted-by":"publisher","first-page":"107150","DOI":"10.1016\/j.asoc.2021.107150","article-title":"Deep transfer learning with limited data for machinery fault diagnosis","volume":"103","author":"Han","year":"2021","journal-title":"Applied Soft Computing"},{"key":"10.7717\/peerj-cs.1173\/ref-15","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"10.7717\/peerj-cs.1173\/ref-16","article-title":"Densely connected convolutional networks","author":"Huang","year":"2018"},{"key":"10.7717\/peerj-cs.1173\/ref-17","doi-asserted-by":"publisher","first-page":"17186","DOI":"10.1038\/s41598-021-96724-7","article-title":"Respiratory sound classification for crackles, wheezes, and rhonchi in the clinical field using deep learning","volume":"11","author":"Kim","year":"2021","journal-title":"Scientific Reports"},{"issue":"2","key":"10.7717\/peerj-cs.1173\/ref-18","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1164\/ajrccm.160.2.9807008","article-title":"Peak flow variability in the SAPALDIA study and its validity in screening for asthma-related conditions. The SPALDIA Team","volume":"160","author":"K\u00fcnzli","year":"1999","journal-title":"American Journal of Respiratory and Critical Care Medicine"},{"key":"10.7717\/peerj-cs.1173\/ref-19","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1109\/OJEMB.2020.3026928","article-title":"COVID-19 artificial intelligence diagnosis using only cough recordings","volume":"1","author":"Laguarta","year":"2020","journal-title":"IEEE Open Journal of Engineering in Medicine and Biology"},{"key":"10.7717\/peerj-cs.1173\/ref-20","first-page":"1","article-title":"Classification between normal and adventitious lung sounds using deep neural network","author":"Li","year":"2016"},{"key":"10.7717\/peerj-cs.1173\/ref-21","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4792298","article-title":"librosa\/librosa: 0.8.1rc2 (0.8.1rc2)","author":"McFee","year":"2021","journal-title":"Zenodo"},{"key":"10.7717\/peerj-cs.1173\/ref-22","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"10.7717\/peerj-cs.1173\/ref-23","article-title":"Rethinking CNN models for audio classification","author":"Palanisamy","year":"2020"},{"key":"10.7717\/peerj-cs.1173\/ref-24","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"10.7717\/peerj-cs.1173\/ref-25","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.7717\/peerj-cs.1173\/ref-26","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1145\/2733373.2806390","article-title":"ESC: dataset for environmental sound classification","author":"Piczak","year":"2015"},{"key":"10.7717\/peerj-cs.1173\/ref-27","first-page":"204","article-title":"Discriminability-based transfer between neural networks","author":"Pratt","year":"1992"},{"key":"10.7717\/peerj-cs.1173\/ref-28","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.rmedc.2009.01.001","article-title":"The ASAP project: a first step to an auscultation\u2019s school creation","volume":"2","author":"Reicbert","year":"2009","journal-title":"Respiratory Medicine CME"},{"key":"10.7717\/peerj-cs.1173\/ref-29","first-page":"45","article-title":"Analysis of respiratory sounds: state of the art","volume":"2","author":"Reichert","year":"2008","journal-title":"Clinical Medicine: Circulatory Respiratory and Pulmonary Medicine"},{"issue":"3","key":"10.7717\/peerj-cs.1173\/ref-30","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2009.187","article-title":"Sensitivity analysis of k-fold cross validation in prediction error estimation","volume":"32","author":"Rodriguez","year":"2010","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.1173\/ref-31","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/1471-2466-9-31","article-title":"Diagnostic accuracy of spirometry in primary care","volume":"9","author":"Schneider","year":"2009","journal-title":"BMC Pulmonary Medicine"},{"key":"10.7717\/peerj-cs.1173\/ref-32","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s11517-012-0958-9","article-title":"Detection of swallows with silent aspiration using swallowing and breath sound analysis","volume":"50","author":"Shirazi","year":"2012","journal-title":"Medical & Biological Engineering & Computing"},{"key":"10.7717\/peerj-cs.1173\/ref-33","article-title":"Learning important features through propagating activation differences","author":"Shrikumar","year":"2017"},{"issue":"77","key":"10.7717\/peerj-cs.1173\/ref-34","first-page":"597","article-title":"Definition of terms for applications of respiratory sounds","volume":"10","author":"Sovijarvi","year":"2000","journal-title":"European Respiratory Journal"},{"key":"10.7717\/peerj-cs.1173\/ref-35","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1016\/j.compbiomed.2006.09.007","article-title":"Wheeze detection based on time -frequency analysis of breath sounds","volume":"37","author":"Taplidou","year":"2007","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.1173\/ref-36","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.alit.2019.04.010","article-title":"Deep learning facilitates the diagnosis of adult asthma","volume":"68","author":"Tomita","year":"2019","journal-title":"Allergology International"},{"key":"10.7717\/peerj-cs.1173\/ref-37","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.4172\/2155-6121.S2-006","article-title":"Spirometry with FEV0.75 increases the sensitivity for the diagnosis of obstructive disorder in children of asthmatic mothers","volume":"2013","author":"Valadares","year":"2013","journal-title":"Journal of Allergy and Clinical Immunology"},{"issue":"3","key":"10.7717\/peerj-cs.1173\/ref-38","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"Fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nature Methods"},{"key":"10.7717\/peerj-cs.1173\/ref-39","doi-asserted-by":"publisher","first-page":"7399","DOI":"10.3390\/s130607399","article-title":"Soft stethoscope for detecting asthma wheeze in young children","volume":"13","author":"Yu","year":"2013","journal-title":"Sensors"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-1173.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1173.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1173.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1173.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T08:39:06Z","timestamp":1673339946000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-1173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":39,"alternative-id":["10.7717\/peerj-cs.1173"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.1173","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,10]]},"article-number":"e1173"}}