{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T23:29:31Z","timestamp":1790033371545,"version":"4.0.1"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"R&D projects of Zhejiang Province of China","award":["2023C03107"],"award-info":[{"award-number":["2023C03107"]}]},{"name":"Zhejiang health information association research program","award":["No.2023XHSZ-Z04"],"award-info":[{"award-number":["No.2023XHSZ-Z04"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Since the COVID-19, cough sounds have been widely used for screening purposes. Intelligent analysis techniques have proven to be effective in detecting respiratory diseases. In 2021, there were up to 10 million TB-infected patients worldwide, with an annual growth rate of 4.5%. Most of the patients were from economically underdeveloped regions and countries. The PPD test, a common screening method in the community, has a sensitivity of as low as 77%. Although IGRA and Xpert MTB\/RIF offer high specificity and sensitivity, their cost makes them less accessible. In this study, we proposed a feature fusion model-based cough sound classification method for primary TB screening in communities. Data were collected from hospitals using smart phones, including 230 cough sounds from 70 patients with TB and 226 cough sounds from 74 healthy subjects. We employed Bi-LSTM and Bi-GRU recurrent neural networks to analyze five traditional feature sets including the Mel frequency cepstrum coefficient (MFCC), zero-crossing rate (ZCR), short-time energy, root mean square, and chroma_cens. The incorporation of features extracted from the speech spectrogram by 2D convolution training into the Bi-LSTM model enhanced the classification results. With traditional futures, the best TB patient detection result was achieved with the Bi-LSTM model, with 93.99% accuracy, 93.93% specificity, and 92.39% sensitivity. When combined with a speech spectrogram, the classification results showed 96.33% accuracy, 94.99% specificity, and 98.13% sensitivity. Our findings underscore that traditional features and deep features have good complementarity when fused using Bi LSTM modelling, which outperforms existing PPD detection methods in terms of both efficiency and accuracy.<\/jats:p>","DOI":"10.1371\/journal.pone.0302651","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:44:41Z","timestamp":1715708681000},"page":"e0302651","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Feature fusion method for pulmonary tuberculosis patient detection based on cough sound"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-8638","authenticated-orcid":true,"given":"Wenlong","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomin","family":"Lou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1074-2601","authenticated-orcid":true,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,5,14]]},"reference":[{"key":"pone.0302651.ref001","unstructured":"Global Tuberculosis Report 2022 Available online at https:\/\/www.who.int\/publications\/i\/item\/9789240061729."},{"key":"pone.0302651.ref002","article-title":"TB or not TB?","author":"G. Frost","year":"2022","journal-title":"Acoustic cough analysis for tuberculosis classification"},{"issue":"4","key":"pone.0302651.ref003","doi-asserted-by":"crossref","first-page":"045005","DOI":"10.1088\/1361-6579\/aab6d0","article-title":"Detection of tuberculosis by automatic cough sound analysis","volume":"39","author":"G.H.R. Botha","year":"2018","journal-title":"Physiol Meas"},{"key":"pone.0302651.ref004","article-title":"Drug-Resistant Tuberculosis on the Balkan Peninsula: Determination of Drug Resistance Mechanisms with Xpert MTB\/XDR and Whole-Genome Sequencing Analysis","author":"S. Truden","journal-title":"MICROBIOLOGY SPECTRUM"},{"key":"pone.0302651.ref005","doi-asserted-by":"crossref","first-page":"110","DOI":"10.11604\/pamj.2019.33.110.15319","article-title":"The effect of sputum quality and volume on the yield of bacteriologically-confirmed TB by Xpert MTB\/RIF and smear","volume":"33","author":"O. Zimba","year":"2019","journal-title":"Pan Afr Med J"},{"issue":"2","key":"pone.0302651.ref006","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics12020453","article-title":"Diagnostic Value of Interferon-Gamma Release Assays for Tuberculosis in the Immunocompromised Population.","volume":"12","author":"Y. Yang","year":"2022","journal-title":"DIAGNOSTICS"},{"issue":"2","key":"pone.0302651.ref007","doi-asserted-by":"crossref","first-page":"123","DOI":"10.4067\/s0717-73482022000300123","article-title":"Tuberculosis latente: diagn\u00f3stico y tratamiento actual X1 - Latent tuberculosis: current diagnosis and treatment.","volume":"38","author":"C. Pe\u00f1a M","year":"2022","journal-title":"Revista chilena de enfermedades respiratorias"},{"issue":"23","key":"pone.0302651.ref008","article-title":"A Comparative Study on the Mechanism of Delayed-Type Hypersensitivity Mediated by the Recombinant Mycobacterium tuberculosis Fusion Protein ESAT6-CFP10 and Purified Protein Derivative","volume":"24","author":"X.A. Guo","year":"2023","journal-title":"INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES"},{"key":"pone.0302651.ref009","article-title":"Recombinant mycobacterium tuberculosis fusion protein for diagnosis of mycobacterium tuberculosis infection: a short-term economic evaluation.","volume":"11","author":"Z. Liu","year":"2023","journal-title":"FRONTIERS IN PUBLIC HEALTH"},{"issue":"2","key":"pone.0302651.ref010","article-title":"Role of QuantiFERON-TB Gold, Interferon Gamma Inducible Protein-10 and Tuberculin Skin Test in Active Tuberculosis Diagnosis","volume":"5","author":"B.S.A. Kabeer","year":"2010","journal-title":". PLOS ONE"},{"issue":"9","key":"pone.0302651.ref011","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.3390\/diagnostics13091624","article-title":"U-Net-Based Models towards Optimal MR Brain Image Segmentation","volume":"13","author":"R. Yousef","year":"2023","journal-title":"Diagnostics"},{"key":"pone.0302651.ref012","doi-asserted-by":"crossref","first-page":"2340102","DOI":"10.1142\/S0218348X23401023","article-title":"DCNNBT: A novel deep convolution neural network-based brain tumor classification model.","author":"M.A. Haq","year":"2023","journal-title":"Fractals"},{"key":"pone.0302651.ref013","doi-asserted-by":"crossref","first-page":"e0275479","DOI":"10.1371\/journal.pone.0275479","article-title":"A classification framework for identifying bronchitis and pneumonia in children based on a small-scale cough sounds dataset","volume":"17","author":"S. Liao","year":"2022","journal-title":"PLOS ONE"},{"key":"pone.0302651.ref014","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1007\/s12652-019-01618-2","article-title":"Exhaled breath monitoring during home ventilo-therapy in COPD patients by a new distributed tele-medicine system","volume":"12","author":"A.V. Radogna","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"pone.0302651.ref015","first-page":"1","author":"D. Grant","year":"2021","journal-title":"Rapid and Scalable COVID-19 Screening using Speech, Breath, and Cough Recordings"},{"key":"pone.0302651.ref016","first-page":"1","author":"M.U. Khan","year":"2021","journal-title":"Automated System Design for Classification of Chronic Lung Viruses using Non-Linear Dynamic System Features and K-Nearest Neighbour"},{"key":"pone.0302651.ref017","doi-asserted-by":"crossref","unstructured":"Infante, C., D.B. Chamberlain, R. Kodgule, R.R. Fletcher, Classification of voluntary coughs applied to the screening of respiratory disease. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017.","DOI":"10.1109\/EMBC.2017.8037098"},{"key":"pone.0302651.ref018","doi-asserted-by":"crossref","DOI":"10.1109\/GHTC.2017.8239338","article-title":"Use of cough sounds for diagnosis and screening of pulmonary disease.","author":"C. Infante","year":"2017","journal-title":"2017 IEEE Global Humanitarian Technology Conference (GHTC)"},{"key":"pone.0302651.ref019","first-page":"331","article-title":"WAVELET ANALYSIS OF VOLUNTARY COUGH SOUND IN PATIENTS WITH RESPIRATORY DISEASES","volume":"59","author":"J. Knocikova","year":"2008","journal-title":"JOURNAL OF PHYSIOLOGY AND PHARMACOLOGY"},{"issue":"16","key":"pone.0302651.ref020","doi-asserted-by":"crossref","DOI":"10.3390\/s21165555","article-title":"Deep Neural Network-Based Respiratory Pathology Classification Using Cough Sounds","volume":"21","author":"B.T. Balamurali","year":"2021","journal-title":"SENSORS"},{"issue":"2","key":"pone.0302651.ref021","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1080\/02770903.2019.1684516","article-title":"Stratifying asthma severity in children using cough sound analytic technology","volume":"58","author":"V. Swarnkar","year":"2021","journal-title":"JOURNAL OF ASTHMA"},{"key":"pone.0302651.ref022","doi-asserted-by":"crossref","first-page":"104572","DOI":"10.1016\/j.compbiomed.2021.104572","article-title":"COVID-19 cough classification using machine learning and global smartphone recordings","volume":"135","author":"M. Pahar","year":"2021","journal-title":"Comput Biol Med"},{"key":"pone.0302651.ref023","doi-asserted-by":"crossref","first-page":"105020","DOI":"10.1016\/j.compbiomed.2021.105020","article-title":"Mirjalili, COVID-19 cough sound symptoms classification from scalogram image representation using deep learning models","volume":"139","author":"M.S. Loey","year":"2021","journal-title":"Comput Biol Med"},{"key":"pone.0302651.ref024","article-title":"A Generic Deep Learning Based Cough Analysis System From Clinically Validated Samples for Point-of-Need Covid-19 Test and Severity Levels.","author":"J. Andreu-Perez","year":"2022","journal-title":"IEEE"},{"issue":"11","key":"pone.0302651.ref025","doi-asserted-by":"crossref","first-page":"2448","DOI":"10.1007\/s10439-013-0836-0","article-title":"Cough sound analysis can rapidly diagnose childhood pneumonia","volume":"41","author":"U.R. Abeyratne","year":"2013","journal-title":"Ann Biomed Eng"},{"key":"pone.0302651.ref026","doi-asserted-by":"crossref","first-page":"105014","DOI":"10.1088\/1361-6579\/ac2fb8","article-title":"Automatic cough classification for tuberculosis screening in a real-world environment","volume":"42","author":"M. Pahar","year":"2021","journal-title":"Physiological Measurement"},{"key":"pone.0302651.ref027","first-page":"1","author":"M. Pahar","year":"2022","journal-title":"Automatic Tuberculosis and COVID-19 cough classification using deep learning"},{"key":"pone.0302651.ref028","doi-asserted-by":"crossref","unstructured":"Mulimani, M., S.G. Koolagudi,Ieee, Acoustic Event Classification Using Spectrogram Features, in PROCEEDINGS OF TENCON 2018 - 2018 IEEE REGION 10 CONFERENCE. 2018. p. 1460-1464.","DOI":"10.1109\/TENCON.2018.8650444"},{"key":"pone.0302651.ref029","doi-asserted-by":"crossref","unstructured":"Sudha, D., M. Ramakrishna,Ieee, Comparative Study of Features Fusion Techniques, in 2017 INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN ELECTRONICS AND COMMUNICATION TECHNOLOGY (ICRAECT). 2017. p. 235-239.","DOI":"10.1109\/ICRAECT.2017.39"},{"key":"pone.0302651.ref030","doi-asserted-by":"crossref","first-page":"118409","DOI":"10.1109\/ACCESS.2022.3220735","article-title":"Residual Learning for Marine Mammal Classification","volume":"10","author":"D.T. Murphy","year":"2022","journal-title":"IEEE ACCESS"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0302651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:45:18Z","timestamp":1715708718000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0302651"}},"subtitle":[],"editor":[{"given":"John","family":"Blake","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,5,14]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,5,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0302651","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,14]]}}}