Detection of tuberculosis by automatic cough sound analysis - PubMed

Affiliations

Affiliation

• 1 Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa.

• PMID: 29543189
• DOI: 10.1088/1361-6579/aab6d0

Item in Clipboard

G H R Botha  et al. Physiol Meas . 2018 .

Affiliation

• 1 Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa.

• PMID: 29543189
• DOI: 10.1088/1361-6579/aab6d0

Item in Clipboard

Abstract

Objective: Globally, tuberculosis (TB) remains one of the most deadly diseases. Although several effective diagnosis methods exist, in lower income countries clinics may not be in a position to afford expensive equipment and employ the trained experts needed to interpret results. In these situations, symptoms including cough are commonly used to identify patients for testing. However, self-reported cough has suboptimal sensitivity and specificity, which may be improved by digital detection.

Approach: This study investigates a simple and easily applied method for TB screening based on the automatic analysis of coughing sounds. A database of cough audio recordings was collected and used to develop statistical classifiers.

Main results: These classifiers use short-term spectral information to automatically distinguish between the coughs of TB positive patients and healthy controls with an accuracy of 78% and an AUC of 0.95. When a set of five clinical measurements is available in addition to the audio, this accuracy improves to 82%. By choosing an appropriate decision threshold, the system can achieve a sensitivity of 95% at a specificity of approximately 72%. The experiments suggest that the classifiers are using some spectral information that is not perceivable by the human auditory system, and that certain frequencies are more useful for classification than others.

Significance: We conclude that automatic classification of coughing sounds may represent a viable low-cost and low-complexity screening method for TB.

PubMed Disclaimer

Similar articles

• Automatic cough classification for tuberculosis screening in a real-world environment.

  Pahar M, Klopper M, Reeve B, Warren R, Theron G, Niesler T. Pahar M, et al. Physiol Meas. 2021 Nov 26;42(10):10.1088/1361-6579/ac2fb8. doi: 10.1088/1361-6579/ac2fb8. Physiol Meas. 2021. PMID: 34649231 Free PMC article.

• Automatic Recognition, Segmentation, and Sex Assignment of Nocturnal Asthmatic Coughs and Cough Epochs in Smartphone Audio Recordings: Observational Field Study.

  Barata F, Tinschert P, Rassouli F, Steurer-Stey C, Fleisch E, Puhan MA, Brutsche M, Kotz D, Kowatsch T. Barata F, et al. J Med Internet Res. 2020 Jul 14;22(7):e18082. doi: 10.2196/18082. J Med Internet Res. 2020. PMID: 32459641 Free PMC article.

• An ensemble learning approach to digital corona virus preliminary screening from cough sounds.

  Mohammed EA, Keyhani M, Sanati-Nezhad A, Hejazi SH, Far BH. Mohammed EA, et al. Sci Rep. 2021 Jul 28;11(1):15404. doi: 10.1038/s41598-021-95042-2. Sci Rep. 2021. PMID: 34321592 Free PMC article.

• Lateral flow urine lipoarabinomannan assay for detecting active tuberculosis in HIV-positive adults.

  Shah M, Hanrahan C, Wang ZY, Dendukuri N, Lawn SD, Denkinger CM, Steingart KR. Shah M, et al. Cochrane Database Syst Rev. 2016 May 10;2016(5):CD011420. doi: 10.1002/14651858.CD011420.pub2. Cochrane Database Syst Rev. 2016. PMID: 27163343 Free PMC article. Review.

• Automatic adventitious respiratory sound analysis: A systematic review.

  Pramono RXA, Bowyer S, Rodriguez-Villegas E. Pramono RXA, et al. PLoS One. 2017 May 26;12(5):e0177926. doi: 10.1371/journal.pone.0177926. eCollection 2017. PLoS One. 2017. PMID: 28552969 Free PMC article. Review.

Cited by

• TBscreen: A passive cough classifier for tuberculosis screening with a controlled dataset.

  Sharma M, Nduba V, Njagi LN, Murithi W, Mwongera Z, Hawn TR, Patel SN, Horne DJ. Sharma M, et al. Sci Adv. 2024 Jan 5;10(1):eadi0282. doi: 10.1126/sciadv.adi0282. Epub 2024 Jan 3. Sci Adv. 2024. PMID: 38170773 Free PMC article.

• Advancing tuberculosis management: the role of predictive, preventive, and personalized medicine.

  Dohál M, Porvazník I, Solovič I, Mokrý J. Dohál M, et al. Front Microbiol. 2023 Oct 4;14:1225438. doi: 10.3389/fmicb.2023.1225438. eCollection 2023. Front Microbiol. 2023. PMID: 37860132 Free PMC article. Review.

• HEAR4Health: a blueprint for making computer audition a staple of modern healthcare.

  Triantafyllopoulos A, Kathan A, Baird A, Christ L, Gebhard A, Gerczuk M, Karas V, Hübner T, Jing X, Liu S, Mallol-Ragolta A, Milling M, Ottl S, Semertzidou A, Rajamani ST, Yan T, Yang Z, Dineley J, Amiriparian S, Bartl-Pokorny KD, Batliner A, Pokorny FB, Schuller BW. Triantafyllopoulos A, et al. Front Digit Health. 2023 Sep 12;5:1196079. doi: 10.3389/fdgth.2023.1196079. eCollection 2023. Front Digit Health. 2023. PMID: 37767523 Free PMC article. Review.

• Diagnosis of COVID-19 by sound-based analysis of vocal recordings.

  Carreiro-Martins P, Paixão P, Caires I, Rodrigues A, Matias P, Gamboa H, Carreiro A, Soares F, Gomez P, Sousa J, Neuparth N. Carreiro-Martins P, et al. Pulmonology. 2023 Nov-Dec;29(6):455-456. doi: 10.1016/j.pulmoe.2023.03.003. Epub 2023 Mar 21. Pulmonology. 2023. PMID: 37030999 Free PMC article. No abstract available.

• Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB.

  Yellapu GD, Rudraraju G, Sripada NR, Mamidgi B, Jalukuru C, Firmal P, Yechuri V, Varanasi S, Peddireddi VS, Bhimarasetty DM, Kanisetti S, Joshi N, Mohapatra P, Pamarthi K. Yellapu GD, et al. Sci Rep. 2023 Mar 23;13(1):4740. doi: 10.1038/s41598-023-31772-9. Sci Rep. 2023. PMID: 36959347 Free PMC article.