The University of Southampton
University of Southampton Institutional Repository

Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach

Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach
Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach

Introduction: To self-monitor asthma symptoms, existing methods (e.g. peak flow metre, smart spirometer) require special equipment and are not always used by the patients. Voice recording has the potential to generate surrogate measures of lung function and this study aims to apply machine learning approaches to predict lung function and severity of abnormal lung function from recorded voice for asthma patients. Methods: A threshold-based mechanism was designed to separate speech and breathing from 323 recordings. Features extracted from these were combined with biological factors to predict lung function. Three predictive models were developed using Random Forest (RF), Support Vector Machine (SVM), and linear regression algorithms: (a) regression models to predict lung function, (b) multi-class classification models to predict severity of lung function abnormality, and (c) binary classification models to predict lung function abnormality. Training and test samples were separated (70%:30%, using balanced portioning), features were normalised, 10-fold cross-validation was used and model performances were evaluated on the test samples. Results: The RF-based regression model performed better with the lowest root mean square error of 10·86. To predict severity of lung function impairment, the SVM-based model performed best in multi-class classification (accuracy = 73.20%), whereas the RF-based model performed best in binary classification models for predicting abnormal lung function (accuracy = 85%). Conclusion: Our machine learning approaches can predict lung function, from recorded voice files, better than published approaches. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

FEV, asthma, breathe, human voice, machine learning, pulmonary function, speech
750226
Alam, Md. Zahangir
45dc8998-6d85-4cc6-936a-f5b162c93259
Simonetti, Albino
319fe9e6-1de8-4328-ae95-314ff8db4a3c
Brillantino, Raffaele
9e5fbea5-5402-47ab-8f08-7c3f5bdb118d
Tayler, Nick
5fa0803c-acbb-4cce-91c9-e4ea176b2693
Grainge, Chris
2aab2c22-5df3-40ec-896e-edfb6da87e69
Siribaddana, Pandula
8f4600f1-0a56-47c5-8d25-42469c541c85
Nouraei, S. A. Reza
f09047ee-ed51-495d-a257-11837e74c2b3
Batchelor, James
e53c36c7-aa7f-4fae-8113-30bfbb9b36ee
Rahman, M. Sohel
5adb0833-4ff0-45ee-bcbe-cfa2929c96ad
Mancuzo, Eliane V.
5ed42ae4-da25-4b9e-a92f-bdbb42714af3
Holloway, John W.
4bbd77e6-c095-445d-a36b-a50a72f6fe1a
Holloway, Judith A.
f22f45f3-6fc8-4a4c-bc6c-24add507037c
Rezwan, Faisal I.
203f8f38-1f5d-485b-ab11-c546b4276338
Alam, Md. Zahangir
45dc8998-6d85-4cc6-936a-f5b162c93259
Simonetti, Albino
319fe9e6-1de8-4328-ae95-314ff8db4a3c
Brillantino, Raffaele
9e5fbea5-5402-47ab-8f08-7c3f5bdb118d
Tayler, Nick
5fa0803c-acbb-4cce-91c9-e4ea176b2693
Grainge, Chris
2aab2c22-5df3-40ec-896e-edfb6da87e69
Siribaddana, Pandula
8f4600f1-0a56-47c5-8d25-42469c541c85
Nouraei, S. A. Reza
f09047ee-ed51-495d-a257-11837e74c2b3
Batchelor, James
e53c36c7-aa7f-4fae-8113-30bfbb9b36ee
Rahman, M. Sohel
5adb0833-4ff0-45ee-bcbe-cfa2929c96ad
Mancuzo, Eliane V.
5ed42ae4-da25-4b9e-a92f-bdbb42714af3
Holloway, John W.
4bbd77e6-c095-445d-a36b-a50a72f6fe1a
Holloway, Judith A.
f22f45f3-6fc8-4a4c-bc6c-24add507037c
Rezwan, Faisal I.
203f8f38-1f5d-485b-ab11-c546b4276338

Alam, Md. Zahangir, Simonetti, Albino, Brillantino, Raffaele, Tayler, Nick, Grainge, Chris, Siribaddana, Pandula, Nouraei, S. A. Reza, Batchelor, James, Rahman, M. Sohel, Mancuzo, Eliane V., Holloway, John W., Holloway, Judith A. and Rezwan, Faisal I. (2022) Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach. Frontiers in Digital Health, 4, 750226, [750226]. (doi:10.3389/fdgth.2022.750226).

Record type: Article

Abstract

Introduction: To self-monitor asthma symptoms, existing methods (e.g. peak flow metre, smart spirometer) require special equipment and are not always used by the patients. Voice recording has the potential to generate surrogate measures of lung function and this study aims to apply machine learning approaches to predict lung function and severity of abnormal lung function from recorded voice for asthma patients. Methods: A threshold-based mechanism was designed to separate speech and breathing from 323 recordings. Features extracted from these were combined with biological factors to predict lung function. Three predictive models were developed using Random Forest (RF), Support Vector Machine (SVM), and linear regression algorithms: (a) regression models to predict lung function, (b) multi-class classification models to predict severity of lung function abnormality, and (c) binary classification models to predict lung function abnormality. Training and test samples were separated (70%:30%, using balanced portioning), features were normalised, 10-fold cross-validation was used and model performances were evaluated on the test samples. Results: The RF-based regression model performed better with the lowest root mean square error of 10·86. To predict severity of lung function impairment, the SVM-based model performed best in multi-class classification (accuracy = 73.20%), whereas the RF-based model performed best in binary classification models for predicting abnormal lung function (accuracy = 85%). Conclusion: Our machine learning approaches can predict lung function, from recorded voice files, better than published approaches. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

Text
fdgth-04-750226 (1) - Version of Record
Available under License Creative Commons Attribution.
Download (792kB)

More information

Accepted/In Press date: 14 January 2022
Published date: 8 February 2022
Additional Information: Publisher Copyright: Copyright © 2022 Alam, Simonetti, Brillantino, Tayler, Grainge, Siribaddana, Nouraei, Batchelor, Rahman, Mancuzo, Holloway, Holloway and Rezwan.
Keywords: FEV, asthma, breathe, human voice, machine learning, pulmonary function, speech

Identifiers

Local EPrints ID: 455699
URI: http://eprints.soton.ac.uk/id/eprint/455699
PURE UUID: 64060f68-c9d4-4f08-9bb2-aef0dabf566d
ORCID for James Batchelor: ORCID iD orcid.org/0000-0002-5307-552X
ORCID for John W. Holloway: ORCID iD orcid.org/0000-0001-9998-0464
ORCID for Judith A. Holloway: ORCID iD orcid.org/0000-0002-2268-3071
ORCID for Faisal I. Rezwan: ORCID iD orcid.org/0000-0001-9921-222X

Catalogue record

Date deposited: 30 Mar 2022 17:03
Last modified: 28 Jul 2022 01:46

Export record

Altmetrics

Contributors

Author: Md. Zahangir Alam
Author: Albino Simonetti
Author: Raffaele Brillantino
Author: Nick Tayler
Author: Chris Grainge
Author: Pandula Siribaddana
Author: S. A. Reza Nouraei
Author: James Batchelor ORCID iD
Author: M. Sohel Rahman
Author: Eliane V. Mancuzo
Author: Faisal I. Rezwan ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×