Tab Application Banner
  • Users Online: 1909
  • Home
  • Print this page
  • Email this page
Home About us Editorial board Ahead of print Current issue Search Archives Submit article Instructions Subscribe Contacts Login 


 
 Table of Contents  
LETTER TO EDITOR
Year : 2021  |  Volume : 16  |  Issue : 3  |  Page : 371-372

Toward voice detection for screening rheumatology patients


Department of Gerontology, Faculty of Social Welfare Health Science, University of Haifa, Israel

Date of Submission31-Jan-2021
Date of Acceptance07-Jul-2021
Date of Web Publication21-Sep-2021

Correspondence Address:
Mr. Or Aharonov
Department of Gerontology, The University of Haifa, Abba Khoushy Ave 199, Haifa
Israel
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/injr.injr_27_21

Rights and Permissions

How to cite this article:
Aharonov O. Toward voice detection for screening rheumatology patients. Indian J Rheumatol 2021;16:371-2

How to cite this URL:
Aharonov O. Toward voice detection for screening rheumatology patients. Indian J Rheumatol [serial online] 2021 [cited 2021 Dec 6];16:371-2. Available from: https://www.indianjrheumatol.com/text.asp?2021/16/3/371/324768



Dear Editor,

It is not uncommon for troubling times to herald bright prospects for the near future. Among the domains expected to be significantly impacted by the coronavirus disease (COVID-19) pandemic is the health-care system, struggling with the challenging duty of safeguarding health-care resources against infection risk. As a result, interest in the use of new technologies aiming at alleviating the overburdened health-care system has increased significantly, with some already being implemented and benefiting the public health-care systems and its workforce. In this letter, we would like to highlight the benefits that voice-analysis technologies can hold for screening of rheumatology patients.

With recent developments in automated assessment tools, frontline health-care workers can mediate patient engagement with a preliminary automated review, allowing them to identify clinically significant observations flagged by the system. Such reviews are not only helpful screening methods before patient evaluation, they can be used as a primary evaluation method helping to detect a possible onset of a medical condition. This can be particularly helpful for the screening of rheumatology patients: since a considerable proportion of rheumatic diseases afflict the elderly, who may have mobility and dexterity limitations coupled with limited access to health-care options due to logistical issues, voice detection systems may offer some key early insights.[1]

As digital technology is increasingly employed to collect sound data, the exploration of audio-based machine learning technologies is on the rise. Recent attempts have been made to use voice analysis for cognitive assessment and to identify neurodegenerative diseases, highlighting the usefulness of speech analysis as a preclinical predicator of Alzheimer's disease (AD).[2] By using machine learning methods, researchers were able to identify voice recordings of patients with early stage of AD from voice recordings of healthy adults, showing promising results in screening patients in early stages of AD.[3] Voice analysis can also be used to detect motor neurodegenerative diseases such as Parkinson's; for instance, MTI's Parkinson's Voice Initiative develops diagnostic tools based on analysis of telephone calls. Voice analysis is also being applied to mental disorders, measuring and identifying them. Notably, in a recent undertaking, an artificial intelligence transfer-learning model was used to analyze cough recordings and use voice analysis for discriminating COVID-19 patients successfully, achieving a high accuracy of discrimination.[4] A similar endeavor using various respiratory sounds for COVID-19 detection is also showing promising initial results.[5]

Voice analysis has a broad range of applications and great potential. Compared to biomarkers obtained from specimens, voice analysis is more cost-effective because it does not require special devices or reagents and can be monitored repeatedly through simple, noninvasive methods. Therefore, it can also be used for household monitoring, which may enable early detection of disease, and for follow-up care.

An accurate analysis of sound data and speech characteristics may be useful to gauging mood and articulation pain, identifying and assessing interstitial lung disease, and predicting patients' likelihood compliance. However, variations in voice due to hoarseness, sicca symptoms, and mood excursions resulting from a labile affect may possibly confound analysis. Thus, the utility of voice-analysis systems to assess rheumatology patients remotely merits further exploration for the betterment of telecare during the pandemic and most inevitably to be in further use in health care. I hope that expanding the scope of voice analysis for other diseases, in particular rheumatological diseases, will show its results.

Acknowledgment

The author thanks Connecting Researchers, Latika Gupta and Vikas Agarwal from the Department of Clinical Immunology and Rheumatology at Sanjay Gandhi Postgraduate Institute of Medical Sciences in Lucknow, for their help with this work.

Financial support and sponsorship

Nil.

Conflicts of interest

There are no conflicts of interest.



 
  References Top

1.
Anthes E. Alexa, do I have COVID-19? Nature 2020;586:22-5.  Back to cited text no. 1
    
2.
Meilán JJ, Martínez-Sánchez F, Ivanova O. Editorial: Speech production in persons with dementia. Curr Alzheimer Res 2018;15:102-3.  Back to cited text no. 2
    
3.
König A, Satt A, Sorin A, Hoory R, Derreumaux A, David R, et al. Use of speech analyses within a mobile application for the assessment of cognitive impairment in elderly people. Curr Alzheimer Res 2018;15:120-9.  Back to cited text no. 3
    
4.
Laguarta J, Hueto F, Subirana B. COVID-19 Artificial Intelligence Diagnosis using only Cough Recordings. IEEE Open Journal of Engineering in Medicine and Biology, 2020;1:275-81, doi: 10.1109/OJEMB.2020.3026928.  Back to cited text no. 4
    
5.
Brown C, Jagmohan C, Grammenos A, Han J, Hasthanasombat A, Spathis D, et al. Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '20). Association for Computing Machinery, New York, NY, USA; 2020. p. 3474-84. [doi: 10.1145/3394486.3412865].  Back to cited text no. 5
    




 

Top
 
 
  Search
 
Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
Access Statistics
Email Alert *
Add to My List *
* Registration required (free)

 
  In this article
References

 Article Access Statistics
    Viewed640    
    Printed12    
    Emailed0    
    PDF Downloaded29    
    Comments [Add]    

Recommend this journal


[TAG2]
[TAG3]
[TAG4]