Skip to Main content Skip to Navigation
Master Thesis

Analyse automatisée de la voix et biomarqueurs vocaux : une aide au diagnostic différentiel entre dépression et troubles cognitifs légers chez le sujet âgé ?

Abstract : Depression is a very frequent pathology among elderly people. Some depressive symptoms are common in neurocognitive disorders which can make it difficult to detect and diagnose them. Indeed, there is a high comorbidity of cognitive disorders and late-life depression. There are only a few diagnostic tools to help with differential diagnosis. Vocal analysis and the extraction of vocal biomarkers could be a non-invasive new method to support this process. In this study, we included patients aged over 60 diagnosed with depression without a neurodegenerative disease or others psychiatric disorders. They were asked to perform two short cognitive vocal tasks: a verbal semantic fluency and a picture description which were recorded. Then, in a second step, vocal and prosodic features were extracted from the audio files using machine learning methods. In a final step, we compared these features to those from a cohort of patients with a diagnosis of MCI diagnosis without any mood disorder. Automatic analysis of vocal cognitive tasks such as semantic verbal fluency and the picture description could be fast solution for supporting early characterization of patients. Speech analysis shows promising results and prosodic features should be further explored.
To conclude, automatic speech analyses could be an additional objective assessment tool for differentiating depression from mild cognitive impairment.
Document type :
Master Thesis
Complete list of metadata

https://dumas.ccsd.cnrs.fr/dumas-02996367
Contributor : Bibliothèque Universitaire de Médecine Nice <>
Submitted on : Monday, November 9, 2020 - 3:54:59 PM
Last modification on : Wednesday, March 31, 2021 - 3:14:24 AM

File

2020NICEM122.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : dumas-02996367, version 1

Citation

Céline Labbe. Analyse automatisée de la voix et biomarqueurs vocaux : une aide au diagnostic différentiel entre dépression et troubles cognitifs légers chez le sujet âgé ?. Médecine humaine et pathologie. 2020. ⟨dumas-02996367⟩

Share

Metrics

Record views

34

Files downloads

22