Automated speech analysis enables MCI diagnosis

Authors

  • Charalambos Themistocleous Department of Neurology, Johns Hopkins University, USA Author
  • Marie Eckerström Department of Psychiatry & Neurochemistry, University of Gothenburg, Sweden Author
  • Dimitrios Kokkinakis Department of Swedish, University of Gothenburg, Sweden Author

DOI:

https://doi.org/10.36505/ExLing-2020/11/0050/000465

Keywords:

acoustic analysis, machine learning, cognitive impairment, MMSE

Abstract

Mild Cognitive Impairment (MCI) is a condition characterized by cognitive decline greater than expected for an individual's age and education level. In this study, we are investigating whether acoustic properties of speech production can improve the classification of individuals with MCI from healthy controls augmenting the Mini Mental State Examination, a traditional screening tool, with automatically extracted acoustic information. We found that just one acoustic feature, can improve the AUC score (measuring a trade-off between sensitivity and specificity) from 0.77 to 0.89 in a boosting classification task. These preliminary results suggest that computerized language analysis can improve the accuracy of traditional screening tools.

 

References

Downloads

Published

01-01-2020

Data Availability Statement

Boersma, P., Weenink, D. 2018. Praat. Retrieved from http://www.praat.org Fraser, K., Lundholm Fors, K., Eckerström, M., Themistocleous, C., Kokkinakis, D. 2018. Improving the sensitivity and specificity of MCI screening with linguistic information. LREC, Miyazaki, Japan. Goodglass, H., Kaplan, E., Barresi, B. 2001. BDAE-3: Boston Diagnostic Aphasia Examination–Third Edition. Philadelphia, PA: Lippincott Williams & Wilkins. Themistocleous, C., Eckerström, M., Kokkinakis, D. 2018. Identification of Mild Cognitive Impairment From Speech in Swedish Using Deep Sequential Neural Networks. Frontiers in Neurology 9, 975. doi:10.3389/fneur.2018.00975 Themistocleous, C., Eckerström, M., Kokkinakis, D. 2020. Voice quality and speech fluency distinguish individuals with Mild Cognitive Impairment from Healthy Controls. PLoS One 15(7), e0236009. doi:10.1371/journal.pone.0236009 Themistocleous, C., Kokkinakis, D., Eckerström, M., Fraser, K., Fors, K. L. 2018. Effects of Cognitive Impairment on vowel duration. ExLing 2018, 113. Wallin, A. et al. 2016. The Gothenburg MCI study. Journal of Cerebral Blood Flow & Metabolism 36(1), 114-131. doi:10.1038/jcbfm.2015.147.

How to Cite

Automated speech analysis enables MCI diagnosis. (2020). Linguistic Proceedings Series, 11(1), 201-204. https://doi.org/10.36505/ExLing-2020/11/0050/000465

Similar Articles

1-10 of 296

You may also start an advanced similarity search for this article.