Background: Various types of dementia and Mild Cognitive Impairment (MCI) are manifested
as irregularities in human speech and language, which have proven to be strong predictors for the
disease presence and progress ion. Therefore, automatic speech analytics provided by a mobile application
may be a useful tool in providing additional indicators for assessment and detection of early stage
dementia and MCI.
Method: 165 participants (subjects with subjective cognitive impairment (SCI), MCI patients, Alzheimer's
disease (AD) and mixed dementia (MD) patients) were recorded with a mobile application
while performing several short vocal cognitive tasks during a regular consultation. These tasks included
verbal fluency, picture description, counting down and a free speech task. The voice recordings were
processed in two steps: in the first step, vocal markers were extracted using speech signal processing
techniques; in the second, the vocal markers were tested to assess their ‘power' to distinguish between
SCI, MCI, AD and MD. The second step included training automatic classifiers for detecting MCI and
AD, based on machine learning methods, and testing the detection accuracy.
Results: The fluency and free speech tasks obtain the highest accuracy rates of classifying AD vs. MD
vs. MCI vs. SCI. Using the data, we demonstrated classification accuracy as follows: SCI vs. AD = 92%
accuracy; SCI vs. MD = 92% accuracy; SCI vs. MCI = 86% accuracy and MCI vs. AD = 86%.
Conclusions: Our results indicate the potential value of vocal analytics and the use of a mobile application
for accurate automatic differentiation between SCI, MCI and AD. This tool can provide the clinician
with meaningful information for assessment and monitoring of people with MCI and AD based on
a non-invasive, simple and low-cost method.