O4‐12‐02: Innovative Voice Analytics for the Assessment and Monitoring of Cognitive Decline in People with Dementia and Mild Cognitive Impairment
Alexandra König, Aharon Satt, Renaud David, Philippe H. Robert · Alzheimer s & Dementia · 2016
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 progression. 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. 165 participants (Healthy elderly subjects (HC), MCI patients and Alzheimer’s disease (AD) 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 and counting down. 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 HC, MCI and AD. The second step included training automatic classifiers for detecting MCI and AD, based on machine learning methods, and testing the detection accuracy. Based on previous data collection, the automatic voice analysis software produces a cognitive vocal score ranging from 0-1. High accuracy rates for the continuous ‘cognitive vocal score’ which was calculated for each participant within the range of 0 – 1 were obtained. The fluency and free speech tasks obtain the highest accuracy rates of classifying AD vs. MCI vs. HC. Using the data, we demonstrated classification accuracy as follows: HC vs AD = 92% accuracy; HC vs. MCI= 86% accuracy; MCI vs. AD = 86% accuracy.