Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier. (2017-2018 à 2020-2021)

Assessing Alzheimer's disease (AD) is an expensive and laborious process that isx000D
unsustainable given our rapidly aging population, especially if one accounts for indirect costsx000D
such as lost time in travel, wait times, and hours spent in assessment, which is a process sox000D
labourious that it is often repeated only every few years. Moreover, the high variability ofx000D
symptoms in AD cannot be ascertained accurately from a single assessment, whichx000D
minimizes the effectiveness of current practice. Rapid, repeatable, and remote assessment isx000D
essential.x000D
Many individuals with AD have diminished language abilities. Linguistic measures, like thex000D
ratio of pronouns to nouns, relate strongly to cognitive decline. By measuring such featuresx000D
and using advanced machine learning software, we have developed computational methodsx000D
that are over 85% accurate in identifying Alzheimer's disease from short speech samples. Asx000D
we continue to improve this technology, we will make it available over the public phonex000D
network accessible by a 1-800 number. This system will automatically receive calls from (andx000D
make calls to) outpatients, and completely automate speech-based tests including questionanswering,x000D
narratives, and random item generation. This will be encapsulated in an interfacex000D
that healthcare workers can use to assign and monitor assessments and exercises.x000D
Currently, to extract language measures, speech must be transcribed by professionals, whichx000D
is impossible on large scales. Unfortunately, no automatic speech recognition (ASR) systemx000D
exists for people with AD. We will therefore provide the first complete ASR system for peoplex000D
with AD.x000D
Our objectives are: 1) to improve the accuracy of ASR for people with AD; 2) to refine andx000D
validate our software in remote monitoring/assessment; 3) to embed our software into a userfriendlyx000D
phone-based interface.