Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Collaborative Health Research Projects (NSERC partnered)

University of Toronto

$220,133.00

Automatic remote screening of speech features associated with Alzheimer's disease

FY 2016-17

Summary
Assessing Alzheimer's disease (AD) is an expensive and laborious process that is unsustainable given our rapidly aging population, especially if one accounts for indirect costs such as lost time in travel, wait times, and hours spent in assessment, which is a process so labourious that it is often repeated only every few years. Moreover, the high variability of symptoms in AD cannot be ascertained accurately from a single assessment, which minimizes the effectiveness of current practice. Rapid, repeatable, and remote assessment is essential. Many individuals with AD have diminished language abilities. Linguistic measures, like the ratio of pronouns to nouns, relate strongly to cognitive decline. By measuring such features and using advanced machine learning software, we have developed computational methods that are over 85% accurate in identifying Alzheimer's disease from short speech samples. As we continue to improve this technology, we will make it available over the public phone network accessible by a 1-800 number. This system will automatically receive calls from (and make calls to) outpatients, and completely automate speech-based tests including question-answering, narratives, and random item generation. This will be encapsulated in an interface that healthcare workers can use to assign and monitor assessments and exercises. Currently, to extract language measures, speech must be transcribed by professionals, which is impossible on large scales. Unfortunately, no automatic speech recognition (ASR) system exists for people with AD. We will therefore provide the first complete ASR system for people with AD. Our objectives are: 1) to improve the accuracy of ASR for people with AD; 2) to refine and validate our software in remote monitoring/assessment; 3) to embed our software into a user-friendly phone-based interface.
Program
Collaborative Health Research Projects (NSERC partnered)
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database

As published

Id
361205
Name
Rudzicz Frank
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Partnername
Natural Sciences and Engineering Research Council of Canada (NSERC)
Instname2
Aging
Theme2
Health systems / services
Prcname2
Collaborative Health Research Projects - NSERC Partnered
Projecttitle
Automatic remote screening of speech features associated with Alzheimer's disease
Programtype2
Operating Grants
Orgnameinp2
University of Toronto
Cihramount2
$220,133
Cihrequipment2
$0
Programname2
Collaborative Health Research Projects (NSERC partnered)
Keyworddelim
(1101) Human Health (Incl. Medically Related Psych. Rsch.); (1211) Medical And Health Sciences; (2605) Pattern Analysis And Machine Intelligence; 2801) Natural Language And Speech Understanding; Artificial Intelligence; Dementia; Remote Assessment; Signal Processing; Speech-Based Interfaces; Speech-Language Pathology
Abstract
Assessing Alzheimer's disease (AD) is an expensive and laborious process that is unsustainable given our rapidly aging population, especially if one accounts for indirect costs such as lost time in travel, wait times, and hours spent in assessment, which is a process so labourious that it is often repeated only every few years. Moreover, the high variability of symptoms in AD cannot be ascertained accurately from a single assessment, which minimizes the effectiveness of current practice. Rapid, repeatable, and remote assessment is essential. Many individuals with AD have diminished language abilities. Linguistic measures, like the ratio of pronouns to nouns, relate strongly to cognitive decline. By measuring such features and using advanced machine learning software, we have developed computational methods that are over 85% accurate in identifying Alzheimer's disease from short speech samples. As we continue to improve this technology, we will make it available over the public phone network accessible by a 1-800 number. This system will automatically receive calls from (and make calls to) outpatients, and completely automate speech-based tests including question-answering, narratives, and random item generation. This will be encapsulated in an interface that healthcare workers can use to assign and monitor assessments and exercises. Currently, to extract language measures, speech must be transcribed by professionals, which is impossible on large scales. Unfortunately, no automatic speech recognition (ASR) system exists for people with AD. We will therefore provide the first complete ASR system for people with AD. Our objectives are: 1) to improve the accuracy of ASR for people with AD; 2) to refine and validate our software in remote monitoring/assessment; 3) to embed our software into a user-friendly phone-based interface.
Competitiondate
201610
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Rudzicz, Frank; Hirst, Graeme; Jokel, Regina
Approvedterm
3 ans 0 mois
Cihrcontribution2
Major Initiatives #2~ $220,133~ $0~