Grant: Master's Award: Canada Graduate Research Scholarships - Master's program
University of Calgary
$27,000.00
Characterizing Wearables-Derived Mobility Signatures in Older Adults for Naturalistic Frailty Assessment
FY 2025-26
Summary
Canada’s population is steadily aging, and by 2068, more than 1 in 5 Canadians will be 65 or older. The aging process can bring several health related challenges like chronic diseases and reduced independent functionality. Frailty is an age-related clinical condition marked by the decline of cognitive, physical, psychological and social domains. Higher frailty can lead to increased risk of falls, hospitalization, and mortality. Multiple frailty screening tools and questionnaires are prevalent in current clinical practice. However, these surveys are subjective and may miss subtle daily variations linked to functional decline. Early interventions can slow down, prevent, or even reverse frailty, but timely detection remains a clinical challenge. Gait and mobility data from wearable devices is an accessible, objective means to extract frailty-related insights. Previous work has utilized brief, high-resolution lab assessments or low-resolution, long-term activity monitoring. There is a need for high-resolution mobility monitoring in daily life settings. This project will implement continuous, real-world approaches using wearable sensory insole and contextual GPS data, to detect mobility signatures of frailty in older adults. Comprehensive gait and community activity features of 60 adults, aged 65 and older, will be collected in lab and unsupervised daily life settings over a 4-week timeframe. These features will be used to develop and validate a machine learning framework for classifying frailty status. The broader objective is to identify digital biomarkers that signal the onset and progression of frailty, enabling earlier intervention, improved patient outcomes, and reduced healthcare burden.
Department
Program
Master's Award: Canada Graduate Research Scholarships - Master's program
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
572791
Name
Mehta Maahika
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Characterizing Wearables-Derived Mobility Signatures in Older Adults for Naturalistic Frailty Assessment
Programtype2
Studentship Programs
Orgnameinp2
University of Calgary
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Research Scholarships - Master's program
Keyworddelim
Chronic Disease; Community Mobility; Digital Health; Early Diagnostic Techniques; Frailty; Gait Biomechanics; Healthy Aging; Machine Learning; Public Health; Wearables
Abstract
Canada’s population is steadily aging, and by 2068, more than 1 in 5 Canadians will be 65 or older. The aging process can bring several health related challenges like chronic diseases and reduced independent functionality. Frailty is an age-related clinical condition marked by the decline of cognitive, physical, psychological and social domains. Higher frailty can lead to increased risk of falls, hospitalization, and mortality. Multiple frailty screening tools and questionnaires are prevalent in current clinical practice. However, these surveys are subjective and may miss subtle daily variations linked to functional decline. Early interventions can slow down, prevent, or even reverse frailty, but timely detection remains a clinical challenge. Gait and mobility data from wearable devices is an accessible, objective means to extract frailty-related insights. Previous work has utilized brief, high-resolution lab assessments or low-resolution, long-term activity monitoring. There is a need for high-resolution mobility monitoring in daily life settings. This project will implement continuous, real-world approaches using wearable sensory insole and contextual GPS data, to detect mobility signatures of frailty in older adults. Comprehensive gait and community activity features of 60 adults, aged 65 and older, will be collected in lab and unsupervised daily life settings over a 4-week timeframe. These features will be used to develop and validate a machine learning framework for classifying frailty status. The broader objective is to identify digital biomarkers that signal the onset and progression of frailty, enabling earlier intervention, improved patient outcomes, and reduced healthcare burden.
Competitiondate
202512
Approvedterm2
1 yr 0 mth
Pinamesdelim
Mehta, Maahika
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~