Technology for Maintaining Good Mental and Cognitive Health

Currently, 747,000 Canadians have some type of cognitive impairment, including dementia. This number is expected to double to 1.4 million by 2031. Furthermore, 20% of Canadian seniors are living with a mental illness, anxiety and depression. Pain tends to be under-reported and not treated, resulting in agitation and aggression, while mood disorders often go untreated. Researchers in TECH-MCH are developing software applications for screening and assessment, interventions to enhance mental health and cognitive function, and tools that can automatically detect behaviours that lead to poor cognitive and mental health. TECH-MCH will result in new technologies in an area that has largely been ignored in the technology and aging field.

Workpackage Leads
  • Lili Liu, University of Alberta
  • Eleni Stroulia, University of Alberta


Core Research Projects

ICT applications for Screening, Assessment and Interventions to Enhance Mental Health – 6.1 MEN-ASSESS

This project focuses on the use of information communication technologies (ICTs) to provide older adults in the community with access to information that helps them manage the stressors of caregiving. It also provides access to a suite of applications that help older adults to manage their own signs and symptoms of depression and anxiety. These apps may also be in the form of games on mobile devices that older adults can use in their own homes to practice cognitive skills including those prescribed by their health professionals.

 

Project Leads
  • Mark Chignell, University of Toronto
  • Lili Liu, University of Alberta
Researchers
  • Bob Alosio, Independent (industry representative)
  • Eleni Stroulia, University of Alberta
  • Jacques Lee, Sunnybrook Health Sciences
  • Leon Zucherman, University of Toronto
  • Marc Kanik, Keebee Play
  • Ron Beleno, Independent

 

Automated Assessments of Cognitive Impairment using Environment-based Sensing – 6.2 COG-ASSESS

How can we monitor a person’s daily-life activities through an easily available and inexpensive hardware-software system, in order to recognize changes that predict future cognitive decline? That is the broad research question being investigated by this project. To that end, we will (a) use a variety of commercial off-the-shelf sensors (from infrared sensors to cameras) and sensor-embedded “smart” devices, (b) design algorithms for analyzing and fusing the sensor data-streams of these devices, as well as the resulting data archives, and (c) develop software systems implementing these algorithms and integrating the physical infrastructure to monitor and predict if an older adult will suffer from cognitive decline. This work is at the core of the AGE-WELL vision “to help older Canadians to maintain their independence, health and quality of life through accessible information communication technologies that increase their safety and security”. Cost-effective technical solutions for recognizing – ahead of time – indicators of potential future cognitive decline will enable independent living for older adults, providing peace of mind for seniors and their families.

Project Leads
  • Eleni Stroulia, University of Alberta
Researchers
  • , University of Manitoba
  • Herbert Yang, University of Alberta
  • Ioanis Nikolaidis, University of Alberta
  • Jacqueline Rousseau, University of Montreal
  • Lili Liu, University of Alberta
  • Norm O'Rourke, Simon Fraser University

 

Development, Implementation and Evaluation of an Automated Pain Detection System for Older Adults with Dementia – 6.3 PAIN-ASSESS

Pain is very common in older populations. However, older adults are often undertreated for pain, especially those with serious dementia who live in nursing homes and cannot report their pain because of cognitive impairments that accompany dementia. The goal of this project is to develop and evaluate an affordable technology that will facilitate regular pain assessment with minimal resources. Our project involves an inexpensive vision-based sensor that can be easily implemented in most long-term care facilities. The system is being designed to assist health-care staff with pain assessment while at the same time addressing limitations due to staffing shortages. The plan is to test and evaluate the complete system in at least two long-term care facilities and determine its impact.

Project Leads
  • Thomas Hadjistavropoulos, University of Regina
  • Babak Taati, Toronto Rehab Institute/University of Toronto
Researchers
  • Greg Marchildon, University of Toronto
  • Kenneth Prkachin, University of Northern British Columbia

 

WinterLight Labs: Cognitive Assessment through Speech – 6.4-S1 SPEECH-ASSESS

Alzheimer’s disease (AD) is the most common cause of dementia and affects 44 million people worldwide. These numbers are predicted to triple by 2050. There is a pressing need for a simple, accessible and efficient system for detecting and monitoring AD. This would improve the lives of people living with Alzheimer’s, accelerate clinical trials, and reduce individual and societal costs. Our team has developed a fully-automated assessment that uses natural language and machine learning to detect cognitive impairment. The software analyzes hundreds of variables in speech and language collected in free-form picture description.

Project Leads
  • Frank Rudzicz, Toronto Rehab Institute/University of Toronto

 

Assessing Cognitive Ability using Automated Assessment of Speech – 6.5-CAT

Clinical measures of cognition typically rely on time-consuming, subjective and expensive assessments. However, our recent advances in computational linguistics, signal processing, and machine learning now allow for objective, automatic, and rapid analysis of cognition, through speech. Our prior work has focused on binary classification problems between people with or without a particular disorder, such as Alzheimer’s disease. In this grant, we will use these modern tools to objectively assess cognition, differentially in people with post-stroke aphasia and memory impairment, by measures of speech and language at 5 time points. This will be applied to a new technological medium – the telephone, which will allow for broader data collection and unique insights in human-computer interaction.

Dr. Frank Rudzicz leads this project, with two industrial partners: WinterLight Labs, and CBI Health Group. WinterLight Labs will supply speech-based assessment to support data collection and data analysis. Patients will be recruited at CBI Health Group clinics, and clinical assessment will be provided by Drs. Regina Jokel and Andrea Iaboni. Research will be conducted at the Toronto Rehabilitation Institute, the Rotman Research Institute at Baycrest, and the University of Toronto.

Our primary objective is to validate the computational speech-based assessment techniques relative to current gold standard assessments. This will involve modern machine learning that is more incisive than the current state-of-the-art. This will be accomplished within two elicitation platforms: a traditional web-based interface, and a phone-based interface. Optimizing the latter is crucial in order to establish the feasibility of using this platform across as wide a population as possible.

In the short term, this project will 1) validate current automatic cognitive assessments, 2) create a new industrial collaboration between a large healthcare network and a local technology startup in Canada, and 3) further our understanding of cognitive function in different patient populations among older Canadians.

Project Leads
  • Frank Rudzicz, Toronto Rehab Institute/University of Toronto
Researchers
  • Regina Jokel, University of Toronto

 

Big Data Analysis Algorithm for the Analysis of Lifestyle Factors on the Aging Process – 6.6-CAT

The number of older adults (age 65+) is increasing rapidly in Canada. In order to preserve health and minimize strain on limited healthcare resources, it is important to mobilize knowledge and efficiently allocate resources to allow older adults to proactively maintain their own health. A key limitation to this is that older adults often do not know what type of activities can best support their health, nor the amount of time they should engage in them. In order to reduce these barriers, we propose a Big Data analysis to identify the lifestyle factors most strongly associated with good health. These factors will be simplified and combined into a single Aging Health Score (AHS) that older adults can use to understand and improve their own health. This AHS will be developed in close partnership with the YMCA of Greater Vancouver to ensure that it is both ecologically valid and easily measured from end-users. We will then work with the local YMCA to identify ways to improve the AHS in its older adult members. To do this, we will use data analytics to identify ways in which the YMCA can efficiently deliver impactful programs and services that are targeted to its members. The successful completion of this project will allow for larger adoption by the YMCA at the provincial and national levels, and will provide researchers with a flexible analysis pipeline that can be used to make informed, data-driven decisions about healthcare delivery for older adults.

Project Leads
  • Martin Ester, Simon Fraser University
Researchers
  • Sylvain Moreno, Simon Fraser University

 

Brain Fitness APP for Aging with a Healthy Brain and Detecting Cognitive Declines – 6.7-CAT

Memory and cognitive declines are associated with normal brain aging but are also precursors to dementia, in particular the so-called pandemic of the century, Alzheimer’s disease. While currently there is no cure or “vaccine” against dementia, there are hopes to delay the onset of the disease by living a brain-healthy lifestyle. The proposed research offers a novel approach to prevent dementia and age-related cognitive disorders.

We propose to create a brain fitness APP for the aging population. The proposed APP is based on the premise of brain plasticity, and targets the brain functions that are declining with normal aging and dementia. In a pilot study, we showed very positive effects of our custom designed brain exercises to strengthen left-right side brain connectivity in older adults when used regularly. Leveraging our previous design, we propose to develop an end-user product with additional features and enhanced user interface and user experience that will allow it to be used for neuro-cognitive rehabilitation by an individual without supervision.

The proposed APP will be tested on a large population with statistical rigor. We will analyze the logged performance of the participants, and assess their cognitive state with an independent test compared to a matched control group before and after the trial. The APP will be commercialized by our industrial partner to reach older adults nationally and internationally.

We anticipate the frequent use of the proposed APP will help to maintain a healthy brain as well as detecting the onset of cognitive decline. In addition, its frequent use will slow and even reverse the progression of the cognition decline in individuals with mild cognitive impairment or dementia. The APP will have many different levels of difficulty so that it can be applied to a wide age range and conditions.

Project Leads
  • Zahra Moussavi, University of Manitoba

 

Product adaptation and verification of a technology to monitor cognition in older adults – 6.8-SIP A1

Problem: According to the Alzheimer's Association, about 600,000 Canadians have some form of dementia, costing more than $10.4 billion annually. In 15 years, this number will climb to 937,000. Early diagnosis and ongoing validation of treatments with respect to cognitive impairment is critical to promote healthy aging amongst this population. Thus, there is increasing demand for rapid, user-friendly technologies to identify early decline in brain function. Yet, there are currently no cost-effective ways to monitor the physiological impacts of treatments for cognitive decline. Research suggests evoked potentials using electroencephalography (EEG), may provide such a measure. However, current state-of-the-art requires numerous 'leads' and extensive clinical training. Standard EEG testing puts strain on the cognitivelyimpaired, who have trouble sitting still for typical 1-hour examination periods: 25 minutes of EEG cap set-up and multiple paradigms each taking some 10 minutes. 

Purpose: We will validate the use of a low-cost, 'rapid output' EEG platform for the diagnosis and assessment of cognitive impairment. NeuroCatchTM is a clinician-friendly software tool, translating established brain waves into a clinicallyaccessible, understandable framework. NeuroCatchTM outperforms existing EEG tools by extracting critical brain data in about 5 minutes. NeuroCatchTM has been tested amongst people with brain injuries and concussions. Given that the cognitively-impaired have similar challenges, reworking the product for this population is a logical next step.

Impact: We will verify NeuroCatch's capacity to assess functional brain status amongst people with cognitive impairment, establishing a new product for healthy aging. Funding will support minor design changes, field-testing and deliver a validated prototype. Led by trainees, this project delivers a cheaper accessible tool for clinicians, saves healthcare costs, improves diagnosis and treatment monitoring and reaches the global cognition market, ultimately improving the lives of aging adults in Canada and internationally.

Project Leads
  • Frank Knoefel, Bruyere Research Institute

 

Towards a Market Ready Centivizer Product: Evaluation and Refinement of Prototypes in Long-term Care Settings – 6.9-SIP A2

Individuals living with dementia in long-term care are often under-stimulated and lack much of the physical and cognitive engagement required for a meaningful quality of life. The Centivizer system provides rewarded interactions to people with dementia..  It  has  been developed  by  specialists  in  human  factors  and  applied  psychology,  working  with  an  electrical engineer and a mechanical engineer in the Interactive Media Lab, University of Toronto. The current Centivizer prototype has a slider, a lever, and large coloured buttons as input devices to a number of game-like applications where interactions are rewarded with music and lights. Feedback is provided with a large screen and speakers, and the unit also has a pullout draw that contains two standalone activities (a Whack-a-Mole game and a talking phone). We are also developing a modular Centivizer platform where third party developers will be invited to contribute (and license) their modules to the system. Earlier Centivizer prototypes have been demonstrated at conferences and informally user tested in a number of long-term care homes. The purpose of this SIP Accelerator project is to evaluate the Centivizer prototype at Lakeside Long-Term Care Centre in Toronto, Ontario and at York Care Centre in Fredericton, New Brunswick as a final step towards commercialization. Our goal is to develop and market the first Centivizer product once this research project is completed. Key deliverables for this project will be an improved Centivizer prototype and a finalized product specification ready for productization and marketing, along with an application program interface (API) for adding modules to the Centivizer system.

Project Leads
  • Mark Chignell, University of Toronto

 

Click here to return to the Research Themes and Projects page.