Explainable Artificial Intelligence (XAI) for Remote Health Sensing and Monitoring Systems in Northern Canada
- Funded by Canadian Institutes of Health Research (CIHR)
- Total publications:0 publications
Grant number: 516603
Grant search
Key facts
Disease
COVID-19start year
2024.0Known Financial Commitments (USD)
$155,910.09Funder
Canadian Institutes of Health Research (CIHR)Principal Investigator
. Banerjee Shib SundarResearch Location
CanadaLead Research Institution
St. Michael's Hospital Foundation (Toronto, ON)Research Priority Alignment
N/A
Research Category
Secondary impacts of disease, response & control measures
Research Subcategory
Indirect health impacts
Special Interest Tags
N/A
Study Type
Non-Clinical
Clinical Trial Details
N/A
Broad Policy Alignment
Pending
Age Group
Unspecified
Vulnerable Population
Indigenous People
Occupations of Interest
Unspecified
Abstract
The recent outbreak of COVID-19 has underscored the critical role of telehealth and digital therapeutics in pandemic preparedness. This is especially true for northern Indigenous communities, where the assessment of mental health is crucial due to the increasing incidence of depression, addiction, and suicide. Detection and intervention through digital platforms can enhance mental well-being and enable personalized treatment strategies, even in remote settings. The aim of this proposal is to develop a comprehensive digital health monitoring (DHM) system for remote mental health assessment. This system will integrate multimodal monitoring using wearable devices, mobile application platforms, and VR modules. The ultimate objective is to develop a digital decision support system with added explainability for clinicians, facilitating the early detection, diagnosis, and intervention of common mental disorders. This Indigenous co-led project includes the design of a digital framework to inform clinicians about the mental health status of patients for continuous monitoring purposes. The multimodal data recorded from members of the Indigenous community will be analyzed on a single platform using advanced fusion approaches. Intelligent and explainable algorithms will be developed to classify participants in the context of psychiatric nosology, providing an objective measurement of individual mental health risk. Best practices will be adopted regarding privacy, ethics, and transparency for both data curation and transfer. The outcomes of the study will be useful for implementing Digital Mental Health Interventions (DMHIs) using multimodal measurement systems and validating the DMHI framework for the clinical management of marginalized populations in a post-pandemic scenario. The framework can further be standardized under the Software-as-a-Medical-Device (SaMD) context within the regulatory landscape of Canada and beyond.