Grant: Alliance Grants
University of Calgary
$50,000.00
An end-to-end machine learning development and deployment platform for digital health researchers and innovators
EF 2023-24
Résumé
Currently, machine learning (ML) is an enormously popular research topic in digital health. Despite the interest, ML has not made much impact in real-world clinical environments because it is challenging to translate ML-based technologies from in silico to real-world settings. Such a translation requires an iterative process that trains initial ML models, deploys them at the point of care, monitors the performance of the deployed models, detects data and concept drifts in production, and re-train/re-deploy the models (i.e., MLOps). This is a daunting, cumbersome, and complex process for most digital health researchers and innovators. To fill this gap, this project aims to develop a web-based, end-to-end software solution to automate and streamline the entire ML development, deployment, and management cycle. No programming will be required, and a graphical user interface will make it easy to manage complex health ML projects from start to finish. ML development will be optimized automatically in a systematic way and fully leverage available computing resources. The deliverables at the end of the 2-year funding period will be a product feature specification based on iterative co-applicant feedback, a working prototype validated in lab environments, and its source code. The commercial potential of our technology is outstanding given that the health artificial intelligence market is poised to grow explosively in the coming years. Both health researchers without technical expertise and experienced digital health innovators will benefit from our technology. Moreover, although our initial focus will be on health, our technology can easily be adapted to other problem domains. We anticipate that our technology will increase the number of successful health ML projects in Alberta and significantly accelerate their progress. Alberta's health care system will save costs through improved patient outcomes and clinical efficiency resulting from effective ML-based innovations.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
590556-2023
Name nom
Lee, Joon J
Department département
Cardiac Sciences
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
50000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1101
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Human health (including medically-related psychological research)
Area of application fr
Santé publique (y compris recherche psychologique liée à la médecine)
Research subject code
2705
Research subject group en
Information technology
Research subject group fr
Software and development
Research subject en
Technologie de l'information
Research subject fr
Logiciels et développement
Application title
An end-to-end machine learning development and deployment platform for digital health researchers and innovators
Keyword
artificial intelligence; digital health; machine learning; MLOps
Application summary
Currently, machine learning (ML) is an enormously popular research topic in digital health. Despite the interest, ML has not made much impact in real-world clinical environments because it is challenging to translate ML-based technologies from in silico to real-world settings. Such a translation requires an iterative process that trains initial ML models, deploys them at the point of care, monitors the performance of the deployed models, detects data and concept drifts in production, and re-train/re-deploy the models (i.e., MLOps). This is a daunting, cumbersome, and complex process for most digital health researchers and innovators. To fill this gap, this project aims to develop a web-based, end-to-end software solution to automate and streamline the entire ML development, deployment, and management cycle. No programming will be required, and a graphical user interface will make it easy to manage complex health ML projects from start to finish. ML development will be optimized automatically in a systematic way and fully leverage available computing resources. The deliverables at the end of the 2-year funding period will be a product feature specification based on iterative co-applicant feedback, a working prototype validated in lab environments, and its source code. The commercial potential of our technology is outstanding given that the health artificial intelligence market is poised to grow explosively in the coming years. Both health researchers without technical expertise and experienced digital health innovators will benefit from our technology. Moreover, although our initial focus will be on health, our technology can easily be adapted to other problem domains. We anticipate that our technology will increase the number of successful health ML projects in Alberta and significantly accelerate their progress. Alberta's health care system will save costs through improved patient outcomes and clinical efficiency resulting from effective ML-based innovations.