Grant: Alliance Grants
University of Calgary
$50,000.00
Trustworthy Artificial Intelligence for Healthcare Applications
EF 2023-24
Résumé
Artificial Intelligence (AI) is largely used in healthcare applications for multiple purposes: providing screening/triage tools, supporting patients' diagnosis, and assisting experts in decision-making. These models learn from datasets and are then used for personalized decision-making and targeted treatments. However, translating AI models for diverse and more extensive populations presents challenges, including biases, poor generalization, inconsistent recommendations, and issues of limited clinical relevance, reinforcing health inequality.Our main goal is to develop "better" AI algorithms for healthcare. Our definition of "better" considers not only accurate diagnosis but also factors like fairness, interpretability, and transparency. We will study and mitigate multiple sources of bias related to demographic variables, among others. Although this proposal focuses on healthcare applications, the translation of the proposed analysis and techniques to other applications, such as recommendation systems and security systems, is anticipated.In this proposal, our anticipated outcome is identifying problems, proposing solutions, and performing feasibility analysis, prototyping and testing to facilitate translation to real-world applications. Trustworthy AI in healthcare will deliver more confident, less prone to errors, and consistent findings to diverse populations, mitigating risks and possible harm to participants. We anticipate the impact on healthcare costs by minimizing misdiagnosis and delayed treatment, health disparities, inequality and inefficient resource allocation. Our proposal considers Equity, Diversity, and Inclusion a priority, as a trustworthy AI application presents reliable performance for equity-deserving groups and consistent results for participants of different genders, age ranges, ethnicity, varying educational backgrounds, among others, mitigating health inequality.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
590222-2023
Name nom
Pinheiro Bento, Mariana M
Department département
Schulich School of Engineering
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
1211
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Medical and health sciences
Area of application fr
Sciences médicales et de la santé
Research subject code
2804
Research subject group en
Artificial intelligence
Research subject group fr
Expert systems
Research subject en
Intelligence artificielle
Research subject fr
Systèmes experts
Application title
Trustworthy Artificial Intelligence for Healthcare Applications
Keyword
Artificial Intelligence; Data Aggregation; Fairness; Healthcare Application; Health Inequalities; Interpretability; Responsible AI; Trustworthy
Application summary
Artificial Intelligence (AI) is largely used in healthcare applications for multiple purposes: providing screening/triage tools, supporting patients' diagnosis, and assisting experts in decision-making. These models learn from datasets and are then used for personalized decision-making and targeted treatments. However, translating AI models for diverse and more extensive populations presents challenges, including biases, poor generalization, inconsistent recommendations, and issues of limited clinical relevance, reinforcing health inequality.Our main goal is to develop "better" AI algorithms for healthcare. Our definition of "better" considers not only accurate diagnosis but also factors like fairness, interpretability, and transparency. We will study and mitigate multiple sources of bias related to demographic variables, among others. Although this proposal focuses on healthcare applications, the translation of the proposed analysis and techniques to other applications, such as recommendation systems and security systems, is anticipated.In this proposal, our anticipated outcome is identifying problems, proposing solutions, and performing feasibility analysis, prototyping and testing to facilitate translation to real-world applications. Trustworthy AI in healthcare will deliver more confident, less prone to errors, and consistent findings to diverse populations, mitigating risks and possible harm to participants. We anticipate the impact on healthcare costs by minimizing misdiagnosis and delayed treatment, health disparities, inequality and inefficient resource allocation. Our proposal considers Equity, Diversity, and Inclusion a priority, as a trustworthy AI application presents reliable performance for equity-deserving groups and consistent results for participants of different genders, age ranges, ethnicity, varying educational backgrounds, among others, mitigating health inequality.