Grant: DRA: Canada Impact+ Research Training Awards - Doctoral
University of Calgary
$120,000.00
Assessing the Health System Impact of AI/Machine Learning–Enhanced Case-Finding in Patients with Chronic Kidney Disease
EF 2025-26
Résumé
"The integration of artificial intelligence (AI) and machine learning (ML) into healthcare, particularly for the early detection and management of chronic diseases, remains constrained by limited evidence of real-world clinical, economic, and system-level impact. Most evaluations emphasize technical performance rather than outcomes affecting patient care or health system efficiency. Although federated learning (FL) enables multi-institutional model development without sharing patient-level data, its robustness and feasibility in routine practice remain insufficiently assessed. Meanwhile, detection methods still rely on administrative classification systems that lack clinical granularity, have limited sensitivity for early disease, and are susceptible to miscoding. Using chronic kidney disease (CKD) as the primary use case, this project will develop and evaluate generalizable methodologies for AI/ML/FL-based case-finding and risk prediction to support earlier detection and enhance health system performance. The project has three objectives: (1) to conduct scoping review to synthesize the health and economic burden associated with delayed CKD detection; (2) to develop and applying methodological frameworks to compare AI/ML-based early detection with ICD-based approaches; and (3) to assess patient-level and system-level clinical and economic impact of implementing AI/ML models, including FL in practice.
Using population-based clinical data from Alberta, the project will assess outcomes across four domains: clinical indicators (e.g., kidney failure progression), economic measures (e.g., healthcare costs and potential savings), operational metrics (e.g., timeliness and accuracy of detection), and equity assessments (e.g., disparities in detection across socioeconomic groups)."
Programme
DRA: Canada Impact+ Research Training Awards - Doctoral
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
568234
Name
Al-Mukdad Sawsan
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Canada Impact+ Research Training Awards - Doctoral
Projecttitle
Assessing the Health System Impact of AI/Machine Learning–Enhanced Case-Finding in Patients with Chronic Kidney Disease
Programtype2
Studentship Programs
Orgnameinp2
University of Calgary
Cihramount2
$120,000
Cihrequipment2
$0
Programname2
DRA: Canada Impact+ Research Training Awards - Doctoral
Keyworddelim
Artificial Intelligence; Chronic Kidney Disease; Disease Detection; Economic Impact; Federated Learning; Machine Learning; Patient-Level Outcomes; Risk Prediction; System-Level Outcomes
Abstract
"The integration of artificial intelligence (AI) and machine learning (ML) into healthcare, particularly for the early detection and management of chronic diseases, remains constrained by limited evidence of real-world clinical, economic, and system-level impact. Most evaluations emphasize technical performance rather than outcomes affecting patient care or health system efficiency. Although federated learning (FL) enables multi-institutional model development without sharing patient-level data, its robustness and feasibility in routine practice remain insufficiently assessed. Meanwhile, detection methods still rely on administrative classification systems that lack clinical granularity, have limited sensitivity for early disease, and are susceptible to miscoding. Using chronic kidney disease (CKD) as the primary use case, this project will develop and evaluate generalizable methodologies for AI/ML/FL-based case-finding and risk prediction to support earlier detection and enhance health system performance. The project has three objectives: (1) to conduct scoping review to synthesize the health and economic burden associated with delayed CKD detection; (2) to develop and applying methodological frameworks to compare AI/ML-based early detection with ICD-based approaches; and (3) to assess patient-level and system-level clinical and economic impact of implementing AI/ML models, including FL in practice.
Using population-based clinical data from Alberta, the project will assess outcomes across four domains: clinical indicators (e.g., kidney failure progression), economic measures (e.g., healthcare costs and potential savings), operational metrics (e.g., timeliness and accuracy of detection), and equity assessments (e.g., disparities in detection across socioeconomic groups)."
Competitiondate
202603
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Al-Mukdad, Sawsan
Approvedterm
3 ans 0 mois
Cihrcontribution2
~ $120,000~ $0~