Grant: Master's Award: Canada Graduate Research Scholarships - Master's program
University of British Columbia
$27,000.00
Precision Medicine and Equity: Assessing Accuracy, Clinical Utility, and Fairness of Risk Stratification Algorithms for Chronic Obstructive Pulmonary Disease (COPD)
EF 2025-26
Résumé
COPD is a chronic lung condition affecting 2.6 million Canadians, characterised by episodes of acute worsening symptoms known as exacerbations. Current guidelines recommend risk stratification based on exacerbation history in the previous 12 months; however, multivariable risk stratification algorithms can significantly improve the accuracy of risk stratification. One of the popular risk stratification algorithms is the Acute COPD Exacerbation Prediction Tool (ACCEPT) that has been developed and validated using data from highly selective randomised trials and clinical cohorts. Before implementation for patient care, tools like ACCEPT must be externally validated in a representative sample. External validity is assessed using calibration, discrimination, and clinical utility. An important and often overlooked aspect of validity is prediction fairness: that the algorithm provides equally useful predictions among different patient subgroups. Prediction accuracy can vary across and within populations according to social determinants of health, including age, sex, socio-economic status, and ethnicity. These differences often remain hidden, resulting in the loss of clinical utility among vulnerable subgroups. This can perpetuate existing disparities in healthcare and outcomes. In all, it is unknown whether current risk stratification algorithms are generalisable across populations and subgroups within a population. This study aims to evaluate the performance and fairness of risk stratification for exacerbations, namely exacerbation history and ACCEPT, among COPD patients in Canada and internationally across geographic areas and by age, sex, socio-economic status, and ethnicity, Ultimately improving patient outcomes while ensuring optimal use of limited healthcare resources.
Programme
Master's Award: Canada Graduate Research Scholarships - Master's program
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
572620
Name
Leung Crystal
Region
British Columbia
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Precision Medicine and Equity: Assessing Accuracy, Clinical Utility, and Fairness of Risk Stratification Algorithms for Chronic Obstructive Pulmonary Disease (COPD)
Programtype2
Studentship Programs
Orgnameinp2
University of British Columbia
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Research Scholarships - Master's program
Keyworddelim
Biostatistics; Chronic Obstructive Pulmonary Disease; Equity; Fairness Metrics; Model Validation; Precision Medicine; Predictive Modelling; Respiratory; Risk Prediction; Social Determinants Of Respiratory Diseases
Abstract
COPD is a chronic lung condition affecting 2.6 million Canadians, characterised by episodes of acute worsening symptoms known as exacerbations. Current guidelines recommend risk stratification based on exacerbation history in the previous 12 months; however, multivariable risk stratification algorithms can significantly improve the accuracy of risk stratification. One of the popular risk stratification algorithms is the Acute COPD Exacerbation Prediction Tool (ACCEPT) that has been developed and validated using data from highly selective randomised trials and clinical cohorts. Before implementation for patient care, tools like ACCEPT must be externally validated in a representative sample. External validity is assessed using calibration, discrimination, and clinical utility. An important and often overlooked aspect of validity is prediction fairness: that the algorithm provides equally useful predictions among different patient subgroups. Prediction accuracy can vary across and within populations according to social determinants of health, including age, sex, socio-economic status, and ethnicity. These differences often remain hidden, resulting in the loss of clinical utility among vulnerable subgroups. This can perpetuate existing disparities in healthcare and outcomes. In all, it is unknown whether current risk stratification algorithms are generalisable across populations and subgroups within a population. This study aims to evaluate the performance and fairness of risk stratification for exacerbations, namely exacerbation history and ACCEPT, among COPD patients in Canada and internationally across geographic areas and by age, sex, socio-economic status, and ethnicity, Ultimately improving patient outcomes while ensuring optimal use of limited healthcare resources.
Competitiondate
202512
Approvedterm2
1 yr 0 mth
Pinamesdelim
Leung, Crystal
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~