Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Doctoral Research Award: Canada Graduate Scholarships

University of Toronto

$105,000.00

Development, validation, and evaluation of an organized prostate cancer screening policy leveraging a population-based machine learning model predicting clinically significant prostate cancer

EF 2023-24

Résumé
Prostate cancer is common and the third leading cause of cancer-related death among Canadian men. Marginalized populations, including individuals with lower socioeconomic status and health literacy, are less likely to be diagnosed with prostate cancer at an early, curable stage and thus more likely to die of it. Current approaches to prostate cancer screening are done opportunistically on a case-by-case basis, which further reduces their accessibility to prostate-specific antigen (PSA) test screening for the early diagnosis of prostate cancer. A systematic, population-wide, organized PSA screening strategy may alleviate disparities in access to PSA screening and reduce later-stage prostate cancer diagnoses and mortality rates. However, organized PSA screening is not recommended due to overdiagnosis and overtreatment of clinically indolent prostate cancer. Therefore, there is an unmet need for smarter, organized prostate cancer screening policies that enhance equitable access to PSA screening while mitigating overdiagnosis. To address this challenge, I will develop a population-based machine learning model to better pinpoint individuals who would most benefit from PSA screening. This model will incorporate social determinants of health in addition to comprehensive, longitudinal, and population-based demographic, clinical, and healthcare data. Following the model's creation, I will evaluate the impact of an organized prostate cancer screening strategy guided by my machine learning model on overall societal well-being and disparities using modelling approaches. My work can reshape prostate cancer screening through machine learning-guided organized prostate cancer screening policies that enhance equity, reduce overdiagnosis, and improve outcomes of prostate cancer. It can inform the development and evaluation of similar machine learning-based screening strategies for other cancers. Co-Supervisors: Drs. Laura Rosella & Dr. Girish Kulkarni (University of Toronto)
Programme
Doctoral Research Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
495472
Name
Nguyen David-Dan
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Instname2
Health Services and Policy Research
Theme2
Health systems / services
Prcname2
Doctoral Research Awards - B
Projecttitle
Development, validation, and evaluation of an organized prostate cancer screening policy leveraging a population-based machine learning model predicting clinically significant prostate cancer
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$105,000
Cihrequipment2
$0
Programname2
Doctoral Research Award: Canada Graduate Scholarships
Keyworddelim
Cancer; Health Equity; Health Policy; Machine Learning; Prostate Cancer Screening
Abstract
Prostate cancer is common and the third leading cause of cancer-related death among Canadian men. Marginalized populations, including individuals with lower socioeconomic status and health literacy, are less likely to be diagnosed with prostate cancer at an early, curable stage and thus more likely to die of it. Current approaches to prostate cancer screening are done opportunistically on a case-by-case basis, which further reduces their accessibility to prostate-specific antigen (PSA) test screening for the early diagnosis of prostate cancer. A systematic, population-wide, organized PSA screening strategy may alleviate disparities in access to PSA screening and reduce later-stage prostate cancer diagnoses and mortality rates. However, organized PSA screening is not recommended due to overdiagnosis and overtreatment of clinically indolent prostate cancer. Therefore, there is an unmet need for smarter, organized prostate cancer screening policies that enhance equitable access to PSA screening while mitigating overdiagnosis. To address this challenge, I will develop a population-based machine learning model to better pinpoint individuals who would most benefit from PSA screening. This model will incorporate social determinants of health in addition to comprehensive, longitudinal, and population-based demographic, clinical, and healthcare data. Following the model's creation, I will evaluate the impact of an organized prostate cancer screening strategy guided by my machine learning model on overall societal well-being and disparities using modelling approaches. My work can reshape prostate cancer screening through machine learning-guided organized prostate cancer screening policies that enhance equity, reduce overdiagnosis, and improve outcomes of prostate cancer. It can inform the development and evaluation of similar machine learning-based screening strategies for other cancers. Co-Supervisors: Drs. Laura Rosella & Dr. Girish Kulkarni (University of Toronto)
Competitiondate
202311
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Nguyen, David-Dan
Approvedterm
3 ans 0 mois
Cihrcontribution2
~ $105,000~ $0~