Grant: Master's Award: Canada Graduate Scholarships
University of Toronto
$17,500.00
Predicting Long-term Survival and Cause-specific Mortality in Patients with Metabolic Syndrome Associated Liver Disease Using Machine Learning Algorithms
EF 2023-24
Résumé
Metabolic syndrome associated liver disease (MASLD) affects a quarter of the global population. People with MASLD face not only liver-related complications like cirrhosis and hepatocellular carcinoma, but also systemic health issues such as heart disease, stroke, and other de novo malignancies. Recent studies show that these systemic health issues contribute more to the overall health of individuals with MASLD than liver disease.
There are currently no clinical tools that accurately predict long-term mortality in patients with MASLD and cirrhosis given the complexity of considering both liver-related complications and competing risks of systemic complications. Machine learning (ML) has recently emerged as a promising solution, possessing the ability to integrate vast amounts of data and infer non-linear complex relationships among large quantities of variables.
We will use data from over 200,000 patients in Ontario, Canada, sourced from the Institute for Clinical Evaluative Sciences (IC/ES) database to train and validate a machine learning algorithm that not only accurately predicts long-term mortality, but also stratifies cause-specific mortality risk in patients with MASLD. This data will include blood samples, patient demographics, and medical history, among other factors. We will build tree-based and artificial neural network architectures modified to handle survival analysis for this purpose.
Ultimately, we aspire to create an online resource for healthcare professionals, enabling them to utilise our machine learning model for better managing patients with MASLD and cirrhosis, enhancing understanding of the long-term complications of MASLD, and assisting in the development of more individualised treatment plans for patient benefit.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
506583
Name
Zhao Xun
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Predicting Long-term Survival and Cause-specific Mortality in Patients with Metabolic Syndrome Associated Liver Disease Using Machine Learning Algorithms
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Cardiovascular Mortality; Cirrhosis; Competing Risk Of Mortality; End-Stage Liver Disease; Machine Learning; Metabolic Syndrome-Associated Liver Disease
Abstract
Metabolic syndrome associated liver disease (MASLD) affects a quarter of the global population. People with MASLD face not only liver-related complications like cirrhosis and hepatocellular carcinoma, but also systemic health issues such as heart disease, stroke, and other de novo malignancies. Recent studies show that these systemic health issues contribute more to the overall health of individuals with MASLD than liver disease.
There are currently no clinical tools that accurately predict long-term mortality in patients with MASLD and cirrhosis given the complexity of considering both liver-related complications and competing risks of systemic complications. Machine learning (ML) has recently emerged as a promising solution, possessing the ability to integrate vast amounts of data and infer non-linear complex relationships among large quantities of variables.
We will use data from over 200,000 patients in Ontario, Canada, sourced from the Institute for Clinical Evaluative Sciences (IC/ES) database to train and validate a machine learning algorithm that not only accurately predicts long-term mortality, but also stratifies cause-specific mortality risk in patients with MASLD. This data will include blood samples, patient demographics, and medical history, among other factors. We will build tree-based and artificial neural network architectures modified to handle survival analysis for this purpose.
Ultimately, we aspire to create an online resource for healthcare professionals, enabling them to utilise our machine learning model for better managing patients with MASLD and cirrhosis, enhancing understanding of the long-term complications of MASLD, and assisting in the development of more individualised treatment plans for patient benefit.
Competitiondate
202312
Approvedterm2
1 yr 0 mth
Pinamesdelim
Zhao, Xun
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~