Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Master's Award: Canada Graduate Scholarships

University of Toronto

$17,500.00

End-to-end development and validation of a deep learning model for dengue outbreak prediction

FY 2019-20

Summary
"Dengue is a potentially deadly, mosquito-borne disease with a significant impact on global health. In their mosquito control efforts, public health officials rarely have access to models that inform when and where outbreaks are likely to occur. Current models oversimplify the various human and environmental factors known to drive outbreaks. Here, I propose using a form of artificial intelligence known as deep learning to overcome existing limitations and more accurately predict outbreaks within Southeast Asia—a global dengue hotspot. Deep learning allows computers to learn patterns from massive datasets and create predictive models. After interviewing public health stakeholders in Singapore, the Philippines, and Laos to understand their needs, I will create an outbreak prediction model using state-of-the-art deep learning architectures. Groups predominantly only use climate and weather data to create predictive models, but these are not the only factors that drive outbreaks. I will overcome this limitation by leveraging not only meteorological data, but also data capturing mosquito distributions, air and ground travel, historical outbreak case numbers, and urbanization from the region. Once I have tuned model performance in a laboratory setting, I will convene stakeholders to evaluate perceptions of our model in an outbreak simulation exercise. My work will create a dengue outbreak prediction model that overcomes the limitations of traditional methods by using deep learning and involves stakeholders in the design and validation processes. By demonstrating the application of artificial intelligence for timely outbreak response and containment, this translational research will help public health agencies combat a devastating global health threat. "
Program
Master's Award: Canada Graduate Scholarships
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database

As published

Id
428852
Name
Harish Vinyas
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
End-to-end development and validation of a deep learning model for dengue outbreak prediction
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Dengue; Global Health; Infectious Disease Epidemiology; Machine Learning; Mosquito-Borne Diseases
Abstract
"Dengue is a potentially deadly, mosquito-borne disease with a significant impact on global health. In their mosquito control efforts, public health officials rarely have access to models that inform when and where outbreaks are likely to occur. Current models oversimplify the various human and environmental factors known to drive outbreaks. Here, I propose using a form of artificial intelligence known as deep learning to overcome existing limitations and more accurately predict outbreaks within Southeast Asia—a global dengue hotspot. Deep learning allows computers to learn patterns from massive datasets and create predictive models. After interviewing public health stakeholders in Singapore, the Philippines, and Laos to understand their needs, I will create an outbreak prediction model using state-of-the-art deep learning architectures. Groups predominantly only use climate and weather data to create predictive models, but these are not the only factors that drive outbreaks. I will overcome this limitation by leveraging not only meteorological data, but also data capturing mosquito distributions, air and ground travel, historical outbreak case numbers, and urbanization from the region. Once I have tuned model performance in a laboratory setting, I will convene stakeholders to evaluate perceptions of our model in an outbreak simulation exercise. My work will create a dengue outbreak prediction model that overcomes the limitations of traditional methods by using deep learning and involves stakeholders in the design and validation processes. By demonstrating the application of artificial intelligence for timely outbreak response and containment, this translational research will help public health agencies combat a devastating global health threat. "
Competitiondate
201912
Approvedterm2
1 yr 0 mth
Pinamesdelim
Harish, Vinyas
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~