Grant: Master's Award: Canada Graduate Scholarships
McGill University
$17,500.00
Development of a deep learning algorithm to predict disability progression in progressive multiple sclerosis using baseline clinical information and magnetic resonance imaging of the brain.
FY 2019-20
Summary
"Multiple sclerosis is a neurological disease thought to be caused by the immune system attacking the protective covering around neurons (myelin). Some patients have a type of disease that progresses continuously, called progressive multiple sclerosis (PMS). Only one drug, ocrelizumab, has been approved in Canada to treat PMS, and its effect is unfortunately modest. There is therefore a need to facilitate drug development for PMS. A major bottleneck occurs in phase 2 clinical trials, where a drug's effect must be demonstrated in a very short time-frame (12 to 24 months) in order to be taken to the next phases where it is tested on larger groups of patients. Phase 2 efficiency could be improved by including more patients who are predicted to progress rapidly, but making this prediction has been difficult. Deep learning is a state-of-the-art method in the field of artificial intelligence that can learn complex patterns in data in order to make predictions. We hypothesize that it can predict if a patient with PMS will progress in the time allotted to a phase 2 clinical trial. We will design a deep learning algorithm that uses a patient's baseline clinical information and magnetic resonance imaging (MRI) to predict progression over 1 year. It will learn to make this prediction from a large database pertaining to 2,724 patients with PMS that was acquired through 4 clinical trials. Once optimized, we will compare our algorithm's prediction accuracy to existing markers of disease progression such as brain volume loss. If successful, this algorithm has the potential to not only improve drug development efficiency, but also to pave the path to precision medicine, where physicians could predict the future course of an individual patient's disease and adjust treatment accordingly."
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
428800
Name
Falet Jean-Pierre R
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Development of a deep learning algorithm to predict disability progression in progressive multiple sclerosis using baseline clinical information and magnetic resonance imaging of the brain.
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Deep Learning; Machine Learning; Magnetic Resonance Imaging; Multiple Sclerosis; Precision Medicine; Prediction; Progression
Abstract
"Multiple sclerosis is a neurological disease thought to be caused by the immune system attacking the protective covering around neurons (myelin). Some patients have a type of disease that progresses continuously, called progressive multiple sclerosis (PMS). Only one drug, ocrelizumab, has been approved in Canada to treat PMS, and its effect is unfortunately modest. There is therefore a need to facilitate drug development for PMS. A major bottleneck occurs in phase 2 clinical trials, where a drug's effect must be demonstrated in a very short time-frame (12 to 24 months) in order to be taken to the next phases where it is tested on larger groups of patients. Phase 2 efficiency could be improved by including more patients who are predicted to progress rapidly, but making this prediction has been difficult. Deep learning is a state-of-the-art method in the field of artificial intelligence that can learn complex patterns in data in order to make predictions. We hypothesize that it can predict if a patient with PMS will progress in the time allotted to a phase 2 clinical trial. We will design a deep learning algorithm that uses a patient's baseline clinical information and magnetic resonance imaging (MRI) to predict progression over 1 year. It will learn to make this prediction from a large database pertaining to 2,724 patients with PMS that was acquired through 4 clinical trials. Once optimized, we will compare our algorithm's prediction accuracy to existing markers of disease progression such as brain volume loss. If successful, this algorithm has the potential to not only improve drug development efficiency, but also to pave the path to precision medicine, where physicians could predict the future course of an individual patient's disease and adjust treatment accordingly."
Competitiondate
201912
Approvedterm2
1 yr 0 mth
Pinamesdelim
Falet, Jean-Pierre R
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~