Grant: Master's Award: Canada Graduate Scholarships
University of Calgary
$17,500.00
Integrating clinical metrics and an advanced MRI protocol to improve machine learning modelling of mild degenerative cervical myelopathy.
EF 2022-23
Résumé
Degenerative Cervical Myelopathy (DCM) is the most common form of non-traumatic spinal cord injury globally. Patients with DCM experience, to varying extents, ‘degenerative arthritis’ of their spine, causing spinal cord compression and, ultimately, problems with hand coordination, walking, and carrying out day-to-day activities. Currently, the only method of treating DCM is through surgery. However, through experience, we know that patients with mild disease may never deteriorate and, therefore, undertaking surgery may not be necessary. Currently, an effective scheme that distinguishes between patients who are likely to remain mild for years and those who may rapidly progress to more severe forms of DCM – and thus would benefit from early treatment – is lacking. This poses a problem for millions of other people with mild forms of DCM at risk of getting worse but are currently overlooked for surgical intervention. I will use machine learning tools to evaluate different clinical metrics and magnetic resonance imaging-derived (MRI) metrics to predict which mild DCM patients are at risk of future neurological deterioration. As such, our machine learning models will allow us to identify which clinical tests are the best predictors of spine deterioration and, ultimately, aid clinicians to better prioritize mild patients for surgery. Thus, even for clinics which do not integrate our models into their workflows, the guidelines we devise will allow them to make informed decisions about which patients should receive surgery. Ultimately, this work will be an innovative use of computational neuroscience to provide a clinically practical and cost-effective solution to a long-standing and growing healthcare problem.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
486560
Name
Al-Shawwa Abdul
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Integrating clinical metrics and an advanced MRI protocol to improve machine learning modelling of mild degenerative cervical myelopathy.
Programtype2
Studentship Programs
Orgnameinp2
University of Calgary
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Bioinformatics; Cervical Spondylotic Myelopathy; Clinical Guidelines; Degenerative Cervical Myelopathy; Disease Prediction; Disease Prognosis; Health Data Science; Machine Learning; Spine
Abstract
Degenerative Cervical Myelopathy (DCM) is the most common form of non-traumatic spinal cord injury globally. Patients with DCM experience, to varying extents, ‘degenerative arthritis’ of their spine, causing spinal cord compression and, ultimately, problems with hand coordination, walking, and carrying out day-to-day activities. Currently, the only method of treating DCM is through surgery. However, through experience, we know that patients with mild disease may never deteriorate and, therefore, undertaking surgery may not be necessary. Currently, an effective scheme that distinguishes between patients who are likely to remain mild for years and those who may rapidly progress to more severe forms of DCM – and thus would benefit from early treatment – is lacking. This poses a problem for millions of other people with mild forms of DCM at risk of getting worse but are currently overlooked for surgical intervention. I will use machine learning tools to evaluate different clinical metrics and magnetic resonance imaging-derived (MRI) metrics to predict which mild DCM patients are at risk of future neurological deterioration. As such, our machine learning models will allow us to identify which clinical tests are the best predictors of spine deterioration and, ultimately, aid clinicians to better prioritize mild patients for surgery. Thus, even for clinics which do not integrate our models into their workflows, the guidelines we devise will allow them to make informed decisions about which patients should receive surgery. Ultimately, this work will be an innovative use of computational neuroscience to provide a clinically practical and cost-effective solution to a long-standing and growing healthcare problem.
Competitiondate
202212
Approvedterm2
1 yr 0 mth
Pinamesdelim
Al-Shawwa, Abdul
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~