Grant: Doctoral Research Award: Canada Graduate Scholarships
University of Toronto
$120,000.00
Development and Validation of Clinical Prediction Models for Functional and Patient-Reported Degenerative Cervical Myelopathy Outcomes
FY 2024-25
Summary
Degenerative cervical myelopathy (DCM) is a common and disabling condition which occurs when progressive age-related arthritic changes narrow the cervical spinal canal leading to chronic spinal cord compression and neurological dysfunction. Patients with DCM experience significant impairment in quality of life driven by symptoms including neck pain, hand clumsiness, difficulty walking, numbness in arms and feet, and in severe cases, loss of bladder or bowel control. Surgical intervention is the primary treatment modality for those with moderate to severe DCM. While the primary aim of surgery is to halt further functional decline, recent research has shown benefits in neurological function, pain relief, and reduced disability across various symptom severities. That said, not all patients do well post-operatively; while 2/3 of patients experience improvement in function and disability, 1/3rd experience no improvement or may be worse after surgery. Considering the significant variability observed in patient outcomes, my thesis will focus on developing predictive models that can guide clinical decision-making and tailor treatment strategies to individual patient profiles. We aim to develop, train, and validate a machine learning algorithm to predict surgical outcomes in patients with DCM utilizing multidimensional clinical and patient-reported outcome measures. Moreover, we will use two multicenter databases: the Canadian Spine Outcomes and Research Network (CSORN) and the AO Spine databases, which together provide a comprehensive repository of over 2000 patients with DCM, representing the largest combined dataset of DCM patients worldwide to our knowledge. These databases contain patient-level information, including demographic, clinical, radiological, and surgical variables. The development and validation of such models have the potential to revolutionize the management of DCM, enabling a personalized medicine approach to facilitate improved patient care and outcomes.
Department
Program
Doctoral Research Award: Canada Graduate Scholarships
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
518359
Name
Karthikeyan Vishwathsen
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Instname2
Population and Public Health
Theme2
Clinical
Prcname2
Doctoral Research Awards - B
Projecttitle
Development and Validation of Clinical Prediction Models for Functional and Patient-Reported Degenerative Cervical Myelopathy Outcomes
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$120,000
Cihrequipment2
$0
Programname2
Doctoral Research Award: Canada Graduate Scholarships
Keyworddelim
Clinical Epidemiology; Clinical Prediction Modelling; Degenerative Cervical Myelopathy; Machine Learning; Population Health; Quality Of Life; Regression Analysis; Spine Surgery; Surgical Outcomes
Abstract
Degenerative cervical myelopathy (DCM) is a common and disabling condition which occurs when progressive age-related arthritic changes narrow the cervical spinal canal leading to chronic spinal cord compression and neurological dysfunction. Patients with DCM experience significant impairment in quality of life driven by symptoms including neck pain, hand clumsiness, difficulty walking, numbness in arms and feet, and in severe cases, loss of bladder or bowel control. Surgical intervention is the primary treatment modality for those with moderate to severe DCM. While the primary aim of surgery is to halt further functional decline, recent research has shown benefits in neurological function, pain relief, and reduced disability across various symptom severities. That said, not all patients do well post-operatively; while 2/3 of patients experience improvement in function and disability, 1/3rd experience no improvement or may be worse after surgery. Considering the significant variability observed in patient outcomes, my thesis will focus on developing predictive models that can guide clinical decision-making and tailor treatment strategies to individual patient profiles. We aim to develop, train, and validate a machine learning algorithm to predict surgical outcomes in patients with DCM utilizing multidimensional clinical and patient-reported outcome measures. Moreover, we will use two multicenter databases: the Canadian Spine Outcomes and Research Network (CSORN) and the AO Spine databases, which together provide a comprehensive repository of over 2000 patients with DCM, representing the largest combined dataset of DCM patients worldwide to our knowledge. These databases contain patient-level information, including demographic, clinical, radiological, and surgical variables. The development and validation of such models have the potential to revolutionize the management of DCM, enabling a personalized medicine approach to facilitate improved patient care and outcomes.
Competitiondate
202411
Approvedterm2
3 yrs 0 mth
Pinamesdelim
Karthikeyan, Vishwathsen
Approvedterm
3 ans 0 mois
Cihrcontribution2
~ $120,000~ $0~