Creation of a Multi-center Database Registry to Study Real World Thalamus Volume Changes by Use of Artificial Intelligence in Patients With Multiple Sclerosis (MS)
Trial Snapshot
- Phase
- Not Applicable
- Status
- Completed
- Sponsor
- University at Buffalo
- Enrollment
- 1,000
- Locations
- 1
- Primary Endpoint
- Multi-center registry of MRI scans
Study Overview
Brief Summary
In this study the Investigator's propose to validate a newly developed approach, DeepGRAI (Deep Gray Rating via Artificial Intelligence), to simplify the calculation of thalamic atrophy in a clinical routine and allow academic and community neurologists to plan, perform, and publish novel and influential clinical research using data from clinical routine, by employing deep machine learning (DML) pattern recognition (PR) information through use of artificial intelligence (AI).
Detailed Description
This is a multicenter, observational, retrospective, cross-sectional and longitudinal population study of brain volume changes in MS patients. The retrospective electronic medical record (EMR) and brain MRI image data will be collected at participating MS centers and de-identified data will be integrated into a central research database. All the data to be integrated into the database has already been collected by physicians at the centers as part of their routine clinical practice and is thus non-interventional and retrospective in nature. This new approach will be compared to existing approaches of brain volume measurement that are currently widely available. This breakthrough approach would lead to potentially abandoning classis measurement of the specific brain volume structures and would be applicable in real-time in clinical routine.
Study Design
- Study Type
- Observational
- Observational Model
- Case Only
- Time Perspective
- Retrospective
Eligibility Criteria
- Ages
- 18 Years to 85 Years (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Patient diagnosed with relapsing-remitting (RR) MS
- •Access to raw MRI index scan images that meet all of the below criteria
- •MRI scan image acquired at index
- •The scan was performed on 1.5T or 3T scanners
- •The scan must have a T2-FLAIR sequence
- •Access to raw MRI post-index scan images that meet all of the below listed criteria
- •MRI scan image acquired at post-index
- •The scan was performed on 1.5T or 3T scanners
- •The scan must have a T2-FLAIR sequence
- •Age 18-85 at index
- •Fulfilling the MRI scan and clinical data requirements outlined in Table 2
- •None of the exclusion criteria
Exclusion Criteria
- •Have received an investigational drug or experimental procedure during the study period
- •Women who were pregnant, or lactating at index or during the post-index period
- •Patients who had a relapse 30 days prior to the selected MRI scan date
- •Patients who received steroid treatment 30 days prior to the selected MRI scan date
- •Presence of other neurologic diseases affecting CNS
Outcomes
Primary Outcomes
Multi-center registry of MRI scans
Time Frame: 2 years
Measuring the ability of DeepGRAI to measure thalamus volume as a predictor of clinical outcomes for patients with multiple sclerosis
Secondary Outcomes
No secondary outcomes reported
Investigators
Robert Zivadinov, MD, PhD
Director and Professor
University at Buffalo