Home »
Academic Articles »
C »
A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis
A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis
Michael Barnett
(Sydney Neuroimaging Analysis Centre)
Dongang Wang
(Sydney Neuroimaging Analysis Centre)
Heidi Beadnall
(Brain and Mind Centre, University of Sydney)
Antje Bischof
(Department of Neurology, University Hospital of Muenster)
David Brunacci
(Department of Radiology, Royal Prince Alfred Hospital)
Helmut Butzkueven
(Department of Neurology, The Alfred Hospital)
J. William L. Brown
(Department of Clinical Neurosciences, University of Cambridge)
Mariano Cabezas
(Brain and Mind Centre, University of Sydney)
Tilak Das
(Department of Radiology, University of Cambridge)
Tej Dugal
(Sydney Neuroimaging Analysis Centre)
Daniel Guilfoyle
(Department of Neurology, Royal Prince Alfred Hospital)
Alexander Klistorner
(Sydney Neuroimaging Analysis Centre)
Stephen Krieger
(Department of Neurology, Icahn School of Medicine at Mount Sinai)
Kain Kyle
(Sydney Neuroimaging Analysis Centre)
Linda Ly
(Sydney Neuroimaging Analysis Centre)
Lynette Masters
(I-MED Radiology)
Andy Shieh
(Sydney Neuroimaging Analysis Centre)
Zihao Tang
(Sydney Neuroimaging Analysis Centre)
Anneke van der Walt
(Department of Radiology, Royal Prince Alfred Hospital)
Kayla Ward
(Department of Neurology, Royal Prince Alfred Hospital)
Heinz Wiendl
(Department of Neurology, University Hospital of Muenster)
Geng Zhan
(Sydney Neuroimaging Analysis Centre)
Robert Zivadinov
(Buffalo Neuroimaging Analysis Centre)
Yael Barnett
(Sydney Neuroimaging Analysis Centre)
Chenyu Wang
(Sydney Neuroimaging Analysis Centre)
Journal: npj Digital Medicine
•
• Nature Portfolio
• ISSN: 2398-6352
Abstract
Abstract Modern management of MS targets No Evidence of Disease Activity (NEDA): no clinical relapses, no magnetic resonance imaging (MRI) disease activity and no disability worsening. While MRI is the principal tool available to neurologists for monitoring clinically silent MS disease activity and, where appropriate, escalating treatment, standard radiology reports are qualitative and may be insensitive to the development of new or enlarging lesions. Existing quantitative neuroimaging tools lack adequate clinical validation. In 397 multi-center MRI scan pairs acquired in routine practice, we demonstrate superior case-level sensitivity of a clinically integrated AI-based tool over standard radiology reports (93.3% vs 58.3%), relative to a consensus ground truth, with minimal loss of specificity. We also demonstrate equivalence of the AI-tool with a core clinical trial imaging lab for lesion activity and quantitative brain volumetric measures, including percentage brain volume loss (PBVC), an accepted biomarker of neurodegeneration in MS (mean PBVC −0.32% vs −0.36%, respectively), whereas even severe atrophy (>0.8% loss) was not appreciated in radiology reports. Finally, the AI-tool additionally embeds a clinically meaningful, experiential comparator that returns a relevant MS patient centile for lesion burden, revealing, in our cohort, inconsistencies in qualitative descriptors used in radiology reports. AI-based image quantitation enhances the accuracy of, and value-adds to, qualitative radiology reporting. Scaled deployment of these tools will open a path to precision management for patients with MS.
Michael Barnett, Dongang Wang, Heidi Beadnall, et al. (2023). "A real-world clinical validation for AI-based MRI monitoring in multiple sclerosis". npj Digital Medicine. https://doi.org/10.1038/s41746-023-00940-6