Friedrich, M.U., Relton, S. orcid.org/0000-0003-0634-4587, Wong, D. orcid.org/0000-0001-8117-9193 et al. (1 more author) (2025) Computer Vision in Clinical Neurology. JAMA Neurology, 82 (4). ISSN 2168-6149
Abstract
Importance Neurological examinations traditionally rely on visual analysis of physical clinical signs, such as tremor, ataxia, or nystagmus. Contemporary score-based assessments aim to standardize and quantify these observations, but these tools suffer from clinimetric limitations and often fail to capture subtle yet important aspects of human movement. This poses a significant roadblock to more precise and personalized neurological care, which increasingly focuses on early stages of disease. Computer vision, a branch of artificial intelligence, has the potential to address these challenges by providing objective measures of neurological signs based solely on video footage.
Observations Recent studies highlight the potential of computer vision to measure disease severity, discover novel biomarkers, and characterize therapeutic outcomes in neurology with high accuracy and granularity. Computer vision may enable sensitive detection of subtle movement patterns that escape the human eye, aligning with an emerging research focus on early disease stages. However, challenges in accessibility, ethics, and validation need to be addressed for widespread adoption. In particular, improvements in clinical usability and algorithmic robustness are key priorities for future developments.
Conclusions and Relevance Computer vision technologies have the potential to revolutionize neurological practice by providing objective, quantitative measures of neurological signs. These tools could enhance diagnostic accuracy, improve treatment monitoring, and democratize specialized neurological care. Clinicians should be aware of these emerging technologies and their potential to complement traditional assessment methods. However, further research focusing on clinical validation, ethical considerations, and practical implementation is necessary to fully realize the potential of computer vision in clinical neurology.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Medicine and Health (Leeds) > School of Medicine (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 19 Mar 2025 14:46 |
Last Modified: | 19 Mar 2025 14:46 |
Status: | Published |
Publisher: | American Medical Association |
Identification Number: | 10.1001/jamaneurol.2024.5326 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:224571 |