The final, formatted version of the article will be published soon.
SYSTEMATIC REVIEW article
Front. Neurosci.
Sec. Neurodegeneration
Volume 18 - 2024 |
doi: 10.3389/fnins.2024.1446878
The Identification of Cognitive Impairment in Parkinson’s Disease Using Biofluids, Neuroimaging, and Artificial Intelligence
Provisionally accepted- 1 Krembil Brain Institute, University Health Network (UHN), Toronto, Canada
- 2 Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada
- 3 Brain Health Imaging Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada
- 4 Edmond J. Safra Program in Parkinson's Disease and the Morton and Gloria Shulman Movement Disorders Clinic, Division of Neurology, Krembil Neuroscience Centre (KNC), Toronto Western Hospital, Toronto, Ontario, Canada
Parkinson's disease (PD) is a neurodegenerative movement disorder causing severe disability and cognitive impairment as the disease progresses. It is necessary to develop biomarkers for cognitive decline in PD for earlier detection and prediction of disease progression. We reviewed literature which used artificial intelligence-based techniques, which can be more sensitive than other analyses, to determine potential biomarkers for cognitive impairment in PD. We found that combining biomarker types, including those from neuroimaging and biofluids, resulted in higher accuracy. Focused analysis on each biomarker type revealed that using structural and functional magnetic resonance imaging (MRI) resulted in accuracy and area under the curve (AUC) values above 80%/0.80, and that beta-amyloid-42 and tau were able to classify PD subjects by cognitive function with accuracy and AUC values above 90%/0.90. We can conclude that applying both blood-based and imaging-based biomarkers may improve diagnostic accuracy and prediction of cognitive impairment in PD.
Keywords: cognitive impairment, Parkinson's disease, diagnosis, biomarkers, machine learning, artificial intelligence
Received: 10 Jun 2024; Accepted: 02 Sep 2024.
Copyright: © 2024 Dennis and Strafella. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Anthaea-Grace Patricia Dennis, Krembil Brain Institute, University Health Network (UHN), Toronto, Canada
Antonio P. Strafella, Krembil Brain Institute, University Health Network (UHN), Toronto, Canada
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.