Explainable machine learning algorithm predicting working memory performance in Parkinson's disease using task-fMRI.
Authors
Affiliations (13)
Affiliations (13)
- Department of Neurology and Neurological Science, Institute of Science Tokyo, Bunkyo-Ku, Tokyo, Japan.
- Department of Neurology and Neurological Science, Institute of Science Tokyo, Bunkyo-Ku, Tokyo, Japan. [email protected].
- Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA. [email protected].
- Center for Education in Healthcare Innovation, Institute of Science Tokyo, Bunkyo-Ku, Tokyo, Japan.
- The Systems Biology Institute, Shinagawa-Ku, Tokyo, Japan.
- SBX BioSciences, Inc., Vancouver, BC, Canada.
- Faculty of Pharmacy, Keio University, Minato-Ku, Tokyo, Japan.
- Center for Mathematical Modelling and Data Science, Osaka University, Toyonaka, Osaka, Japan.
- Department of Diagnostic Radiology, Institute of Science Tokyo, Bunkyo-Ku, Tokyo, Japan.
- Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
- Division of Clinical Research, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
- Center for Integrated Human Brain Science, Brain Research Institute, Niigata University, Chuo-Ku, Niigata, Japan.
- Center for Advanced Medicine and Clinical Research, Sapporo Hakuyokai Hospital, Sapporo, Hokkaido, Japan.
Abstract
Parkinson's disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data. We enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs. The model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model's decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance. We developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice.