Related Experiment Video
Updated: Aug 2, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Machine Learning Model for Mild Cognitive Impairment Stage Based on Gait and MRI Images
Ingyu Park1, Sang-Kyu Lee2, Hui-Chul Choi3
1Department of Electronic Engineering, Hallym University, Chuncheon 24252, Republic of Korea.
Abstract:
In patients with mild cognitive impairment (MCI), a lower level of cognitive function is associated with a higher likelihood of progression to dementia. In addition, gait disturbances and structural changes on brain MRI scans reflect cognitive levels. Therefore, we aimed to classify MCI based on cognitive level using gait parameters and brain MRI data. Eighty patients diagnosed with MCI from three dementia centres in Gangwon-do, Korea, were recruited for this study. We defined MCI as a Clinical Dementia Rating global score of ≥0.5, with a memory domain score of ≥0.5. Patients were classified as early-stage or late-stage MCI based on their mini-mental status examination (MMSE) z-scores. We trained a machine learning model using gait and MRI data parameters. The convolutional neural network (CNN) resulted in the best classifier performance in separating late-stage MCI from early-stage MCI; its performance was maximised when feature patterns that included multimodal features (GAIT + white matter dataset) were used. The single support time was the strongest predictor. Machine learning that incorporated gait and white matter parameters achieved the highest accuracy in distinguishing between late-stage MCI and early-stage MCI.
Insights
Machine learning models can accurately distinguish between early and late stages of mild cognitive impairment (MCI) using gait and brain MRI data. The single support time in gait analysis was the most significant predictor for classifying MCI progression.
Area of Science:
- Neurology
- Gerontology
- Biomedical Engineering
Background:
- Mild cognitive impairment (MCI) signifies reduced cognitive function, increasing dementia risk.
- Gait disturbances and brain MRI structural changes correlate with cognitive decline in MCI patients.
Purpose of the Study:
- To classify mild cognitive impairment (MCI) stages using gait parameters and brain MRI data.
- To identify reliable predictors for differentiating early-stage from late-stage MCI.
Main Methods:
- Eighty MCI patients were recruited and classified into early or late stages based on MMSE z-scores.
- A machine learning model, specifically a convolutional neural network (CNN), was trained using gait and MRI data.
- Multimodal features, including gait parameters and white matter datasets, were utilized to optimize classification.
Main Results:
- The CNN model achieved high performance in distinguishing late-stage from early-stage MCI.
- Integrating multimodal features (GAIT + white matter dataset) maximized the CNN classifier's performance.
- Single support time emerged as the strongest predictor for MCI stage classification.
Conclusions:
- Machine learning incorporating gait and white matter parameters effectively differentiates between late-stage and early-stage MCI.
- This approach offers a promising tool for objective MCI staging and monitoring disease progression.
