Related Experiment Video
Updated: Jan 18, 2026
05:58
Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
Published on: March 11, 2021
5.0K
Community-based assisted screening for mild cognitive impairment using gait and handwriting kinematic parameters
Yin-Xia Ren1, Bei Wu2, Jian-Lin Lou3
1School of Medicine, Huzhou Key Laboratory of Precise Prevention and Control of Major Chronic Diseases, Huzhou University, Huzhou 313000, Zhejiang Province, China.
World Journal of Psychiatry
|September 11, 2025
Summary
Combining gait and handwriting analysis effectively screens for mild cognitive impairment (MCI) in older adults. This multimodal approach shows promise for early detection and large-scale screening, particularly in resource-limited settings.
Area of Science:
- Neurology
- Biomedical Engineering
- Gerontology
Background:
- Older adults with mild cognitive impairment (MCI) frequently exhibit motor deficits, such as slower walking and altered handwriting.
- While gait and handwriting are individually recognized indicators, their combined utility in differentiating MCI from normal cognition remains under investigation.
Purpose of the Study:
- To evaluate gait and handwriting characteristics for their potential in screening older adults for MCI.
- To explore the combined discriminative power of gait and handwriting data for MCI detection.
Main Methods:
- Ninety-five older adults (34 with MCI, 61 controls) participated.
- Gait was assessed using the GAITRite® system, and handwriting was captured with a dot-matrix pen.
- Five machine learning models were employed to analyze the data and assess MCI screening potential.
Main Results:
- Individuals with MCI demonstrated significantly slower gait velocity, shorter stride/step lengths, and altered gait timing compared to controls.
- Handwriting analysis revealed reduced pressure, lower accuracy, and distinct kinematic differences (e.g., velocity, acceleration) in the MCI group.
- A multimodal approach integrating gait and handwriting data achieved 74.4% accuracy in distinguishing MCI using a Gradient Boosting Classifier.
Conclusions:
- The integration of gait and handwriting kinematic parameters offers a viable method for distinguishing individuals with MCI.
- This combined approach holds potential for supporting large-scale MCI screening, especially in settings with limited resources.
