Cerebral stroke patient symmetric gait-oriented lower limb motion function assessment method and system
By collecting and analyzing electromyographic signals from the lower limbs of stroke patients, a multimodal feature fusion dataset was constructed, and a lightweight gradient booster algorithm was used to evaluate the model. This solved the subjectivity problem in the assessment of lower limb motor function in existing technologies, and enabled quantitative assessment of lower limb motor function and the development of personalized rehabilitation plans for stroke patients.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHANGCHUN UNIV OF TECH
- Filing Date
- 2026-04-23
- Publication Date
- 2026-05-26
AI Technical Summary
Existing lower limb motor function assessment techniques suffer from strong subjectivity and a lack of quantitative analysis, making it difficult to accurately assess the rehabilitation progress of stroke patients and develop personalized intervention strategies.
By collecting lower limb surface electromyography signals from stroke patients and healthy subjects, feature extraction and quantification were performed to construct a multimodal feature fusion dataset. A lightweight gradient booster algorithm was used to build an evaluation model, and the contribution of each feature was quantified using the Shapley additive interpretation method to achieve qualitative classification and functional scoring of the subjects' pathological and normal movement patterns.
It enables an effective and comprehensive quantitative assessment of lower limb motor function in stroke patients, providing quantitative evidence, laying the foundation for the development of personalized rehabilitation training plans, and improving the scientific nature and accuracy of the assessment.
Smart Images

Figure CN122074967A_ABST
Abstract
Citation Information
Patent Citations
CN103886215A
CN112494054A
CN118252497A
US20120184838A1
US20220095989A1