Analysis of Conjoint Response in Post-stroke Patients Using the Attention-coupled Weighting Method

Rehabilitation assessment plays a vital role in the recovery process of post-stroke patients. Currently, many studies have focused on the implementation of automated assessment scales. However, the impact of stroke on the synergistic pattern between different human joints is not well understood. In this study, we developed an attention-coupled weighting based quantitative analysis model to identify the pathological alteration in the conjoint response structure between stroke patients and healthy participants, thus providing more intrinsic suggestions for the post-stroke rehabilitation training. In collaboration with the China Rehabilitation Research Center and the Macau University of Science and Technology, we recruited 15 post-stroke patients and 15 healthy participants to complete several actions selected from the Fugl-Meyer assessment (FMA) scale, which is a commonly used post-stroke rehabilitation assessment scale in clinical practice. Our study proposed an attentional coupling weight (ACW) extraction method. By filtering the weights in the attentional coupling network using a priori matrix, we can analyse the effect of stroke on the alteration of synergistic structures and the coordination patterns of the upper and lower extremities. Moreover, we used a commonly accepted synergy analysis method, the non-negative matrix decomposition (NMF) method, for comparison and validation. The experimental results demonstrated the effectiveness of our method in quantifying the synergistic structure pattern alterations in post-stroke patients, which provides a new targeted option for the rehabilitation process.