Clinical Efficacy of Motor Imagery-Based Brain-Computer Interface Collaborative Training Combined with Conventional Rehabilitation Therapy on Subacute Stroke Patients with Hemiplegia

<bold>Objective</bold> To observe the effects of motor imagery (MI)-based brain-computer interface (BCI) collaborative training on subacute stroke patients with hemiplegia. <bold>Methods</bold> A total of 40 stroke patients with hemiplegia hospitalized in the Hebei General Hospital from September 2022 to July 2023 were randomly divided into control group and experimental group by a random sequence generated from computer, with 20 cases in each group. The control group received conventional rehabilitation therapy (three hours a day, five days a week for three weeks) and routine upper limb motor training (30 minutes a time, once a day, five days a week for three weeks). The experimental group received MI-BCI collaborative training before routine rehabilitation treatment (30 minutes a time, once a day, five days a week for three weeks). Before and after three weeks of treatment, Fugl-Meyer Assessment for Upper Extremity (FMA-UE) and Wolf Motor Function Test (WMFT) were used to evaluate motor function of upper limb; Modified Barthel Index (MBI) was used to evaluate activities of daily living; BCI system was used to evaluate motor imagery accuracy. <bold>Results</bold> (1) FMA-UE, WMFT and MBI scores: compared with that before treatment, FMA-UE, WMFT and MBI scores in both groups after treatment increased significantly, and the differences were statistically significant (<italic>P</italic>&lt;0.05). Compared with the control group, FMA-UE, WMFT and MBI scores were significantly higher in the experimental group after treatment, and the differences were statistically significant (<italic>P</italic>&lt;0.05). (2) Correlation between the accuracy of motor imagery and FMA-UE, WMFT and MBI scores: the accuracy of motor imagery before treatment in the experimental group was (63.45±9.08)%, and the accuracy of motor imagery at the end of treatment was (80.50±13.77)%, and the difference was statistically significant (<italic>P</italic>&lt;0.05). The accuracy of motor imagery in the experimental group was positively correlated with FMA-UE (<italic>r</italic>=0.638, <italic>P</italic>=0.004), WMFT (<italic>r</italic>=0.660, <italic>P</italic>=0.002) and MBI scores (<italic>r</italic>=0.561, <italic>P</italic>=0.012). <bold>Conclusion</bold> MI-BCI collaborative training combined with conventional rehabilitation therapy can effectively improve the upper limb motor function, activities of daily living and the accuracy of motor imagery of subacute stroke patients with hemiplegia. Motor imagery has a positive effect on the recovery of upper limb motor function and activities of daily living.