Using a brain-machine interface to control a hybrid upper limb exoskeleton during rehabilitation of patients with neurological conditions

Abstract

Background: As a consequence of the increase of cerebro-vascular accidents, the number of people suffering from motor disabilities is raising. Exoskeletons, Functional Electrical Stimulation (FES) devices and Brain-Machine Interfaces (BMIs) could be combined for rehabilitation purposes in order to improve therapy outcomes.

Methods: In this work, a system based on a hybrid upper limb exoskeleton is used for neurological rehabilitation. Reaching movements are supported by the passive exoskeleton ArmeoSpring and FES. The movement execution is triggered by an EEG-based BMI. The BMI uses two different methods to interact with the exoskeleton from the user's brain activity. The first method relies on motor imagery tasks classification, whilst the second one is based on movement intention detection.

Results: Three healthy users and five patients with neurological conditions participated in the experiments to verify the usability of the system. Using the BMI based on motor imagery, healthy volunteers obtained an average accuracy of 82.9 ± 14.5 %, and patients obtained an accuracy of 65.3 ± 9.0 %, with a low False Positives rate (FP) (19.2 ± 10.4 % and 15.0 ± 8.4 %, respectively). On the other hand, by using the BMI based on detecting the arm movement intention, the average accuracy was 76.7 ± 13.2 % for healthy users and 71.6 ± 15.8 % for patients, with 28.7 ± 19.9 % and 21.2 ± 13.3 % of FP rate (healthy users and patients, respectively).

Conclusions: The accuracy of the results shows that the combined use of a hybrid upper limb exoskeleton and a BMI could be used for rehabilitation therapies. The advantage of this system is that the user is an active part of the rehabilitation procedure. The next step will be to verify what are the clinical benefits for the patients using this new rehabilitation procedure.

Fig. 1

Experimental setup diagram. The diagram represents the offline and online setups. In the offline test (red dashed line), the Task cuing block guides the user and EEG signals are registered for further analysis. In the online test (orange solid line), the EEG information is processed and classified to control the elbow movements (using the FES in the arm supported by the exoskeleton)

Fig. 2

Training paradigms. a Task sequences of the motor imagery test. The graphical interface shows a cross during three seconds. Afterward, the task to be performed is shown during two seconds. Finally, 10 or 30 s are established to perform the demanded task (motor imagery or rest time respectively). b Task sequence of the movement intention test. Firstly, the corresponding task is shown during three seconds. After that, seven seconds are established to perform the task, where the data between the seconds 4.5 and 8.5 are used as valid data to the classifier

Fig. 3

Motor imagery results - Online test. Percentages of TPR and FPR (and their average value) for healthy volunteers (H) and patients (P)

Fig. 4

Movement intention results - Offline test. Percentages of TPR and FPR (and their average value) for healthy volunteers (H) and patients (P)

Fig. 5

Movement intention results - Online test. Percentages of TPR and FPR (and their average value) for healthy volunteers (H) and patients (P)