Effects of Assist-As-Needed Upper Extremity Robotic Therapy after Incomplete Spinal Cord Injury: A Parallel-Group Controlled Trial

Abstract

Background: Robotic rehabilitation of the upper limb following neurological injury has been supported through several large clinical studies for individuals with chronic stroke. The application of robotic rehabilitation to the treatment of other neurological injuries is less developed, despite indications that strategies successful for restoration of motor capability following stroke may benefit individuals with incomplete spinal cord injury (SCI) as well. Although recent studies suggest that robot-aided rehabilitation might be beneficial after incomplete SCI, it is still unclear what type of robot-aided intervention contributes to motor recovery.

Methods: We developed a novel assist-as-needed (AAN) robotic controller to adjust challenge and robotic assistance continuously during rehabilitation therapy delivered via an upper extremity exoskeleton, the MAHI Exo-II, to train independent elbow and wrist joint movements. We further enrolled seventeen patients with incomplete spinal cord injury (AIS C and D levels) in a parallel-group balanced controlled trial to test the efficacy of the AAN controller, compared to a subject-triggered (ST) controller that does not adjust assistance or challenge levels continuously during therapy. The conducted study is a stage two, development-of-concept pilot study.

Results: We validated the AAN controller in its capability of modulating assistance and challenge during therapy via analysis of longitudinal robotic metrics. For the selected primary outcome measure, the pre-post difference in ARAT score, no statistically significant change was measured in either group of subjects. Ancillary analysis of secondary outcome measures obtained via robotic testing indicates gradual improvement in movement quality during the therapy program in both groups, with the AAN controller affording greater increases in movement quality over the ST controller.

Conclusion: The present study demonstrates feasibility of subject-adaptive robotic therapy after incomplete spinal cord injury, but does not demonstrate gains in arm function occurring as a result of the robot-assisted rehabilitation program, nor differential gains obtained as a result of the developed AAN controller. Further research is warranted to better quantify the recovery potential provided by AAN control strategies for robotic rehabilitation of the upper limb following incomplete SCI. ClinicalTrials.gov registration number: NCT02803255.

Keywords: adaptive control; assist-as-needed therapy; incomplete spinal cord injury; motor learning; robot-aided rehabilitation.

Figure 1

Subject using the MAHI Exo-II robotic upper limb exoskeleton.

Figure 2

Flow diagram describing progression of subjects through the study.

Figure 3

Block diagram of the AAN controller implemented in this paper. Blocks with a yellow background include components of the adaptive controller (Slotine and Li, 1987). The dashed line refers to a discontinuous update of signal variables, i.e., the feedback gain is changed on a task-by-task basis.

Figure 4

(A) GUI used in the AAN controller, during the online recalculation “off” phase. The red circle corresponds to the active target, the blue circles are the other targets (center and periphery). The current subject position is displayed with the yellow ring, while the ghost cursor is the smaller yellow cursor leading the subject in this center-to-periphery movement (black arrow). (B) Sequence of the two modes of the ST controller. (1) A virtual wall is implemented, and the force required to keep the desired position (blue circle) is continuously measured. When the force exceeds F_th, the system switches to mode (2), where the robot implements position control toward the target (red circle).

Figure 5

Change in average controller gain $\mathrm{\Delta }{K}_{\text{d}}^{\left(k\right)}$ (blue) and allotted time ΔT^(k) (red) per session relative to session T1 for elbow [upper left], wrist PS [upper right], wrist FE [lower left], and wrist RUD [lower right]. Negative values indicate a decrease in the amount of assistance (gain) received or amount of time allotted for the task, respectively. The legend indicates the number of AAN subjects who completed the task at each training session. Error bars extend to ± the standard error for the group.

Figure 6

Comparison of number of training repetitions completed per session relative to training session T1 for elbow [upper left], wrist PS [upper right], wrist FE [lower left], and wrist RUD [lower right]. The legend indicates the number of subjects who completed the task at each training session. Error bars extend to ± the standard error for the group.

Figure 7

Percent change in ST group force threshold during the therapy program, relative the value used in the first session. Error bars extend to ± the standard error for the group.

Figure 8

Comparison of the clinical measures to baseline, measured post-treatment (PT), 2 weeks after treatment (2wk), and 2 months after treatment (2 M). The AAN values are shown in red, and the ST values are shown in blue. The clinical measures presented are the Action Research Arm Test (ARAT) [upper left], the quantitative [upper right], strength [middle-left], and sensation [middle-right] portions of the Graded Redefined Assessment of Strength, Sensibility, and Prehension Test (GRASSP), the Modified Ashworth Scale (MAS) [lower left], and the Grip Pinch Strength assessment [lower right]. The legend indicates the number of subjects who completed the task at each session for that measure. Error bars extend to ± the standard error for the group.

Figure 9

Longitudinal outcomes for spectral arc length (SAL) showing change in metric for each training session relative to training session T1 for elbow [upper left], wrist PS [upper right], wrist FE [lower left], and wrist RUD [lower right]. Positive values indicate smoother movements than exhibited in T1. Linearly increasing trends indicate continuous improvement in movement smoothness during the course of therapy. The legend indicates the number of subjects who completed the task at each training session. Error bars extend to ± the standard error for the group.