Training finger individuation with a mechatronic-virtual reality system leads to improved fine motor control post-stroke

Abstract

Background: Dexterous manipulation of the hand, one of the features of human motor control, is often compromised after stroke, to the detriment of basic functions. Despite the importance of independent movement of the digits to activities of daily living, relatively few studies have assessed the impact of specifically targeting individuated movements of the digits on hand rehabilitation. The purpose of this study was to investigate the impact of such finger individuation training, by means of a novel mechatronic-virtual reality system, on fine motor control after stroke.

Methods: An actuated virtual keypad (AVK) system was developed in which the impaired hand controls a virtual hand playing a set of keys. Creation of individuated digit movements is assisted by a pneumatically actuated glove, the PneuGlove. A study examining efficacy of the AVK system was subsequently performed. Participants had chronic, moderate hand impairment resulting from a single stroke incurred at least 6 months prior. Each subject underwent 18 hour-long sessions of extensive therapy (3x per week for 6 weeks) targeted at finger individuation. Subjects were randomly divided into two groups: the first group (Keypad: N = 7) utilized the AVK system while the other group (OT: N = 7) received a similarly intensive dose of occupational therapy; both groups worked directly with a licensed occupational therapist. Outcome measures such as the Jebsen-Taylor Hand Function Test (JTHFT), Action research Arm Test (ARAT), Fugl-Meyer Upper Extremity Motor Assessment/Hand subcomponent (FMUE/FMH), grip and pinch strengths were collected at baseline, post-treatment and one-month post-treatment.

Results: While both groups exhibited some signs of change after the training sessions, only the Keypad group displayed statistically significant improvement both for measures of impairment (FMH: p = 0.048) and measures of task performance (JTHFT: p = 0.021). Additionally, the finger individuation index - a measure of finger independence - improved only for the Keypad group after training (p = 0.05) in the subset (Keypad: N = 4; OT: N = 5) of these participants for which it was measured.

Conclusions: Actively assisted individuation therapy comprised of non task-specific modalities, such as can be achieved with virtual platforms like the AVK described here, may prove to be valuable clinical tools for increasing the effectiveness and efficiency of therapy following stroke.

Figure 1

Actuated virtual keypad (AVK) system. User wears the PneuGlove which both measures joint angles through bend sensors and provides assistance to finger extension or resistance to finger flexion through pneumatic actuation. The user controls the virtual hand through the PneuGlove, and thus depression of the keys.

Figure 2

Graphical User Interface (GUI) for the AVK system. Therapist adjusts parameters to grade task difficulty according to subjects’ ability level throughout the session, such as the amount of assistance/resistance pressure provided, the angular thresholds for key stroke, and the digits to be monitored.

Figure 3

The AVK system. A) Key Combination mode—The user must depress the instructed keys within a specified period of time and then release the keys. If unsuccessful, the digits in error are highlighted with red rings at the end of each trial. A score for each trial and a running score are shown on the screen to the user as feedback (not pictured). B) Song Mode—The user is given a series of key combinations in order to play the chosen song. The pictured sequence was for the ring finger (first image) followed by the index finger (middle image) and middle finger (last image) independently. A score for each key press was awarded and tallied for an overall song score (not pictured). Bonus points could be earned for perfect sequential key presses (e.g. Mega Combo).

Figure 4

Change in finger individuation. Values averaged across subjects for each digit for A) AVK B) OT. Error bars represent SE. *Paired t-test: p-value = 0.050 across all digits.

Figure 5

Noninferiority testing of treatment difference (AVK-OT) at one-month follow-up relative to baseline. A) ARAT and B) JTHFT both showing AVK superiority and C) LPS showing noninferiority.

Figure 6

Performance across training sessions on exercises with the AVK system. Success in Key Combination Mode as quantified by the A) Win Ratio and B) Difficulty. Markers indicate mean across subjects for each session. C) Change in performance of Song Mode for a single subject. Comparison of mean song score during the first (dark gray bar) and last session (light gray bar) for a single subject using the same difficulty settings. Error bars indicate SD. *p-value < 0.005.