Psychological State Estimation From Physiological Recordings During Robot-Assisted Gait Rehabilitation
By Koenig, Alexander; Omlin, Ximena; Zimmerli, Lukas; Sapa, Mark; Krewer, Carmen; Bolliger, Marc; Mueller, Friedemann; Riener, Robert; Journal of Rehabilitation Research and Development, Vol. 48, No. 4, pp. 367-386Publication Date: 2011
Study developed an approach using psychophysiological signals to estimate and classify a patient’s mental engagement during robot assisted gait therapy. The method was developed in light of the psychological state of patients during therapy often being neglected, despite evidence that attention to the task is a key factor for successful rehabilitation. A total of 17 nondisabled participants with a mean age of 24 years and 10 participants with gait impairments due to neurological disorders and a mean age of 52 years took part in the study. For the locomotion training, the study used the Lokomat, an exoskeleton that allows assisted locomotion on a treadmill by guiding users’ legs along a predefined trajectory. Participants were provided with a virtual reality task, projected on a video screen, which had varying difficulty levels to induce feelings of being bored, excited, and overstressed. Automatic classification of participants’ psychological states was performed by a neural network. Results showed that heart rate, skin conductance responses, and skin temperature can be used as markers for psychological states in the presence of physical effort induced by walking. The classifier achieved a classification error of 1.4 percent for nondisabled participants and 2.1 percent for patients with neurological disorders. Using the new method, the psychological state was processed in real time. The method is a first step toward real-time auto-adaptive gait training. The authors conclude it has potential to improve rehabilitation results by optimally challenging patients at all times during exercise.
Assistive Products Discussed: LOKOMATPRO (VERSIONS 5 & 6)
Published by:
VA Rehabilitation Research & Development Service (Web Site: http://www.rehab.research.va.gov )
Link to text: http://www.rehab.research.va.gov/jour/11/484/koenig484.html
