Objective To assess the effect of exercise training by using the Nintendo Wii Fit video game and balance board system on balance and gait in adults with Parkinson disease (PD). Design A prospective interventional cohort study. Setting An outpatient group exercise class. Participants Ten subjects with PD, Hoehn and Yahr stages 2.5 or 3, with a mean age of 67.1 years; 4 men, 6 women. Interventions The subjects participated in supervised group exercise sessions 3 times per week for 8 weeks by practicing 3 different Wii balance board games (marble tracking, skiing, and bubble rafting) adjusted for their individualized function level. The subjects trained for 10 minutes per game, a total of 30 minutes training per session. Main Outcome Measurements Pre-and postexercise training, a physical therapist evaluated subjects’ function by using the Berg Balance Scale, Dynamic Gait Index, and Sharpened Romberg with eyes open and closed. Postural sway was assessed at rest and with tracking tasks by using the Wii balance board. The subjects rated their confidence in balance by using the Activities-specific Balance Confidence scale and depression on the Geriatric Depression Scale. Results Balance as measured by the Berg Balance Scale improved significantly, with an increase of 3.3 points (P = .016). The Dynamic Gait Index improved as well (mean increase, 2.8; P = .004), as did postural sway measured with the balance board (decreased variance in stance with eyes open by 31%; P = .049). Although the Sharpened Romberg with eyes closed increased by 6.85 points and with eyes opened by 3.3 points, improvements neared significance only for eyes closed (P = .07 versus P = .188). There were no significant changes on patient ratings for the Activities-specific Balance Confidence (mean decrease, −1%; P = .922) or the Geriatric Depression Scale (mean increase, 2.2; P = .188). Conclusions An 8-week exercise training class by using the Wii Fit balance board improved selective measures of balance and gait in adults with PD. However, no significant changes were seen in mood or confidence regarding balance.
Mobile phones with built-in accelerometers promise a convenient, objective way to quantify everyday movements and classify those movements into activities. Using accelerometer data we estimate the following activities of 18 healthy subjects and eight patients with Parkinson’s disease: walking, standing, sitting, holding, or not wearing the phone. We use standard machine learning classifiers (support vector machines, regularized logistic regression) to automatically select, weigh, and combine a large set of standard features for time series analysis. Using cross validation across all samples we are able to correctly identify 96.1% of the activities of healthy subjects and 92.2% of the activities of Parkinson’s patients. However, when applying the classification parameters derived from the set of healthy subjects to Parkinson’s patients, the percent correct lowers to 60.3%, due to different characteristics of movement. For a fairer comparison across populations we also applied subject-wise cross validation, identifying healthy subject activities with 86.0% accuracy and 75.1% accuracy for patients. We discuss the key differences between these populations, and why algorithms designed for and trained with healthy subject data are not reliable for activity recognition in populations with motor disabilities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.