Objective: Evaluate the feasibility of implementing cycling-based exergames for children with cerebral palsy (CP) following lower extremity orthopedic surgery and explore its impact on pain and well-being. Methods: Ten children with CP were recruited; the first five received physiotherapy (comparison) and next five received fifteen exergame sessions over 3 weeks and physiotherapy (case) (NCT0376907). Feasibility indicators evaluated recruitment, questionnaire and exergame completion. Faces Pain Scale-Revised (FPS-R), PROMIS Pediatric Pain Interference Scale (PPIS), and KIDSCREEN-27 were administered. Wilcoxon signed-rank and effect size (r) tests evaluated within-group differences and between-group differences were assessed using Mann-Whitney U tests. Results: All feasibility indicators were met. Large effects for improved case group pain were identified (FPS-R r = 0.60, PPIS r = 0.58), as well as significant improvement in KIDSCREEN-27 total (U = 0.50, p = .05) and psychological well-being (U = 3.00, p = .01) scores, favoring the case group. Conclusions: Incorporating pediatric exergames is feasible and demonstrates potential for improving pain and well-being.
Animals can quickly learn the timing of events with fixed intervals and their rate of acquisition does not depend on the length of the interval. In contrast, recurrent neural networks that use gradient based learning have difficulty predicting the timing of events that depend on stimulus that occurred long ago. We present the latent time-adaptive drift-diffusion model (LTDDM), an extension to the time-adaptive driftdiffusion model (TDDM), a model for animal learning of timing that exhibits behavioural properties consistent with experimental data from animals. The performance of LTDDM is compared to that of a state of the art long short-term memory (LSTM) recurrent neural network across three timing tasks. Differences in the relative performance of these two models is discussed and it is shown how LTDDM can learn these events time series orders of magnitude faster than recurrent neural networks.
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.