BACKGROUND: Approximately 5%-10% of elementary school children show delayed development of fine motor skills. To address these problems, detection is required. Current assessment tools are time-consuming, require a trained supervisor, and are not motivating for children. Sensor-augmented toys and machine learning have been presented as possible solutions to address this problem.OBJECTIVE: This study examines whether sensor-augmented toys can be used to assess children's fine motor skills. The objectives were to (1) predict the outcome of the fine motor skill part of the Movement Assessment Battery for Children Second Edition (fine MABC-2) and (2) study the influence of the classification model, game, type of data, and level of difficulty of the game on the prediction.METHODS: Children in elementary school (n=95, age 7.8 [SD 0.7] years) performed the fine MABC-2 and played 2 games with a sensor-augmented toy called "Futuro Cube." The game "roadrunner" focused on speed while the game "maze" focused on precision. Each game had several levels of difficulty. While playing, both sensor and game data were collected. Four supervised machine learning classifiers were trained with these data to predict the fine MABC-2 outcome: k-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), and support vector machine (SVM). First, we compared the performances of the games and classifiers. Subsequently, we compared the levels of difficulty and types of data for the classifier and game that performed best on accuracy and F1 score. For all statistical tests, we used α=.05.RESULTS: The highest achieved mean accuracy (0.76) was achieved with the DT classifier that was trained on both sensor and game data obtained from playing the easiest and the hardest level of the roadrunner game. Significant differences in performance were found in the accuracy scores between data obtained from the roadrunner and maze games (DT, P=.03; KNN, P=.01; LR, P=.02; SVM, P=.04). No significant differences in performance were found in the accuracy scores between the best performing classifier and the other 3 classifiers for both the roadrunner game (DT vs KNN, P=.42; DT vs LR, P=.35; DT vs SVM, P=.08) and the maze game (DT vs KNN, P=.15; DT vs LR, P=.62; DT vs SVM, P=.26). The accuracy of only the best performing level of difficulty (combination of the easiest and hardest level) achieved with the DT classifier trained with sensor and game data obtained from the roadrunner game was significantly better than the combination of the easiest and middle level (P=.046).CONCLUSIONS: The results of our study show that sensor-augmented toys can efficiently predict the fine MABC-2 scores for children in elementary school. Selecting the game type (focusing on speed or precision) and data type (sensor or game data) is more important for determining the performance than selecting the machine learning classifier or level of difficulty.
DOCUMENT
Motor learning is particularly challenging in neurological rehabilitation: patients who suffer from neurological diseases experience both physical limitations and difficulties of cognition and communication that affect and/or complicate the motor learning process. Therapists (e.g.,, physiotherapists and occupational therapists) who work in neurorehabilitation are therefore continuously searching for the best way to facilitate patients during these intensive learning processes. To support therapists in the application of motor learning, a framework was developed, integrating knowledge from the literature and the opinions and experiences of international experts. This article presents the framework, illustrated by cases from daily practice. The framework may assist therapists working in neurorehabilitation in making choices, implementing motor learning in routine practice, and supporting communication of knowledge and experiences about motor learning with colleagues and students. The article discusses the framework and offers suggestions and conditions given for its use in daily practice.
DOCUMENT
Movement is an essential part of our lives. Throughout our lifetime, we acquire many different motor skills that are necessary to take care of ourselves (e.g., eating, dressing), to work (e.g., typing, using tools, care for others) and to pursue our hobbies (e.g., running, dancing, painting). However, as a consequence of aging, trauma or chronic disease, motor skills may deteriorate or become “lost”. Learning, relearning, and improving motor skills may then be essential to maintain or regain independence. There are many different ways in which the process of learning a motor skill can be shaped in practice. The conceptual basis for this thesis was the broad distinction between implicit and explicit forms of motor learning. Physiotherapists and occupational therapists are specialized to provide therapy that is tailored to facilitate the process of motor learning of patients with a wide range of pathologies. In addition to motor impairments, patients suffering from neurological disorders often also experience problems with cognition and communication. These problems may hinder the process of learning at a didactic level, and make motor learning especially challenging for those with neurological disorders. This thesis focused on the theory and application of motor learning during rehabilitation of patients with neurological disorders. The overall aim of this thesis was to provide therapists in neurological rehabilitation with knowledge and tools to support the justified and tailored use of motor learning in daily clinical practice. The thesis is divided into two parts. The aim of the first part (Chapters 2‐5) was to develop a theoretical basis to apply motor learning in clinical practice, using the implicit‐explicit distinction as a conceptual basis. Results of this first part were used to develop a framework for the application of motor learning within neurological rehabilitation (Chapter 6). Afterwards, in the second part, strategies identified in first part were tested for feasibility and potential effects in people with stroke (Chapters 7 and 8). Chapters 5-8 are non-final versions of an article published in final form in: Chapter 5: Kleynen M, Moser A, Haarsma FA, Beurskens AJ, Braun SM. Physiotherapists use a great variety of motor learning options in neurological rehabilitation, from which they choose through an iterative process: a retrospective think-aloud study. Disabil Rehabil. 2017 Aug;39(17):1729-1737. doi: 10.1080/09638288.2016.1207111. Chapter 6: Kleynen M, Beurskens A, Olijve H, Kamphuis J, Braun S. Application of motor learning in neurorehabilitation: a framework for health-care professionals. Physiother Theory Pract. 2018 Jun 19:1-20. doi: 10.1080/09593985.2018.1483987 Chapter 7: Kleynen M, Wilson MR, Jie LJ, te Lintel Hekkert F, Goodwin VA, Braun SM. Exploring the utility of analogies in motor learning after stroke: a feasibility study. Int J Rehabil Res. 2014 Sep;37(3):277-80. doi: 10.1097/MRR.0000000000000058. Chapter 8: Kleynen M, Jie LJ, Theunissen K, Rasquin SM, Masters RS, Meijer K, Beurskens AJ, Braun SM. The immediate influence of implicit motor learning strategies on spatiotemporal gait parameters in stroke patients: a randomized within-subjects design. Clin Rehabil. 2019 Apr;33(4):619-630. doi: 10.1177/0269215518816359.
DOCUMENT
Cliënten met een CVA (cerebrovascular accident of beroerte) hebben verschillende voorkeuren m.b.t. de training van arm-hand vaardigheden (AHV). Adelante heeft de laatste jaren effectieve behandelconcepten voor deze training ontwikkeld die op de laatste inzichten omtrent neurorevalidatie en motorisch leren zijn gebaseerd. Door de korte revalidatieduur blijft de training vaak beperkt tot een gering aantal AHV, wat tot een suboptimale uitkomst leidt. Ergo- en fysiotherapeuten van Adelante willen cliënten vaker, intensiever en in meer realistische omgevingen laten trainen. Belangrijk is dat cliënten veilig zelfstandig kunnen oefenen en van feedback voorzien worden en dat de inhoud van de training t.o.v. huidige programma’s verrijkt wordt. Een nieuw revalidatieprotocol voor immersive Virtual Reality (VR)-ondersteunde AHV training zou hiervoor een oplossingsrichting kunnen zijn, maar er bestaan nog geen commercieel verkrijgbare producten die aan de eisen van professionals en cliënten voldoen. De ergo- en fysiotherapeuten verwachten dat de toepassing van VR binnen een AHV training efficiënter is, tot snellere en betere resultaten (o.a. door betere generaliseerbaarheid/ een betere transfer), en tot lagere behandelkosten leidt. De toevoeging van immersieve virtuele omgevingen die zo (gepersonaliseerd) aanpasbaar zijn dat de cliënt zoveel mogelijk en zelfstandig in de eigen leefomgeving kan oefenen en feedback krijgt, is innovatief voor de revalidatie. Om deze innovatie te kunnen realiseren, wordt in het beoogde project de volgende onderzoeksvraag beantwoord: “Hoe dient een immersieve VR-applicatie vormgegeven te worden om revalidanten met een CVA zo optimaal mogelijk te ondersteunen bij het trainen van AHV?” Het uitgangspunt hierbij is Design Thinking. In vijf fases (Empathising, Defining, Ideating, Prototyping en Testing, met diverse iteraties) worden in co-creatie met alle stakeholders immersieve virtuele omgevingen en geschikte hardware/ interfaces voor toepassing in AHV training ontwikkeld en inzicht verkregen in de meerwaarde, hanteerbaarheid en implementatie van VR bij revalidanten met problemen op het gebied van AHV als gevolg van een CVA.