We aimed to identify activity limitations and participation restrictions encountered by children and youth with disabilities for which assistive products and technology could be helpful. We used a convergent, parallel, mixed-methods design involving a nationwide, French survey composed of closed questions (quantitative) and open questions (qualitative) that enlightened the quantitative data. A total of 1055 responses were received, and 962 included: 92 from children and youth with disabilities, 493 from relatives and 377 from professionals. Difficulties frequently checked and described in detail were participation in recreational activities, leaving the house and traveling, participating in a group, and getting ready. Transversal explanations for difficulties were spontaneously provided (e.g., lack of accessibility and mobility). Solutions proposed included personal assistive devices to facilitate home life, high-tech devices, devices to compensate for impaired body functions, and adaptation of the familiar environment and daily activities. Few public solutions were proposed. The necessity of human assistance was emphasized. The mixed-methods design and involvement of different stakeholders identified common, macroscopic trends in difficulties encountered and desired solutions. Products and technology are required in the following domains: the familiar environment, accessibility and mobility, sports and leisure, high-technology, and family support. We provide suggestions to facilitate the development of innovative solutions.

Gait abnormalities are frequent in children and can be caused by different pathologies, such as cerebral palsy, neuromuscular disease, toe walker syndrome, etc. Analysis of the "gait pattern" (i.e., the way the person walks) using 3D analysis provides highly relevant clinical information. This information is used to guide therapeutic choices; however, it is underused in diagnostic processes, probably because of the lack of standardization of data collection methods. Therefore, 3D gait analysis is currently used as an assessment rather than a diagnostic tool. In this work, we aimed to determine if deep learning could be combined with 3D gait analysis data to diagnose gait disorders in children. We tested the diagnostic accuracy of deep learning methods combined with 3D gait analysis data from 371 children (148 with unilateral cerebral palsy, 60 with neuromuscular disease, 19 toe walkers, 60 with bilateral cerebral palsy, 25 stroke, and 59 typically developing children), with a total of 6400 gait cycles. We evaluated the accuracy, sensitivity, specificity, F1 score, Area Under the Curve (AUC) score, and confusion matrix of the predictions by ResNet, LSTM, and InceptionTime deep learning architectures for time series data. The deep learning-based models had good to excellent diagnostic accuracy (ranging from 0.77 to 0.99) for discrimination between healthy and pathological gait, discrimination between different etiologies of pathological gait (binary and multi-classification); and determining stroke onset time. LSTM performed best overall. This study revealed that the gait pattern contains specific, pathology-related information. These results open the way for an extension of 3D gait analysis from evaluation to diagnosis. Furthermore, the method we propose is a data-driven diagnostic model that can be trained and used without human intervention or expert knowledge. Furthermore, the method could be used to distinguish gait-related pathologies and their onset times beyond those studied in this research.

Article: Digital technologies for pediatric rehabilitation: current access and use in the European Rehatech4child survey - European Journal of Physical and Rehabilitation Medicine 2024 Oct 10 - Minerva Medica - Journals

Technical solutions could facilitate activities and participation in individuals with disabilities. For the development of solutions, hackathons are a method of interdisciplinary collaboration. For...

Background: Digital technologies for rehabilitation (DT4R), such as robotics and treadmill systems (RobTS), virtual reality and active video gaming (VR-AVG), and telehealth and apps (T&Apps), are promising tools for pediatric motor rehabilitation. Identifying acceptance factors is essential for effective clinical adoption. Objective: This study aimed to analyze the use of 3 different technologies for rehabilitation—RobTS, VR-AVG, and T&Apps—through a causal model based on the Unified Theory of Acceptance and Use of Technology (UTAUT). Methods: This study was part of RehaTech4child, a cross-sectional survey (2022) supported by the European Academy of Childhood-onset Disability, aimed at professionals working in pediatric motor rehabilitation across Europe. It assessed DT4R use, intention to use, and UTAUT concepts (performance expectancy, effort expectancy, social influence, and barriers). Structural equation modeling was performed to analyze the data and understand relationships between observed and latent variables. Results: A total of 1397 responses were received, and 635 fulfilled the eligibility criteria. The fitness indices suggested a satisfactory fit between the data and the model. The model explained 67% of the variance in the use of RobTS, 62% in VR-AVG, and 57% in T&Apps. Among all studied determinants, access had the strongest impact on use for all 3 categories of DT4R (RobTS: β=0.78, VR-AVG: β=0.73, and T&Apps: β=0.70; P <.001). Intention to use significantly impacted use behavior for all technologies; it was the second determinant after access for VR-AVG (β=0.18, P <.001) and T&Apps (β=0.21, P <.001), with a lower weight for RobTS (β=0.06, P=.007; P <.001). In the subgroup analysis of respondents reporting easy access, intention to use was the strongest determinant of use. The model explained 61% of the variance in intention to use for RobTS, 67% for VR-AVG, and 68% for T&Apps. Performance expectancy had the strongest effect on intention to use for the 3 technologies (RobTS: β=0.81, VR-AVG: β=0.84, and T&Apps: β=0.90; P <.001). For this concept, the items with the highest weights were significantly related to the effectiveness of DT4R on rehabilitation. Social influence and effort expectancy had a slight impact on intention to use. Conclusions: These results underscore the need to ensure easy access as a prerequisite for assessing relevant determinants of acceptance. Developing the evidence base for DT4R effectiveness and ensuring the availability of existing evidence may facilitate DT4R implementation. In our study, within the framework of the UTAUT model, no acceptance barrier was linked to the use of DT4R with children. Gathering families’ views may be useful for the implementation of RobTS. T&Apps may be useful for involving parents in their child’s rehabilitation. Further studies should focus on children’s and families’ points of view.

Background: A 2019 French national online survey explored activity limitations and participation restrictions among children and youth with disabilities for which innovative solutions could help. Objective: The primary aim of this study was to use text mining analysis to complement previous human-led qualitative research and to uncover actionable additional knowledge related to difficult life situations that innovative solutions could help address and to compare the perspectives of children and youth with disabilities, relatives, and professionals. Methods: This study was part of Innovation for Participation , a cross-sectional online survey, including (1) closed questions about sociodemographic characteristics, (2) closed questions about life situations that induced difficulties, and (3) open questions to explore these situations in greater depth. This study used a text mining approach designed for French data to analyze answers to open-ended questions about difficulties and desired innovative solutions. The analysis process included (1) data cleansing; (2) computing and analyzing the word frequency in the answers and their cooccurrence; (3) clustering answers using K-means algorithms; (4) analyzing the cluster words to define a title for each one and identify answers that are consistent with cluster titles, thereafter defined as well-classified; and (5) evaluating internal consistency defined as the ratio of well-classified answers to the total number of answers. Results: In total, 1055 responses were received, and 962 (91.2%) were included, representing 2018 open-ended answers to questions about difficult life situations for which innovative solutions could be useful. Frequency analysis highlighted the desire for action and autonomy by children and youth with disabilities and their relatives (“do” in first position, closely followed by “by themselves” in third position). “Disability” was frequently used by professionals (third position) but did not figure among the 20 most frequently used terms by other respondents. Cooccurrences with “do” revealed a deep interest in “doing sports.” Answers were gathered into 14 clusters, ranging in size from 9 to 681 answers; 5 underwent a second clustering step. Internal consistency ranged from 42% to 100%. Finally, 8 clusters were related to the difficulties linked to a desire for autonomy, and 4 highlighted difficulties related to actions within a group or community. Some clusters reinforced domains that emerged in the human-led analysis. Conclusions: Analysis of 2018 open-ended answers using a text mining approach designed for French data revealed that solutions are required to facilitate autonomy and the ability to “do it by myself (or themselves),” as well as integration into group and community life. Complementary to previous human-led analysis, the results reinforced the need for solutions to facilitate mobility, transport, and sports. They additionally highlighted differences in vocabulary used between the 3 respondent groups, suggesting that professionals may need to consider the language they use when communicating with individuals and relatives.