Measuring functional hand use in children with unilateral cerebral palsy using accelerometry and machine learning.

AIM: To investigate wearable sensors for measuring functional hand use in children with unilateral cerebral palsy (CP). METHOD: Dual wrist-worn accelerometry data were collected from three females and seven males with unilateral CP (mean age = 10 years 2 months [SD 3 years]) while performing hand tasks during video-recorded play sessions. Video observers labelled instances of functional and non-functional hand use. Machine learning was compared to the conventional activity count approach for identifying unilateral hand movements as functional or non-functional. Correlation and agreement analyses compared the functional usage metrics derived from each method. RESULTS: The best-performing machine learning approach had high precision and recall when trained on an individual basis (F1 = 0.896 [SD 0.043]). On an individual basis, the best-performing classifier showed a significant correlation (r = 0.990, p < 0.001) and strong agreement (bias = 0.57%, 95% confidence interval = -4.98 to 6.13) with video observations. When validated in a leave-one-subject-out scenario, performance decreased significantly (F1 = 0.584 [SD 0.076]). The activity count approach failed to detect significant differences in non-functional or functional hand activity and showed no significant correlation or agreement with the video observations. INTERPRETATION: With further development, wearable accelerometry combined with machine learning may enable quantitative monitoring of everyday functional hand use in children with unilateral CP.

Evaluating the impact of movement tracking feedback on engagement with home exercise programmes of children with cerebral palsy using a new therapy app: a protocol for a mixed-methods single-case experimental design with alternating treatments.

INTRODUCTION: Children with cerebral palsy (CP) are prescribed home exercise programmes (HEPs) to increase the frequency of movement practice, yet adherence to HEPs can be low. This paper outlines the protocol for a single-case experimental design (SCED) with alternating treatments, using a new home therapy exercise application, Bootle Boot Camp (BBCamp), offered with and without movement tracking feedback. This study will explore the impact of feedback on engagement, movement quality, lower limb function and family experiences to help understand how technology-supported HEPs should be translated and the added value, if any, of movement tracking technology. METHODS AND ANALYSIS: In this explanatory sequential mixed-methods study using a SCED, 16 children with CP (aged 6-12 years, Gross Motor Function Classification System levels I-II) will set lower limb goals and be prescribed an individualised HEP by their physiotherapist to complete using BBCamp on their home television equipped with a three-dimensional camera-computer system. Children will complete four weekly exercise sessions over 6 weeks. Children will be randomised to 1 of 16 alternating treatment schedules where BBCamp will provide or withhold feedback during the first 4 weeks. The version of BBCamp that results in the most therapeutic benefit will be continued for 2 final weeks. Goals will be re-evaluated and families interviewed. The primary outcome is adherence (proportion of prescribed exercise repetitions attempted) as a measure of behavioural engagement. Secondary outcomes are affective and cognitive engagement (smiley face ratings), exercise fidelity, lower limb function, goal achievement and participant experiences. SCED data will be analysed using visual and statistical methods. Quantitative and qualitative data will be integrated using joint displays. ETHICS AND DISSEMINATION: Ethical approval was obtained from the Research Ethics Boards at Bloorview Research Institute and the University of Toronto. Results will be distributed through peer-reviewed journals and scientific conferences. TRIAL REGISTRATION NUMBER: NCT05998239; pre-results.

Clinician perspectives on the implementation of inpatient cycling-based exergames for children with cerebral palsy: A qualitative study.

OBJECTIVE: To understand the perspectives of key stakeholder clinicians in implementing inpatient cycling-based exergames for children with cerebral palsy (CP) into pediatric rehabilitation. METHODS: Sixteen clinicians (nurses, physiotherapists, recreational therapists) that participated in a study exploring the feasibility of implementing cycling-based exergames for inpatient children with CP were interviewed. Clinicians' responses were coded using the Theoretical Domains Framework (TDF). Beliefs were generated from each response and relevant domains were identified. RESULTS: Ten domains from the TDF were identified as relevant. Key enablers to clinician participation in future implementation included revision of clinician roles and responsibilities, the belief that children with CP will benefit from exergames, and the belief in potential applicability to other pediatric populations. Barriers included clinician limited time and exergame responsibilities not aligning with perceived clinician roles. CONCLUSIONS: This study identifies key barriers and enablers that future inpatient pediatric rehabilitation settings should consider when incorporating exergames into rehabilitation practice.