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.

What this paper adds: Wearable (wrist-worn) accelerometry with machine learning shows potential for measuring functional hand use in children with unilateral cerebral palsy. Traditional activity count accelerometry cannot distinguish functional from non-functional hand use.