Harnessing Fast Fourier Transform for Rapid Community Travel Distance and Step Estimation in Children with Duchenne Muscular Dystrophy

Accurate estimation of gait characteristics, including step length, step velocity, and travel distance, is critical for assessing mobility in toddlers, children, and teens with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers. This study introduces a novel method leveraging Fast Fourier Transform (FFT)-derived step frequency from a single waist-worn consumer-grade accelerometer to predict gait parameters efficiently. The proposed FFT-based step frequency detection approach, combined with regression-derived stride length estimation, enables precise measurement of temporospatial gait features across various walking and running speeds. Our model, developed from a diverse cohort of children aged 3–16, demonstrated high accuracy in step length estimation (R2=0.92, RMSE=0.06 m) using only step frequency and height as inputs. Comparative analysis with ground-truth observations and AI-driven Walk4Me models validated the FFT-based method, showing strong agreement across step count, step frequency, step length, step velocity, and travel distance metrics. The results highlight the feasibility of using widely available mobile devices for gait assessment in real-world settings, offering a scalable solution for monitoring disease progression and mobility changes in individuals with DMD. Future work will focus on refining model performance and expanding applicability to additional movement disorders.