Individualized learning-based ground reaction force estimation in people post-stroke using pressure insoles

Stroke is a leading cause of gait disability that leads to a loss of independence and overall quality of life. The field of clinical biomechanics aims to study how best to provide rehabilitation given an individual's impairments. However, there remains a disconnect between assessment tools used in biomechanical analysis and in clinics. In particular, 3-dimensional ground reaction forces (3D GRFs) are used to quantify key gait characteristics, but require lab-based equipment, such as force plates. Recent efforts have shown that wearable sensors, such as pressure insoles, can estimate GRFs in real-world environments. However, there is limited understanding of how these methods perform in people post-stroke, where gait is highly heterogeneous. Here, we evaluate three subjectspecific machine learning approaches to estimate 3D GRFs with pressure insoles in people post-stroke across varying speeds. We find that a Convolutional Neural Network-based approach achieves the lowest estimation errors of 0.75 +/- 0.24, 1.13 +/- 0.54, and 4.79 +/- 3.04 %bodyweight for the medio-lateral, anteroposterior, and vertical GRF components, respectively. Estimated force components were additionally strongly correlated with the ground truth measurements ( R2 > 0.85). Finally, we show high estimation accuracy for three clinically relevant point metrics on the paretic limb. These results suggest the potential for an individualized machine learning approach to translate to realworld clinical applications.