Gait Environment Recognition Using Biomechanical and Physiological Signals with Feed-Forward Neural Network: A Pilot Study.

Gait, the fundamental form of human locomotion, occurs across diverse environments. The technology for recognizing environmental changes during walking is crucial for preventing falls and controlling wearable robots. This study collected gait data on level ground (LG), ramps, and stairs using a feed-forward neural network (FFNN) to classify the corresponding gait environments.

Effects of community ambulation training with 3D-printed ankle-foot orthosis on gait and functional improvements: a case series of three stroke survivors.

Introduction: Many of the patients using ankle-foot orthoses (AFOs) experience poor fit, pain, discomfort, dislike of the aesthetics of the device, and excessive range of motion restrictions, which diminish the use of AFOs. Although 3D-printed ankle-foot orthoses (3D-AFOs) affect patient satisfaction and overall gait functions such as ankle moment, joint range of motion (ROM), and temporal-spatial parameters, the material properties and manufacturing process of 3D-AFOs are still diverse; the clinical effects of community ambulation using 3D-AFOs and satisfaction in patients with stroke are poorly understood.

Case Description: Case 1: A 30-year-old man, with a history of right basal ganglia hemorrhage, presented with marked foot drop and genu recurvatum.

Bilateral ankle deformities affects gait kinematics in chronic stroke patients.

Objectives: Stroke patients suffer from ankle joint deformities due to spastic ankle muscles. This study evaluated the viability of using 3D scanned surface images of the feet of stroke victims to visually assess the deformities of a hemiparetic foot and investigated the influences of deformed ankle joints on gait kinematics.

Methods: A total of 30 subjects with stroke-induced hemiparesis and 11 age-matched healthy controls completed the clinical assessments.