Validity of Hololens Augmented Reality Head Mounted Display for Measuring Gait Parameters in Healthy Adults and Children with Cerebral Palsy.

Anne-Laure Guinet,Eric Desailly,Guillaume Bouyer,Samir Otmane

doi:10.3390/s21082697

Abstract

Serious games are a promising approach to improve gait rehabilitation for people with gait disorders. Combined with wearable augmented reality headset, serious games for gait rehabilitation in a clinical setting can be envisaged, allowing to evolve in a real environment and provide fun and feedback to enhance patient’s motivation. This requires a method to obtain accurate information on the spatiotemporal gait parameters of the playing patient. To this end, we propose a new algorithm called HoloStep that computes spatiotemporal gait parameters using only the head pose provided by an augmented reality headset (Hololens). It is based on the detection of peaks associated to initial contact event, and uses a combination of locking distance, locking time, peak amplitude detection with custom thresholds for children with CP. The performance of HoloStep was compared during a walking session at comfortable speed to Zeni’s reference algorithm, which is based on kinematics and a full 3D motion capture system. Our study included 62 children with cerebral palsy (CP), classified according to Gross Motor Function Classification System (GMFCS) between levels I and III, and 13 healthy participants (HP). Metrics such as sensitivity, specificity, accuracy and precision for step detection with HoloStep were above 96%. The Intra-Class Coefficient between steps length calculated with HoloStep and the reference was 0.92 (GMFCS I), 0.86 (GMFCS II/III) and 0.78 (HP). HoloStep demonstrated good performance when applied to a wide range of gait patterns, including children with CP using walking aids. Findings provide important insights for future gait intervention using augmented reality games for children with CP.

Highlights

Cerebral Palsy (CP) is the most common cause of childhood disability, affecting17 million people worldwide [1,2]
Using only the head pose recorded with a Hololens AR Head Mounted Display (HMD). It is based on the detection of peaks associated to initial contact event, and uses a combination of locking distance, locking time, peak amplitude detection with custom thresholds for children with CP
The results of our study suggest that HoloStep algorithm using Hololens AR HMD calculate spatiotemporal gait parameters with sufficient accuracy even in people with gait disorders using walking aids

Summary

Introduction

Cerebral Palsy (CP) is the most common cause of childhood disability, affecting17 million people worldwide [1,2]. Cerebral Palsy (CP) is the most common cause of childhood disability, affecting. CP describes a group of permanent disorders of the development of movement and posture, causing activity limitation, which are attributed to non-progressive disturbances that occurred in the developing fetal or infant brain [3]. The natural history in children with CP is a gradual decline in ambulatory function as children grow and age, in particular during adolescence [7,8]. To reverse this trend, physiotherapists propose overground or treadmill-based gait training, with varying body weight support [9].

Objectives

Methods

Results

Discussion

Conclusion