Wearable sensors for gait pattern examination in glaucoma patients

This paper presents a wearable wireless sensor system designed for real-time gait pattern analysis in glaucoma patients. Many clinical studies have reported that glaucoma patients experienced mobility issues such as walking slowly and bumping into obstacles frequently. The gait attributes of glaucoma patients, however, have not been studied in the literature. We design and develop a shoe-integrated sensing system for objective bio-information collection, utilize signal processing algorithms for feature estimation and leverage machine learning as well as statistical analysis approaches for gait pattern examination. The developed sensor platform is utilized in a randomized clinical trial conducted at UCLA Stein Eye Institute with 19 participants. Our trial involved both glaucoma patients and age-matched healthy participants performing a series of gait tests. With the captured sensor data, we develop signal processing and machine learning algorithms to provide a quantitative comparison between gait characteristics in older adults with and without glaucoma. Our results demonstrate that machine learning algorithms achieve an accuracy of over 80% in distinguishing extracted gait features of those with glaucoma from healthy individuals. Our results also demonstrate significant difference between two groups based on extracted gait features. In particular, several features are highly discriminative with a p-value of less than1×10−10.