Ear-worn body sensor network device: an objective tool for functional postoperative home recovery monitoring

Abstract

Patients' functional recovery at home following surgery may be evaluated by monitoring their activities of daily living. Existing tools for assessing these activities are labor-intensive to administer and rely heavily on recall. This study describes the use of a wireless ear-worn activity recognition sensor to monitor postoperative activity levels continuously using a Bayesian activity classification framework. The device was used to monitor the postoperative recovery of five patients following abdominal surgery. Activity was classified into four groups ranging from very low (level 0) to high (level 3). Overall, patients were found to be undertaking a higher proportion of level 0 activities on postoperative day 1 which was gradually replaced by higher-level activities over the next 3 days. This study demonstrates how a pervasive healthcare technology can objectively monitor functional recovery in the unsupervised home setting. This may be a useful adjunct to existing postoperative monitoring systems.

Effect of acute exacerbations on skeletal muscle strength and physical activity in cystic fibrosis

“…The e-AR sensor has been used for energy expenditure prediction [21], activity recognition [22] and for postoperative activity monitoring [23].…”

Introduction

“…These include direct sensing targets as illustrated in Table 1.2, as well as surrogate signs that can be used to indicate the onset of potential postsurgical complications. The ear-worn activity recognition (e-AR) sensor developed by Imperial College London and Sensixa, for example, has been used to quantify post-operative home recovery through activity indices and physiology monitoring systems [28]. Similarly an implantable sensor has been used to monitor the pressure in the aneurysm sac following endovascular stenting [29].…”

SmartFABER: Recognizing fine-grained abnormal behaviors for early detection of mild cognitive impairment

“…Several techniques were proposed to recognize simple activities, which rely on data acquired from body-worn sensors and on the application of supervised learning methods [7,8]. Early attempts in this sense were mainly based on the use of data acquired from multiple body-worn accelerometers [9], possibly coupled with biometrical sensors and integrated in clothes [10], to recognize locomotion types and simple physical activities.…”