Context-Aware System Design for Remote Health Monitoring: An Application to Continuous Edema Assessment
Abstract:
Designing remote health monitoring systems requires a multi-faceted perspective that takes into account requirements and contexts imposed by the medical application, technology and end-user. We study such a design perspective in the context of remote and real-time edema monitoring. Edema (accumulation of fluid in certain soft-tissues) is regarded as one of the most important symptoms for systematic diseases such as heart failure. Monitoring edema allows patients and caregivers to understand the state of sickness and effectiveness of the treatments. This article proposes a novel low-power context-aware and real-time wearable platform capable of continuous assessment of ankle edema in remote settings. Our system keeps track of changes in subject’s ankle circumference as well as current body posture. Examination of our system with 15 subjects demonstrates the effectiveness and reliability of the proposed force-sensitive-resistor-based edema sensor (with an R2 of 0:87 for our regression model and intraclass correlation of 0:97) as well as an over 96% accuracy in activity monitoring that provide the means to perform reliable data validation on ankle circumference measurements in a continuous manner. Furthermore, we devise a novel derivative-free power optimization approach to maximize the battery lifetime resulting in improvement in battery lifetime by a factor of 2:13.
Existing System:
Wearable embedded systems are a the fastest growing areas of cyber-physical systems. Wearables consist of various components such as sensors, processing unit, wireless transmitter and battery. However, most components of wearables are particularly designed for mobile phones [9]. Wearable systems, compared to mobile phones, are subject to aggressive form factor scaling. Smaller system means smaller battery and shortened battery lifetime. As a result, a several challenges facing wearable systems the energy consumption dominates. Various power saving approaches such as dynamic voltage scaling, optimal feature selection, power gating and frequency scaling have been utilized to overcome this challenge [10], [11], [12]. A novel derivate-free optimization approach, namely coordinate search, is presented. Coordinate search performs jointoptimization of sampling frequency and feature selection to efficiently minimize the sensing and computation costs and hence provide prolonged functionality per single charge. To the best of our knowledge such optimization approach has not been used in prior studies on wearable embedded systems.
Proposed System:
The challenge of identifying the right location for monitoring peripheral edema has been studied in clinical domain in the past. While it is feasible to conduct edema monitoring on various lower limb locations, picking the right location that can most effectively measure the changes in edema level is essential. According to recent studies, the medical community has unanimously agreed that the best representative for peripheral edema is ankle. In [2], the authors have investigated the dependability and practicability of eight peripheral edema measurement methods. After comparing each method with the classic clinical assessment, they concluded that ankle circumference measurement is almost a perfect inter-examiner and intra-examiner agreement in assessment of peripheral edema. More prior studies have demonstrated the validity of using circumference measurement as a means for lower limb edema estimation [53], [54]. While water displacement method [55] is considered as the gold standard method for measuring changes in lower limb edema [56], circumference-based measurement offers a much more rapid and convenient way of measuring changes in peripheral edema. Therefore, we aim to develop a wearable sensor platform which can contentiously and reliably monitor ankle circumference as a direct indicator of peripheral edema.
Conclusion:
In this study, a low-power context-aware edema monitoring platform, was proposed. Our multi-perspective design principles aimed to affectively address the medically related concerns and needs. We used an advanced architecture that considers the usability factor by emphasizing on wearablility, small form-factor, and prolonged operating cycle. We built a prototype of our wearable sensing platform that is capable of (1) continuous monitoring of ankle circumference changes in edema patients and their associated body posture and daily activity level; and (2) performing optimized data sensing and processing in order to promote long lasting functionality. The potential use of remote health monitoring in patients with ankle edema has remained unexplored. Outdated methods have resulted in poor intervention rates leading to frequent hospitalization which can cause financial burden on the health-care system and patients. The proposed platform will significantly reduce the burden of in clinic assessments and provide the essentials for more effective interventions which further reduce the hospitalization rates associated with worsened medical conditions.
References:
[1] G. Acampora, D. J. Cook, P. Rashidi, and A. V. Vasilakos, “A survey on ambient intelligence in healthcare,” Proceedings of the IEEE, vol. 101, no. 12, pp. 2470–2494, Dec 2013.
[2] K. G. Brodovicz, K. McNaughton, N. Uemura, G. Meininger, C. J. Girman, and S. H. Yale, “Reliability and feasibility of methods to quantitatively assess peripheral edema,” Clinical medicine & research, vol. 7, no. 1-2, pp. 21–31, 2009.
[3] K. P. Trayes, J. S. Studdiford, S. Pickle, and A. S. Tully, “Edema: diagnosis and management.” American family physician, vol. 88, no. 2, pp. 102–110, 2013.
[4] W. P. Gorman, K. R. Davis, R. Donnelly et al., “Swollen lower limb?1: General assessment and deep vein thrombosis,” BMJ, vol. 320, no. 7247, pp. 1453–1456, 2000.
[5] J. Navas and M. Martinez-Maldonado, “Pathophysiology of edema in congestive heart failure.” Heart disease and stroke: a journal for primary care physicians, vol. 2, no. 4, pp. 325–329, 1992.
[6] T. Kawano, S. Nishida, and M. Hashimoto, “Development of measuring device for lower leg swelling using a strain gauge,” JSME International Journal Series C, vol. 48, no. 4, pp. 592–597, 2005.
[7] R. L. Gause, “Conductive elastomeric extensometer,” 1974, uS Patent 3,820,529.
[8] J. A. Healey, “Method and apparatus for measuring lower extremity volume,” Feb. 3 2009, uS Patent 7,484,408.
[9] J. Williamson, Q. Liu, F. Lu, W. Mohrman, K. Li, R. , and L. Shang, “Data sensing and analysis: Challenges for wearables,” in Design Automation Conference (ASP-DAC), 2015 20th Asia and South Pacific. IEEE, 2015, pp. 136–141.
[10] J. Pouwelse, K. Langendoen, and H. Sips, “Dynamic voltage scaling on a low-power microprocessor,” in Proceedings of the 7th annual international conference on Mobile computing and networking. ACM, 2001, pp. 251–259.