Copyright (c) 2013 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI 10.1109/JBHI.2013.2286157, IEEE Journal of Biomedical and Health Informatics IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. X, NO. X, X 2013 1 Enabling Smart Personalized Healthcare: a Hybrid Mobile-Cloud Approach for ECG Telemonitoring Xiaoliang Wang, Qiong Gui, Bingwei Liu, Zhanpeng Jin, Member, IEEE, and Yu Chen, Member, IEEE Abstract—The severe challenges of the skyrocketing healthcare expenditure and the fast aging population highlight the needs for innovative solutions supporting more accurate, affordable, flexible, and personalized medical diagnosis and treatment. Re- cent advances of mobile technologies have made mobile devices a promising tool to manage patients’ own health status through services like telemedicine. However, the inherent limitations of mobile devices make them less effective in computation- or data- intensive tasks such as medical monitoring. In this study, we pro- pose a new hybrid mobile-cloud computational solution to enable more effective personalized medical monitoring. To demonstrate the efficacy and efficiency of the proposed approach, we present a case study of mobile-cloud based electrocardiograph (ECG) monitoring and analysis and develop a mobile-cloud prototype. The experimental results show that the proposed approach can significantly enhance the conventional mobile-based medical monitoring in terms of diagnostic accuracy, execution efficiency and energy efficiency, and holds the potential in addressing future large-scale data analysis in personalized healthcare. Index Terms—Telemedicine, mobile, cloud, medical monitor- ing, electrocardiograph. I. I NTRODUCTION A CCORDING to the World Health Organization (WHO) [1], the United States spends about 17.6% of its gross domestic product (GDP) on healthcare, the highest level in the world and far higher than the percentage for other devel- oped countries (9.3% on average). Nevertheless, the use of healthcare services in the U.S. is far below that of comparable countries [2], reflecting greater inefficiency and higher prices for healthcare services in the United States. The skyrocketing medical expenditures and continuous aging of the world’s population demand transformative technological innovations to provide more effective and affordable healthcare services, available to anyone at any time and in any place [3]. A critical and costly part of current healthcare systems is the monitoring of patients’ vital signs and other physiological signals, all of which play significant roles in physicians’ diagnostic processes. Modern inpatient and outpatient facil- ities can provide a high level of protection to clinically ill patients, through a set of resting, bedside medical monitoring equipment. However, less attention has been paid to long- term, off-site or in-home care that is believed to be one of the Manuscript received April 30, 2013; revised August 15, 2013; accepted October 7, 2013. Asterisk indicates corresponding author. X. Wang, Q. Gui, B. Liu, and Y. Chen are with the Department of Elec- trical and Computer Engineering, Binghamton University, State University of New York, Binghamton, NY, 13902 USA e-mail: {xwang90, bliu11, qgui1, ychen}@binghamton.edu. *Z. Jin is with the Departments of Electrical and Computer Engineering, and Bioengineering, Binghamton University, State University of New York, Binghamton, NY, 13902 USA e-mail: zjin@binghamton.edu. Cloud Computing Remote clinic Hospital Patient Physician Medical Equipment Home Ambulance Personal Desktop Personal Laptop Hospital Server Smartphone Tablet Video Conferencing Fig. 1. Diverse telemedicine applications based on the cloud. most effective ways for addressing increasingly severe chronic diseases [4]. The highly specialized and extremely expensive medical monitoring equipment found in hospitals is neither easily accessible nor affordable for those scenarios. Recent advances in wireless body sensors and mobile technologies have promoted the use of mobile-based health monitoring and alert systems (usually referred as “mHealth”). Such systems aim at providing real-time feedback about an individuals health condition, while alerting in case of health- threatening conditions. In the United States, it is reported that 88 percent of adults are cellphone owners [5], and the number of smartphone users is expected to be approximately 200 million by 2016 [6]. The increasing popularity of mobile devices can forge new opportunities towards the grand vision of “pervasive healthcare” [7]. Recently, many mobile-based medical monitoring devices have been developed with the capability of processing a wide variety of classes of phys- iological signals [8][9]. However, the limited computational power, storage space, and battery life of existing mobile devices, significantly limit their ability to execute resource- intensive applications [10]. Recently, the fast-growing cloud computing technology has led to a novel computing paradigm, called mobile cloud computing (MCC), which allows users an online access to unlimited computing power and storage space. This paradigm not only enables users to enjoy convenient, versatile, and efficient computing services, but also raises the possibility of providing more accurate off-site personalized medical diagnosis and treatment, as shown in Figure 1.