With an increasingly mobile society and the worldwide deployment of mobile and wireless networks, the wireless infrastructure can support many current and emerging healthcare applications. This could fulfill the vision of "Pervasive Healthcare" or healthcare to anyone, anytime, and anywhere by removing locational, time and other restraints while increasing both the coverage and the quality. In this paper, we present applications and requirements of pervasive healthcare, wireless networking solutions and several important research problems. The pervasive healthcare applications include pervasive health monitoring, intelligent emergency management system, pervasive health-care data access, and ubiquitous mobile telemedicine. One major application in pervasive healthcare, termed comprehensive health monitoring is presented in significant details using wireless networking solutions of wireless LANs, ad hoc wireless networks, and, cellular/GSM/3G infrastructure-oriented networks. Many interesting challenges of comprehensive wireless health monitoring, including context-awareness, reliability, and, autonomous and adaptable operation are also presented along with several high-level solutions. Several interesting research problems have been identified and presented for future research.

Pervasive healthcare and wireless health monitoring

Health care organizations are leveraging machine-learning techniques, such as artificial neural networks (ANN), to improve delivery of care at a reduced cost. Applications of ANN to diagnosis are well-known; however, ANN are increasingly used to inform health care management decisions. We provide a seminal review of the applications of ANN to health care organizational decision-making. We screened 3,397 articles from six databases with coverage of Health Administration, Computer Science and Business Administration. We extracted study characteristics, aim, methodology and context (including level of analysis) from 80 articles meeting inclusion criteria. Articles were published from 1997–2018 and originated from 24 countries, with a plurality of papers (26 articles) published by authors from the United States. Types of ANN used included ANN (36 articles), feed-forward networks (25 articles), or hybrid models (23 articles); reported accuracy varied from 50% to 100%. The majority of ANN informed decision-making at the micro level (61 articles), between patients and health care providers. Fewer ANN were deployed for intra-organizational (meso- level, 29 articles) and system, policy or inter-organizational (macro- level, 10 articles) decision-making. Our review identifies key characteristics and drivers for market uptake of ANN for health care organizational decision-making to guide further adoption of this technique.

/pdf/applications-of-artificial-neural-networks-in-health-care-2rhh6i1o0s.pdf

Applications of artificial neural networks in health care organizational decision-making: A scoping review

Wearable health-monitoring systems are becoming very popular, especially in enabling the noninvasive diagnosis of vital functions of the human body. Besides typical singular heartbeat or perspiration sensors, which have been commercially available in recent years, the deployment of a series of body-worn sensors can enable an effective health-monitoring mechanism. The combined information obtained from such systems can either be relayed directly to any health-monitoring personnel in the case of emergencies or can be logged and analyzed as a part of preventive health measures. However, the deployment of on-body nodes for humans must be performed with care, as they may interfere with the patients' regular movements. This is especially challenging because the relationship between the electromagnetic waves is influenced by the patient's movements, distance from the nearest base station, operating environment, etc. Additional challenges to the deployment of such mechanisms are also faced in situations where the nodes require additional on-body space, impose additional weight, or are not conformal enough to the patient's body. On the hardware design aspect, the sensory and communication functions on the electronic node have to be designed using special materials to avoid reliability issues or damage due to repeated or intense movements. Finally, and perhaps the most important aspect that needs to be addressed concerning such systems, is their electromagnetic safety level, which is defined by their specific absorption rates (SARs). This article aims to review the latest developments in body-worn wireless health-monitoring systems and their current challenges and limitations and to discuss future trends for such worn devices for these applications.

Wearable Wireless Health Monitoring: Current Developments, Challenges, and Future Trends

Healthcare costs in the US are approximately 15% of GNP and are anticipated to reach 17% of GNP in the near future. Management of chronic diseases via technology based ubiquitous patient monitoring services has been widely proposed as a viable option for economizing healthcare resources, and providing efficient, quality healthcare. The process of ubiquitous patient monitoring is information intensive, the information generated is not only fragmented but also spans multiple processes, artifacts, parameters, and decision criteria. The current study explores the complexities associated with the process of ubiquitous patient monitoring and the enabling technologies. The key contribution is a framework that captures the complex processes, the parameters involved, and the decision criteria for ubiquitous patient monitoring. The decision protocols and enabling technologies supporting the processes are detailed in the study along with the opportunities and challenges of ubiquitous patient monitoring. A conceptual model of ubiquitous patient monitoring is developed by leveraging the proposed framework and is validated by a usage scenario. Finally, the implications of future research and contributions of the current research are discussed.

Enabling ubiquitous patient monitoring: Model, decision protocols, opportunities and challenges

In this paper we describe the mobile health (m-health) system in the context of Internet of Things (IoT). We describe the fundamental characteristics of m-health devices such as compactness, IP connectivity, low-power consumption and security. We discuss acquisition of mobile health data via medical gadgets and wearables and application of this data in monitoring various health conditions such as blood sugar level, ECG, blood-pressure, asthma, etc. Security is very critical for IoT based m-health system. We address the issues of confidentiality, privacy, and security in the context of secure m-health system. We listed several measures to protect the information of patients and m-health system. The m-health system will benefit the patients in many ways such as quick diagnosis, remote monitoring and home rehabilitation. Overall m-health system will significantly reduces healthcare cost and unnecessary hospitalizations.

Mobile Health (m-Health) System in the Context of IoT

Telemedicine has significantly broaden its scope the last few years. In the 90's, it was mainly used by healthcare providers, regardless time and location, for second opinion and patient consultation. Today it elaborates solutions for remote health monitoring to support prevention, early diagnosis, disease management, treatment and home rehabilitation. Remote health monitoring could lead to a significant reduction of total cost in healthcare by avoiding unnecessary hospitalisations and ensuring that those who need urgent care get it sooner. Latest developments in micro- and nanotechnologies as well as in information processing and wireless communication offer, today, the possibility for smart miniaturisation and non-invasive biomedical measurement as well as for wearable sensing, processing and communication. Although developing specific systems and applications to address specific user needs, the "smart health wearable" research and industrial community faces a number of common critical issues, e.g. biomedical sensors, scenarios of use (linked to the business scenarios), data security and confidentiality, risk analysis, user interface, medical knowledge/decision support, dissemination, user acceptance and awareness, business models and exploitation. Beyond technology, which seems providing proof of concept, real future challenges such as clinical validation and impact assessment of the newly developed smart wearable applications, are ahead. This paper review the current status in research and development of smart wearable health applications, developed especially under the EU research activities and analyse the outstanding issues and future challenges to be achieved in the future.

A. Lymberis

Papers

Smart wearables for remote health monitoring, from prevention to rehabilitation: current R&D, future challenges