TELEMEDICINE AND E-HEALTH COMMUNICATION SYSTEMS SAPHIRE: intelligent healthcare monitoring based on semantic interoperability platform: pilot applications O. Nee, A. Hein, T. Gorath, N. Hu ¨ lsmann, G.B. Laleci, M. Yuksel, M. Olduz, I. Tasyurt, U. Orhan, A. Dogac, A. Fruntelata, S. Ghiorghe and R. Ludwig Abstract: As a response to the challenge of providing high-quality healthcare services with reason- able costs while the elderly population and the associated chronic diseases increase, SAPHIRE architecture provides an intelligent healthcare monitoring architecture. The monitoring of patients is achieved through a clinical decision support system based on clinical guidelines. SAPHIRE pro- vides the necessary interoperability layers to access the patient’s vital signs from wireless medical sensors and the electronic healthcare records of the patient in order to exploit them in the decision process seamlessly. This architecture is presented through two pilot applications: one for the bedside monitoring of cardiac patients at hospitals, and the other for homecare monitoring of the cardiac patients rehabilitated after a revascularisation therapy. 1 Introduction The World is facing the challenge of delivering high-quality healthcare at affordable cost while the greying population continues to grow at an increasing pace. According to the recent studies, the proportion of the population over 65 is expected to almost double from 16.4% in 2004 to 29.9% in 2050 in Europe [1]. Owing to aging population, chronic diseases and their management costs are also on the rise. The current healthcare delivery model is far from ideal to address the challenges ahead [2]. On the other hand, Information Technology combined with recent advances in networking, mobile communications and wireless medical sensor technologies offers great potential to support health- care professionals and to deliver remote healthcare services, hence providing the opportunities to improve efficiency and quality and better access to care at the point of need. In this paper, we will present SAPHIRE architecture that provides an intelligent healthcare monitoring platform. To be able to assist medical practitioners efficiently, the health- care monitoring platform is enriched with a clinical decision support system (CDSS) based on computerised clinical guidelines. Through the SAPHIRE system, the intelligent monitoring architecture is able to access seamlessly the medical history of a patient stored in medical information systems as well as the vital signs of the patients through wire- less medical sensors. In this way, not only the observations received from wireless medical sensors but also the patient medical history is used in the reasoning process. In the following we will present the basic features of the SAPHIRE architecture by emphasising how it is extending the state-of-the-art healthcare monitoring research: † The healthcare monitoring system needs to access the vital signs of the patients through wireless medical sensor devices. The SAPHIRE architecture provides a Sensor and Data Point abstraction in order to present seamlessly the sensor data to the applications exploiting it. Fig. 1 shows the data layers used in the SAPHIRE system. The bottom layer represents the actual sensor hardware. Above that, the networking layer is comprised of a Bluetooth stack and a TCP/IP stacks. The sensor driver layer implements the communication protocol that determines the sensor’s data structure and how it is transmitted through the network layer. If a new sensor is introduced to the system, the data point abstraction layer ensures that only the pro- prietary sensor driver needs to be adapted. A virtual device, as it can be seen in the layer above the datapoint abstraction, can – but does not necessarily have to – correspond to a physical device. A virtual device can also receive its data from an algorithm that derives data from other (possibly also virtual) devices. In the SAPHIRE context, an example for a virtual device without a hardware representation is the virtual device for the respiratory rate, where the respiratory rate is derived from the signals of a multi-lead ECG device [3]. Data from the virtual devices are stored in the database (where they are exposed as semantically enriched web service so that the CDSS can use it and where the alarm system can access it), exported as file (for the sensor data analysis software such as Cardionics). Also, the data can be published using the publish/subscribe mechanism of the Java message system (JMS) [4]. The real-time viewer (RTViewer) for Sensor data subscribes to the sensor data topics through JMS to display the data on the physicians’ display. † The healthcare monitoring system needs to access the electronic health records of the patient so that the vital signs of the patient can be put into context while giving rec- ommendations/decisions. However patients’ healthcare records are usually physically dispersed in disparate # The Institution of Engineering and Technology 2008 doi:10.1049/iet-com:20060699 Paper first received 26th December 2006 and in revised form 23rd April 2007 O. Nee, A. Hein, T. Gorath and N. Hu ¨lsmann are with OFFIS, Institute for Information Technology, Oldenburg, Germany G.B. Laleci, M. Yuksel, M. Olduz, I. Tasyurt, U. Orhan and A. Dogac are with Software Research and Development Center, Middle East Technical University (METU), Ankara 06531, Turkey A. Fruntelata and S. Ghiorghe are with The Internal Medicine and Cardiology Department of the Emergency Hospital of Bucharest, Bucharest, Romania Ralf Ludwig is with Schu ¨chtermann Klinik, Bad Rothenfelde, Germany E-mail: andreas.hein@offis.de IET Commun., 2008, 2, (2), pp. 192–201 192