The Conceptual MADE Framework for Pervasive and Knowledge-Based Decision Support in Telemedicine

The Conceptual MADE Framework for Pervasive and Knowledge-Based Decision Support in Telemedicine

Nick L. S. Fung (University of Twente, Enschede, Netherlands), Valerie M. Jones (University of Twente, Enschede, Netherlands), Ing Widya (University of Twente, Enschede, Netherlands), Tom H. F. Broens (Academic Medical Center, Amsterdam, Netherlands), Nekane Larburu (University of Twente, Enschede, Netherlands), Richard G. A. Bults (University of Twente, Enschede, Netherlands), Erez Shalom (Ben-Gurion University of the Negev, Beer-Sheva, Israel) and Hermie J. Hermens (Roessingh Research and Development, Enschede, Netherlands)
Copyright: © 2016 |Pages: 15
DOI: 10.4018/IJKSS.2016010102
OnDemand PDF Download:
No Current Special Offers


Telemedicine systems are inherently distributed, but, especially in the context of the Internet-of-Things, their complete physical configuration may only be determined after design time by considering, for example, the individual patient's needs. Therefore, to enable pervasive and knowledge-based decision support to be provided in telemedicine, a conceptual framework was developed for modelling and executing clinical knowledge as networks of four types of concurrent processes: Monitoring (M), Analysis (A), Decision (D) and Effectuation (E). In this way, the required decision support functionality can, as presented in this article, be distributed at run-time by mapping different portions of the knowledge across the devices constituting the system. This MADE framework was applied to model a clinical guideline for gestational diabetes mellitus and to derive a prototype knowledge-based system that executes the resulting MADE network. Thus it is shown to support the full development trajectory of a telemedicine system, including analysis, design and implementation.
Article Preview


Telemedicine services are widely regarded as offering huge opportunities for supporting patient empowerment and patient self-management, enabling the control of the disease management process to be placed close to the patient. At the same time, it is well recognised within the medical community that the adoption of clinical practice guidelines, which document the current best clinical practice as supported by the latest scientific evidence, can improve and ensure the quality of patient care by facilitating adherence to proven best practice (Isern & Moreno, 2008). Therefore, as part of the European project MobiGuide (, which aims to provide knowledge-based decision support to patients whenever necessary, we currently apply body area networks not only for telemonitoring, but also for providing pervasive decision support to patients based on the best available clinical knowledge derived from clinical guidelines.

Since the early days of knowledge-based systems (van Melle, 1979), it has been recognised that separation of concerns—relating to knowledge and the reasoning mechanisms that are applied to knowledge and data—brings the advantage of genericity and enables a plug-and-play approach to knowledge bases. However, for telemedicine applications, device-independence is an equally important property to achieve genericity, since due to different patient preferences and clinical requirements, it may not be known at design time which exact combination of physical devices is most appropriate for each patient. One patient may, for example, require a sensor for monitoring heart rate and prefer to interact with a smartphone whilst another patient may require a blood glucose monitor and only have access to a public desktop computer.

To address the device-dependence problem, one possible approach is to allocate all the required reasoning processes to the back-end infrastructures that can be fixed during design time. However, the limitations of wireless communication in terms of patchy or complete absence of mobile coverage imply that some processing must be performed at the front-end close to the patient in order to assure continuity of real-time and pervasive decision support. Indeed, with the continued development and increasing prevalence of front-end devices such as smartphones and smartwatches, we have the prospect of a large number of possibilities to provide real-time and ubiquitous decision support to the patient by distributing the required knowledge-based decision support functionality across the available physical devices in an opportunistic way.

Therefore, to enable this distribution, we have developed the MADE conceptual framework for modelling and executing clinical knowledge as directed networks of concurrent processes. As presented previously by Fung et al. (2014b) and further elaborated here, each process corresponds to a separable portion of the available knowledge and represents a stateful operation which can be executed in parallel with other processes. In this way, the distribution of decision support functionality can be achieved under this framework by distributing the knowledge corresponding to each process across the available devices. Furthermore, given the direct procedural interpretation of clinical knowledge, the MADE framework also facilitates the design of a corresponding mechanism to execute the distributed knowledge.

In the next section, we present the relevant background including the state-of-the-art in modelling clinical knowledge and the disease management process in general, and this is followed by a description of our proposed MADE framework in the third section. The fourth section introduces the MobiGuide project, within which our research on the proposed framework was performed, and describes how the framework was applied in the case of the MobiGuide project to analyse a clinical guideline for women who develop diabetes during pregnancy and to design a knowledge-based system that can execute clinical knowledge as a network of concurrent processes. In the fifth section we present discussion and plans for future work, followed by conclusions in the last section.

Complete Article List

Search this Journal:
Volume 13: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing