Article

Home Care Decision Support Using an Arden Engine - Merging Smart Home and Vital Signs Data

Peter L. Reichertz Institute for Medical Informatics, University of Braunschweig - Institute of Technology and Hannover Medical School, Germany.
Studies in health technology and informatics 02/2009; 146:483-7. DOI: 10.3233/978-1-60750-024-7-483
Source: PubMed

ABSTRACT The demographic change with a rising proportion of very old people and diminishing resources leads to an intensification of the use of telemedicine and home care concepts. To provide individualized decision support, data from different sources, e.g. vital signs sensors and home environmental sensors, need to be combined and analyzed together. Furthermore, a standardized decision support approach is necessary.
The aim of our research work is to present a laboratory prototype home care architecture that integrates data from different sources and uses a decision support system based on the HL7 standard Arden Syntax for Medical Logical Modules.
Data from environmental sensors connected to a home bus system are stored in a data base along with data from wireless medical sensors. All data are analyzed using an Arden engine with the medical knowledge represented in Medical Logic Modules.
Multi-modal data from four different sensors in the home environment are stored in a single data base and are analyzed using an HL7 standard conformant decision support system.
Individualized home care decision support must be based on all data available, including context data from smart home systems and medical data from electronic health records. Our prototype implementation shows the feasibility of using an Arden engine for decision support in a home setting. Our future work will include the utilization of medical background knowledge for individualized decision support, as there is no one-size-fits-all knowledge base in medicine.

1 Follower
 · 
186 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Objectives: In this paper, we present a prototype of a Home-Centered Health-Enabling Technology (HET-HC), which is able to capture, store, merge and process data from various sensor systems at people's home. In addition, we present an architecture designed to integrate HET-HC into an exemplary regional Health Information System (rHIS). Methods: rHIS are traditionally document-based to fit to the needs in a clinical context. However, HET-HC are producing continuous data streams for which documents might be an inappropriate representation. Therefore, the HET-HC could register placeholder-documents at rHIS. These placeholder-documents are assembled upon user-authenticated request by the HET-HC and are always up-to-date. Moreover, it is not trivial to find a clinical coding system for continuous sensor data and to make the data machine-readable in order to enhance the interoperability of such systems. Therefore, we propose the use of SNOCAP-HET, which is a nomenclature to describe the context of sensor-based measurements in health-enabling technologies. Results: We present an architectural approach to integrate HET-HC into rHIS. Our solution is the centralized registration of placeholder-documents with rHIS and the decentralized data storage at people's home. Conclusions: We concluded that the presented architecture of integrating HET-HC into rHIS might fit well to the traditional approach of document-based data storage. Data security and privacy issues are also duly considered.
    Methods of Information in Medicine 01/2014; 53(2). DOI:10.3414/ME13-02-0008 · 1.08 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The eHome assistance system was developed for supporting older people living alone. The complete activity data resulting from 18 months in 11 flats was subjected in anonymised form to a nearly flat-independent statistical analysis. The data analysis resulted in action classes, from which typical behaviour patterns can be deduced. On their basis, the expert system of eHome will be complemented by a self-learning Bayesian network.
    eHealth2013 - Health Informatics meets eHealth, Big Data – eHealth von der Datenanalyse bis zum Wissensmanagement, Edited by Elske Ammenwerth, Alexander Hörbst, Dieter Hayn, Günter Schreier, 05/2013: chapter Aktionsklassen für Handlungsabläufe im computer-gestützten Wohnen: pages 99-105; Österreichische Computer Gesellschaft.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Against the background of demographic change and a diminishing care workforce there is a growing need for personalized decision support. The aim of this paper is to describe the design and implementation of the standards-based personal intelligent care systems (PICS). PICS makes consistent use of internationally accepted standards such as the Health Level 7 (HL7) Arden syntax for the representation of the decision logic, HL7 Clinical Document Architecture for information representation and is based on a open-source service-oriented architecture framework and a business process management system. Its functionality is exemplified for the application scenario of a patient suffering from congestive heart failure. Several vital signs sensors provide data for the decision support system, and a number of flexible communication channels are available for interaction with patient or caregiver. PICS is a standards-based, open and flexible system enabling personalized decision support. Further development will include the implementation of components on small computers and sensor nodes.
    Studies in health technology and informatics 01/2013; 186:135-9.