Ontology-Based Medical Data Integration for Regional Healthcare Application
The regional information sharing provides the ability to transfer up-to-date patient health information quickly and easily across hospitals and institutes. However, the fact that most systems are developed proprietarily hinders data integration. Most deve
- PDF / 349,449 Bytes
- 6 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 216 Views
Ontology-Based Medical Data Integration for Regional Healthcare Application Yu-Xin Wen, Hua-Qiong Wang, Yi-Fan Zhang and Jing-Song Li
Abstract The regional information sharing provides the ability to transfer up-todate patient health information quickly and easily across hospitals and institutes. However, the fact that most systems are developed proprietarily hinders data integration. Most developers solve this problem by employing specific data model standards, leading to system inflexibility and inextensibility. In this paper, we present an ontology-based integration method to cope with data heterogeneity in the regional health information network. To carry out interoperability at runtime and in a non-intrusive manner, we design three-layer system architecture. The semantic layer is used to perform coordination among heterogeneous systems, which can connect seamlessly without changing original data structure. We adopt the hybrid ontology approach that extracts information from heterogeneous databases to establish local ontologies and uses an upper-level ontology to make these ontologies compatible. This paper demonstrates a means of accessing to heterogeneous databases for better regional information sharing. Keywords Data integration
Hybrid ontology OWL Regional healthcare
191.1 Introduction The development of regional information exchange is viewed as a crucial step in the development of health information technology [1]. The goal of data integration is for information to follow patients, wherever and whenever they seek care, in a private and secure manner so that doctors can provide coordinated and effective care. Unfortunately, most healthcare institutions employ proprietary systems to Y.-X. Wen H.-Q. Wang Y.-F. Zhang J.-S. Li (&) Healthcare Informatics Engineering Research Center, Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou 310027, China e-mail: [email protected]
S. Li et al. (eds.), Frontier and Future Development of Information Technology 1667 in Medicine and Education, Lecture Notes in Electrical Engineering 269, DOI: 10.1007/978-94-007-7618-0_191, Springer Science+Business Media Dordrecht 2014
1668
Y.-X. Wen et al.
store, represent information which hinders data integration and makes it very difficult for clinicians to capture the complete clinical history of a patient at a fast speed [2]. Additionally, as the complexity of the health domain is evolving rapidly, these systems contain a large number of raw data, leading to the phenomenon of data exploding while lacking of semantic. Namely information can be readable only by humans but computer itself cannot effectively process or interpret the data present in it. Moreover, The deficiency of information heterogeneity can be found as follows [3]: different resources often provide heterogeneous data formats: structured as databases, semi-structured as XML documents and non-structured as web pages or other type of documents; the existence of synonyms and homonyms. For example, system A s
Data Loading...