Annotated bayesian networks: A tool to integrate textual and probabilistic medical knowledge

Péter Antal, Tamás Mészáros, Bart De Moor, Tadeusz Dobrowiecki

Research output: Contribution to journalArticle

10 Citations (Scopus)


In previous publications we have reported on the development of Bayesian Network models for the preoperative discrimination between malignant and benign ovarian mass. The models incorporated both medical background knowledge and patient data, which required the traceability of the incorporated prior medical knowledge. For this purpose, we followed a particular annotation method for Bayesian Networks using a dedicated representation. In this paper we present the resulting Annotated Bayesian Network (ABN) representation that consists of a regular Bayesian Network with standard probabilistic semantics and a corresponding semantic network, to which the textual information sources are attached. We demonstrate the applicability of such dual model to represent both the rigorous probabilistic and the unconstrained textual medical knowledge. We describe methods on how these Annotated Bayesian Network models can be used: (1) as a domain model to arrange the personal textual information of the clinician according t o the semantics of the domain, (2) in decision support to provide detailed, even personalized explanation, and (3) to enhance the information retrieval to find new textual information more efficiently.

Original languageEnglish
Pages (from-to)177-182
Number of pages6
JournalProceedings of the IEEE Symposium on Computer-Based Medical Systems
Publication statusPublished - Jan 1 2001

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Annotated bayesian networks: A tool to integrate textual and probabilistic medical knowledge'. Together they form a unique fingerprint.

  • Cite this