Annotated Bayesian networks: a tool to integrate textual and probabilistic medical knowledge

Antal, Péter; Mészáros, Tamás; Moor, B. De; Dobrowiecki, Tadeusz

doi:10.1109/cbms.2001.941717

Cited by 9 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the structure of annotated BNs is Fig. 18 Questionnaire response relevant to individual and relative importance of predictive accuracy not described in detail by [4]. In a following paper, [3] simplify annotated BNs and define it as "a directed, acyclic graph whose nodes are annotated with local probabilistic models (as in standard Bayesian networks) and with textual attributes".…”

Section: Resultsmentioning

confidence: 99%

“…Helsper and van der Gaag [20] also propose a methodology to derive a BN structure from this ontology; however, the method was not used to develop the model in their case study since the ontology is prepared retrospectively from an existing BN. Van [4] annotated BNs aim to clarify knowledge behind BNs, but these frameworks do not aim to show the link between the model and evidence. Helsper and van Der Gaag [21] focus on describing knowledge elicited from experts in more detail.…”

Section: Resultsmentioning

confidence: 99%

“…Evidence from publications or conflicting expert opinions is not shown. Although the aims of the initial version of annotated BNs [4] are similar to our evidence framework, it lacks the structure to store information about the type and source of evidence, and excluded factors. These features are crucial for clarity and completeness of evidence.…”

Section: Resultsmentioning

confidence: 99%

“…Over 85 % of the participants indicated that our evidence framework improves the current practice in prognostic models, and over 90 % thinks that this tool could be used in practice. [4] initially propose annotated BNs as a tool to describe background knowledge for each node, edge, state and fragment of BNs. However, the structure of annotated BNs is Fig.…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Clinical evidence framework for Bayesian networks

et al. 2016

View full text Add to dashboard Cite

There is poor uptake of prognostic decision support models by clinicians regardless of their accuracy. There is evidence that this results from doubts about the basis of the model as the evidence behind clinical models is often not clear to anyone other than their developers. In this paper, we propose a framework for representing the evidence-base of a Bayesian network (BN) decision support model. The aim of this evidence framework is to be able to present all the clinical evidence alongside the BN itself. The evidence framework is capable of presenting supporting and conflicting evidence, and evidence associated with relevant but excluded factors. It also allows the completeness of the evidence to be queried. We illustrate this framework using a BN that has been previously developed to predict acute traumatic coagulopathy, a potentially fatal disorder of blood clotting, at early stages of trauma care.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Clinical evidence framework for Bayesian networks

et al. 2016

View full text Add to dashboard Cite

show abstract

“…To track the route of the incorporated prior background information (studies, papers, experts, etc.) to the Bayesian network model we investigated the use of annotation in the Bayesian network model (ABN) [3]. The annotations consist of natural language comments and references to various levels of the Bayesian network.…”

Section: Introductionmentioning

confidence: 99%

Domain knowledge based information retrieval language: an application of annotated Bayesian networks in ovarian cancer domain

Antal

Moor

Timmerman

et al.

Proceedings of 15th IEEE Symposium on Computer-Based Medical Systems (CBMS 2002)

Self Cite

View full text Add to dashboard Cite

The increasing amount and variety of domain knowledge and the availability of increasingly large quantities of electronic literature requires new types of support for the development of complex knowledge models. In previous publications we proposed the application of so called Annotated Bayesian Networks (ABN), textually enriched probabilistic domain models, which help knowledge engineers and medical experts to find and organize the information necessary in model building. In this paper we describe an information retrieval language in which the formalized domain knowledge and the attached textual information can be accessed in an integrated fashion and can be used to define various retrieval schemes and relevance measures. This language, on one hand, provides maximum flexibility for knowledge engineers to exploit the available annotated domain model as contextual information. On the other hand, it allows the definition of complex, high-level queries, in which the contextual use of the annotated domain model can be optimized for clinical situations. We compare the performance of the standard and the proposed query language in the ovarian cancer domain.

show abstract