OpenClinical: DeGeL

Clinical demonstrators

Methods and tools for the development of computer-interpretable guidelines

Digital electronic Guideline Library

DeGeL is a Web-based, modular, distributed architecture designed to support (i) the development and implementation of clinical guideline applications and (ii) the creation of a Digital electronic Guideline Library.

keywords	Guideline development and execution, clinical practice guidelines, semantic markup, incremental guideline specification, hybrid guideline representation format, URUZ, VisiGuide, QualiGuide, Vaidurya, IndexiGuide, Spock
developed by	Ben-Gurion University of the Negev, Israel
introduced	2001
status	Under development
support	Supported in part by the US National Institutes of Health
in use
tools	Software tools, particularly the Uruz markup tool and Vaidurya search and retrieval tool, are available to developers for research purposes, subject to prior registration with and authorisation from BGU. Contact Ohad Young - ohadyn@bgumail.bgu.ac.il - for more information. Registration with BGU.

description

The DeGeL project is focused on providing automated support for the specification and implementation of clinical guidelines in the treatment of patients, particularly those with chronic conditions such as diabetes, hypertension and depression.
The DeGeL method of guideline specification is based on a hybrid (multiple-format) electronic representation of guidelines in order to cater for the different specification skills of editors and the different needs of each guideline-based-care task. In the DeGeL method, a guideline is first converted from free text into semantically semi-structured text and semi-formal language by a medical expert using a markup editor, then to a fully formal representation by a knowledge engineer (the current default target language is Asbru). The method supports distributed Web-based access for knowledge acquisition, maintenance, retrieval, and enactment.
The DeGeL project has developed a wide range of tools to support the development and implementation of guideline applications see below).
Support is provided for a wide range of tasks central to guideline-based care:
During guideline specification:

verification of the guideline process specification (syntax)

validation of the guideline against its goals (semantics)

During guideline execution:

determination of patient eligibility and guideline applicability

visualization of one or more potentially applicable guidelines
application (execution) of the guideline
quality assessment of providers’ actions
modification of guideline or provider plans
evaluation of guideline effectiveness.

Component tools

Main tools that form the DeGeL framework (screens in following section) :

URUZ: Web-based authoring tool for clinical guidelines using a three-level hybrid representation. URUZ supports upload of source documents (free text guidelines), the specification of a new guideline, semantic markup of existing free-text guidelines into structured text and semi-formal langauge using the semantic tags of a selected target guideline representation language (e.g., Asbru, GEM), and indexing. URUZ operates dynamically by reading the structure tree so can support indexing and markup using any hierarchical guideline-representation format [URUZ screen].

VisiGuide: guideline browsing and visualisation tool [VisiGuide screens].

Vaidurya: guideline search engine providing context-sensitive search and retrieval. Vaidurya uses the VisiGuide tool to facilitate visualization, browsing, and exploration of search results. Helps to determine which guideline is most relevant for current needs [Vaidurya screen].

IndexiGuide: supports semantic classification of guidelines to facilitate later retrieval. Classification of a new guideline uploaded to the DeGeL library is carried out along a multiple hierarchy of several semantic axes (e.g., diagnosis, therapy), and definition of their type (e.g., screening) [IndexiGuide screen].

Spock: runtime environment (currently supports guidelines expressed in hybrid-Asbru)

QualiGuide: supports quality assessment.

GESHER: guideline aquisition tool.

Screens

URUZ Web-based guideline markup tool

[Click for complete screen.]

The tool's basic semi-structuring interface is uniform across all guideline ontologies. The target ontology selected by the medical expert, in this case, Asbru, is displayed in the upper left tree; the guideline source is opened in the upper right frame. The expert physician highlights a portion of the source text (including tables or figures) and drags it for further modification into the bottom frame's Editing Window tab labeled by a semantic role chosen from the target ontology (here, filter condition). Note that contents can be aggregated from different locations in the source. The Comments tab, the tab next to the Editing Window tab, stores remarks on the current selected knowledge-role, thus supporting collaboration among guideline editors.

VisiGuide - 1

[Click for complete screen.]

VisiGuide Interface in the single-guideline view mode. In this mode, the guideline's contents can be more deeply examined. On the left-hand side, the user selects, within the meta-ontology or the chosen target ontology, the knowledge roles he/she is interested in viewing in the meta-ontology or within the guideline's contents. These roles and their contents are then displayed on the right-hand side. It is also possible to return the guideline to a DeGeL application such as Uruz.

VisiGuide - 2

VisiGuide screen

VisiGuide Interface in multiple-ontology mode. In this mode, multiple guidelines, typically retrieved by the Vaidurya search engine, are displayed within the various semantic axes indexing them (left frame). The contents of knowledge roles relevant to the user are displayed and compared as a table (right frame). The "Return Results" button returns selected guideline back to the requesting application (e.g., to the Uruz markup tool). The left-hand icon in the top menu enables the user to select among several preset views, such as an eligibility view (which in the case of the Asbru ontology displays, for all guidelines, along with the guideline's title, the filter and setup conditions)

Vaidurya

[Click for complete screen.]

Screen from the Vaidurya Web-based, context-sensitive, guideline search and retrieval tool. The user defines the relevant search scope by indicating one or more nodes within the semantic axes (upper left and right frames). The search can be further refined by specifying terms to be found within the source text, and even (after selecting a target ontology such as Asbru), within the context of one or more particular knowledge roles of that ontology (middle right frame).

IndexiGuide

[Click for complete screen.]

An example of the VisiGuide Interface in multiple-ontology mode. In this mode, multiple guidelines, typically retrieved by Vaidurya search engine, are displayed within the various semantic axes indexing them (left frame); the contents of knowledge roles relevant to the user are displayed and compared as a table (right frame). The "Return Results" button returns selected guideline back to the requesting application (e.g., to the Uruz markup tool). The left-hand icon in the top menu enables the user to select among several preset views, such as an eligibility view (which in the case of the Asbru ontology displays, for all guidelines, along with the guideline's title, the filter and setup conditions)

plans

references

Y. Shahar, O. Young, E. Shalom et al. A Framework for a Distributed, Hybrid, Multiple-Ontology Clinical-Guideline Library and Automated Guideline-Support Tools. Technical Report, Ben Gurion University of the Negev (2004).

[] [BGU]

Abstract " Clinical Guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, not machine comprehensible, and are not easily accessible to clinicians at the point of care. We introduce a Web-based, modular, distributed architecture, the Digital Electronic Guideline Library (DeGeL), which facilitates gradual conversion of clinical guidelines from text to a formal representation in chosen target guideline ontology. The architecture supports guideline classification, semantic markup, context-sensitive search, browsing, run-time application, and retrospective quality assessment. The DeGeL hybrid meta-ontology includes elements common to all guideline ontologies, such as semantic classification and domain knowledge; it also includes four content-representation formats: free text, semi-structured text, semi-formal representation, and a formal representation. These formats support increasingly sophisticated computational tasks. The DeGeL tools for support of guideline-based care operate, at some level, on all guideline ontologies. We have demonstrated the feasibility of the architecture and the tools for several guideline ontologies, including Asbru and GEM "

Shahar Y, Young O, Shalom E, Mayaffit A, Moskovitch R, Hessing A, and Galperin M. DeGeL: A Hybrid, Multiple-Ontology Framework for Specification and Retrieval of Clinical Guidelines. Proceedings of the 9th Conference on Artificial Intelligence in Medicine—Europe (AIME) ‘03, Protaras, Cyprus, Oct. 2003, Springer-Verlag Heidelberg, pp. 122 - 131.

[] [Ben Gurion University]

Abstract " Clinical Guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, not machine comprehensible, and are not easily accessible to clinicians at the point of care. We introduce a Web-based, modular, distributed architecture, the Digital Electronic Guideline Library (DeGeL), which facilitates gradual conversion of clinical guidelines from text to a formal representation in a chosen guideline ontology. The architecture supports guideline classification, semantic markup, context sensitive search, browsing, run-time application, and retrospective quality assessment. The DeGeL hybrid meta-ontology includes elements common to all guideline ontologies, such as semantic classification, and domain knowledge. The hybrid meta-ontology also includes three guideline-content representation formats: free text, semi-structured text; and a formal representation. These formats support increasingly sophisticated computational tasks. All tools are designed to operate on all representations. We demonstrated the feasibility of the architecture and the tools for the Asbru and GEM guideline ontologies. "

Young O, Shahar Y. Spock: a hybrid model for runtime application of asbru clinical guidelines. Medinfo. 2004;2004(CD):1922.

[PubMed] [BGU]

Abstract " Clinical Guidelines are a major tool in improving the quality of medical care. However, most guidelines are in free text, not machine comprehensible, and are not easily accessible to clinicians at the point of care. We have developed a set of tools, as part of the Digital electronic Guideline Library (De- GeL) framework, for gradually structuring clinical guidelines, from free text to a machine-comprehensible format. Guidelines can thus be in a hybrid representation in, which guidelines and even parts of the same guideline might exist at different formalization levels. However, most guidelines are expected to be in a semi-structured-text format. We introduce a new approach for supporting runtime application of clinical guidelines that are not necessarily in a machine comprehensible format. This new approach, the hybrid runtime application model, is customized at this point to the Asbru guideline specification language and exploits the hybrid structure of guidelines in DeGeL. "

Shahar Y, Shalom E, Mayaffit A et al. A Distributed, Collaborative, Structuring Model for a Clinical-guideline Digital-library. Proc AMIA Symp. 2003;:589-93.

[PubMed] [BGU]

Abstract " The Digital Electronic Guideline Library (DeGeL) is a Web-based framework and a set of distributed tools that facilitate gradual conversion of clinical guidelines from free text, through semi-structured text, to a fully structured, executable representation. Thus, guidelines exist in a hybrid, multiple-format representation The three formats support increasingly sophisticated computational tasks. The tools perform semantic markup, classification, search, and browsing, and support computational modules that we are developing, for run-time application and retrospective quality assessment. We describe the DeGeL architecture and its collaborative-authoring authorization model, which is based on (1) multiple medical-specialty authoring groups, each including a group manager who controls group authorizations, and (2) a hierarchical authorization model based on the different functions involved in the hybrid guideline-specification process. We have implemented the core modules of the DeGeL architecture and demonstrated distributed markup and retrieval using the knowledge roles of two guidelines ontologies (Asbru and GEM). We are currently evaluating several of the DeGeL tools. "

Shalom E, Shahar Y. A Graphical Framework for Specification of Clinical Guidelines at Multiple Representation Levels. Proc. AMIA, 2005.

[] [OC]

" Formalization of a clinical guideline for purposes of automated application and quality assessment mainly involves conversion of its freetext representation into a machine comprehensible representation, i.e., a formal language, thus enabling automated support. The main issues involved in this process are related to the collaboration between the expert physician and the knowledge engineer. We introduce GESHER - a graphical framework for specification of clinical guidelines at multiple representation levels. The GESHER architecture facilitates incremental specification through a set of views adapted to each representation level, enabling this process to proceed smoothly and in a transparent fashion, fostering extensive collaboration among the various types of users. The GESHER framework supports specification of guidelines at multiple representation levels, in more than one specification language, and uses the DeGeL digital guideline library architecture as its knowledge base. The GESHER architecture also uses a temporal abstraction knowledge base to store its declarative knowledge, and a standard medical-vocabularies server for generic specification of key terms, thus enabling reuse of the specification at multiple sites. "

contact

Ohad Young
[ohadyn