OpenClinical logo

Clinical demonstrators

Methods and tools for the development of computer-interpretable guidelines

Italy  GLARE
GuideLine Acquisition, Representation and Execution
keywords Computer-interpretable guidelines, knowledge representation, development and execution, representation formalism, clinical knowledge authoring tool, guideline execution engine, temporal reasoning.
developed by Università del Piemonte Orientale "Amedeo Avogadro", Alessandria; Azienda Ospedaliera S. Giovanni Battista, Torino, Italy.
introduced 1997
status In use / under continued development.
support Internal; Azienda Ospedaliera S. Giovanni Battista, Torino
in use Guideline for ischemic stroke (in association with the Azienda Sanitaria Ospedaliera Molinette San Giovanni Battista di Torino).
tools Under development.
description
GLARE is a domain-independent system for acquiring, representing and executing clinical guidelines. GLARE has been under development since 1997 by the Dipartimento di Informatica, Università del Piemonte Orientale "Amedeo Avogadro", Alessandria, Italy, in co-operation with the Laboratorio di Informatica Clinica, Azienda Ospedaliera S. Giovanni Battista, Torino, Italy.

The system is based on a modular architecture, which includes an acquisition tool and an execution tool.

GLARE architecture

Figure 1: GLARE architecture

The GLARE representation language is designed to achieve a balance between expressiveness and complexity. The formalism consists of a limited, but very focused and clearly understandable set of primitives. It is made up of different types of actions: plans (i.e. composite actions, hierarchically decomposable in their sub-actions) and atomic actions. Atomic actions can be queries, decisions, work actions and conclusions. All actions are linked by control relations (e.g. sequence, alternative, repetition), defining their order of execution [Terenziani et al, 2000, Terenziani et al, 2001].

GLARE provides expert physicians with an "intelligent" guideline acquisition interface. This provides different types of checks to help develop a consistent guideline: syntactic and semantic tests verify the "well-formedness" of a guideline. Further, extended Artificial Intelligence (AI) temporal reasoning techniques are used to check the consistency of temporal constraints imposed between actions [Terenziani et al, 2001]. Figure 2 shows a snapshot of the graphical interface of the authoring tool.

GLARE knowledge acquisition tool graphical interface
Figure 2: GLARE knowledge acquisition tool
[Click for full-size image]

In the GLARE knowledge acquisition tool, different shapes and colours are used to represent different types of actions (e.g. plans, queries, decisions). On the left, the hierarchy of plans and sub-actions is shown in form of a tree; on the right, the control relations between actions are displayed as a graph [Terenziani et al, 2001].

spacer

Decision support

During guideline execution, a physician is often faced with the choice between alternative procedures. Clearly, a tool for collecting the pieces of information that are relevant to the current choice can play a fundamental role in the semi-automatic execution of a guideline. In many cases, decisions should not solely be taken on the basis of "local information", the criteria associated with the current specific decision. The choice may also need to take into account information associated with the alternatives on offer. In GLARE, we allow for use of this "global information" through a hypothetical reasoning facility [Terenziani et al, 2002b] that enables users to gather relevant decision parameters (e.g., costs, resources, times) from selected parts of the guideline in a semi-automatic way. This hypothetical reasoning facility provides a way of simulating the consequences of choosing different alternative paths through a guideline. This facility can be particularly useful when a physician has to choose between different therapeutic procedures and the best one for a specific patient is not obvious. For example, the treatment choice node in figure 2 (for symptomless gallbladder stones) offers expectant management, litholythic therapy, laparotomic and laparoscopic surgery as suitable procedures, but of course each of these procedures would involve different costs, times and resources [Terenziani et al, 2002b]. A GLARE-based guideline can take a clinician through the different implications of each treatment choice.

spacer

Temporal reasoning with GLARE

The GLARE formalism is capable of specifying the temporal issues involved in developing and running a clinical guideline. In most therapies, actions have to be performed according to a set of temporal constraints determining the order in which they are carried out, their duration, and the intervals (cyclical or non-cyclical) between them. The GLARE representation formalism is designed to cope with different types of temporal constraints needed to manage clinical guidelines, and specialised temporal reasoning algorithms operating on them. Temporal reasoning can be useful both when the guideline is being developed (e.g., to check the consistency of the time-based constraints imposed between actions by the expert physicians), and when it is being executed (e.g., within the hypothetical reasoning facility, in order to look for temporally minimal procedures to deal with a given situation) [Terenziani et al, 2002a].

GLARE technology has been succesfully tested in different clinical domains (bladder cancer, reflux esophagitis and heart failure), at the Laboratorio di Informatica Clinica, Azienda Ospedaliera S. Giovanni Battista, Torino, Italy.

plans
 
references

Terenziani P, Montani S, Bottrighi A et al. The GLARE approach to clinical guidelines: main features. Stud Health Technol Inform. 2004;101:162-6.

[PubMed]   []

" In this paper, we present GLARE, a domain-independent prototypical system for acquiring, representing and executing clinical guidelines. GLARE has been built within a 7-year project with Azienda Ospedaliera San Giovanni Battista in Turin (one of the largest hospitals in Italy) and has been successfully tested on clinical guidelines in different domains, including bladder cancer, reflux esophagitis, and heart failure. GLARE is characterized by the adoption of advanced Artificial Intelligence (AI) techniques, to support medical decision making and to manage temporal knowledge. "

Terenziani P, Montani S, Bottrighi A et al. A Context-adaptable Approach to Clinical Guidelines. Medinfo. 2004;2004:169-73.

[PubMed]   []

" One of the most relevant obstacles to the use and dissemination of clinical guidelines is the gap between the generality of guidelines (as defined, e.g., by physicians' committees) and the peculiarities of the specific context of application. In particular, general guidelines do not take into account the fact that the tools needed for laboratory and instrumental investigations might be unavailable at a given hospital. Moreover, computer-based guideline managers must also be integrated with the Hospital Information System (HIS), and usually different DBMS are adopted by different hospitals. The GLARE (Guideline Acquisition, Representation and Execution) system addresses these issues by providing a facility for automatic resource-based adaptation of guidelines to the specific context of application, and by providing a modular architecture in which only limited and well-localised changes are needed to integrate the system with the HIS at hand. "

Terenziani P et al. Supporting physicians in taking decisions in clinical guidelines: the GLARE "What if" facilty. AMIA 2002.

[Abstract - OC]

[]

"GLARE (GuideLine Acquisition, Representation and Execution) is a domain-independent system for the acquisition, representation and execution of clinical guidelines. GLARE is unique in its approach to supporting the decision-making process of users/physicians faced with various alternatives in the guidelines. In many cases, the best alternative cannot be determined on the basis of "local information" alone (i.e., by considering just the selection criteria associated with the decision at hand), but must also take into account information stemming from relevant alternative pathways. Exploitation of "global information" available in the various pathways is made possible by GLARE through the "what if" facility, a form of hypothetical reasoning which allows users to gather relevant decision parameters (e.g., costs, resources, times) from selected parts of the guideline in a semi-automatic fashion. In particular, the extremely complex task of coping with temporal information involves the extension and adaptation of various techniques developed by the Artificial Intelligence (AI) community."
P. Terenziani, C. Carlini, S. Montani, Towards a Comprehensive Treatment of Temporal Constraints in Clinical Guidelines, in Proc. Ninth International Symposium on Temporal Representation and Reasoning (Time-02), IEEE Computer Society Press, Manchester, (2002), 20-27.

[Abstract - OC]  []

"In this paper, we focus on an application and extension of Artificial Intelligence temporal reasoning techniques in order to represent and reason with temporal constraints in clinical guidelines. Particular attention is dedicated to the treatment of repeated (periodic) events, which play a major role in clinical therapies. We also discuss some limitations of our current approach, highlighting possible future enhancements..."
Terenziani P, Mastromonaco F, Molino G, Torchio M. Executing clinical guidelines: temporal issues. Proc AMIA Symp. 2000;:848-52.

[PubMed]    [Abstract - OpenClinical]    [AMIA]

"In this paper, we describe an approach to execute clinical guidelines. We propose a flexible execution engine that can be used in clinical decision support applications, and also for medical education, or for integrating guidelines into the clinical workflow. We also focus our attention on temporal issues in the execution of guidelines, including the treatment of composite, concurrent and/or cyclic actions."
Terenziani P, Molino G, Torchio M. A modular approach for representing and executing clinical guidelines. Artif Intell Med. 2001 Nov;23(3):249-76.

[PubMed] [ScienceDirect]
[Abstract - OpenClinical]

"In this paper, we propose an approach for managing clinical guidelines. We outline a modular architecture, allowing us to separate ... the representation (and acquisition) of clinical guidelines and their execution. We propose an expressive formalism, which allows one to deal with the context-dependent character of clinical guidelines and also takes into account different temporal aspects. We also describe our tool for acquiring clinical guidelines ... In the second part of the paper, we describe a flexible engine for executing clinical guidelines ... focusing our attention on temporal issues."
Guarnero A, Marzuoli M, Molino G, Terenziani P, Torchio M, Vanni K. Contextual and temporal clinical guidelines. Proc AMIA Symp. 1998;:683-7.

[PubMed] [AMIA]
[Abstract - OpenClinical]

"In this paper, we propose an approach for managing clinical guidelines. We sketch a modular architecture, allowing us to separate conceptually distinct aspects in the management and use of clinical guidelines. In particular, we describe the clinical guidelines knowledge representation module and we sketch the acquisition module. The main focus of the paper is the definition of an expressive formalism for representing clinical guidelines, which allows one to deal with the context dependent character of clinical guidelines and takes into account different temporal aspects."
contact Paolo Terenziani
DISTA
Università del Piemonte Orientale Amedeo Avogadro
C.so Borsalino 54
15100 Alessandria, Italy.

E: terenzatdi.unito.it
links  bullet  Dipartimento di Informatica, Università del Piemonte Orientale "Amedeo Avogadro", Alessandria  bullet  Azienda Sanitaria Ospedaliera Molinette San Giovanni Battista di Torino
acknowledgements
Paolo Terenziani, Università del Piemonte Orientale Amedeo Avogadro
page history
Entry on OpenClinical:2002
Last main update: 31 July 2002; (06 April 2005)

 

Search this site
 
Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2002-2011