Applying Artificial Intelligence to Clinical Guidelines: The GLARE Approach

Abstract

Abstract. In this paper, we present GLARE, a domain-independent system for acquiring, representing and executing clinical guidelines. GLARE is characterized by the adoption of Artificial Intelligence (AI) techniques at different levels in the definition and implementation of the system. First of all, a high-level and user-friendly knowledge representation language has been designed, providing a set of representation primitives. Second, a user-friendly acquisition tool has been designed and implemented, on the basis of the knowledge representation formalism. The acquisition tool provides various forms of help for the expert physicians, including different levels of syntactic and semantic tests in order to check the "well-formedness" of the guidelines being acquired. In particular, extended AI temporal reasoning techniques are used to check the consistency of temporal constraints. Third, a tool for executing guidelines on a specific patient has been made available. The tool relies on an "agenda" technique, which provides great flexibility, including the possibility of managing repeated and/or concurrent actions. The execution module also provides hypothetical reasoning facilities, to support physicians in the comparison of alternative diagnostic and/or therapeutic strategies. The GLARE approach has been successfully tested on clinical guidelines in different domains such as bladder cancer, reflux esophagitis, heart failure and stroke.

Temporal reasoning techniques for the analysis of interactions in the treatment of comorbid patients

“…GLARE (Guideline Acquisition, Representation and Execution) [6], [7] has been built starting from 1997 in a long-term cooperation between the Department of Computer Science of the University of Piemonte Orientale, Alessandria, Italy and the Azienda Ospedaliera San Giovanni Battista in Turin (one of the largest hospitals in Italy). GLARE supports the use of advanced artificial intelligence techniques and decision-support techniques in the treatment of CIGs [7] (a comparison of GLARE with other approaches coping with CIGs can be found in [3]).…”

“…GLARE supports the use of advanced artificial intelligence techniques and decision-support techniques in the treatment of CIGs [7] (a comparison of GLARE with other approaches coping with CIGs can be found in [3]). In GLARE, a CIG can be represented as a hierarchical graph, where nodes are the actions to be executed and arcs are the control relations linking them.…”

“…To do so, an extended representation formalism has to be identified, to model time and temporal interactions, as well as advanced temporal reasoning techniques, to discover whether the effects of potentially conflicting actions overlap in time. In this paper, we propose an advanced Artificial Intelligence approach facing such issues, developed on top of the GLARE system [6], [7]. Notice, however, that the methodology we propose is largely system-independent.…”

Automated generation of patient-tailored electronic care pathways by translating computer-interpretable guidelines into hierarchical task networks

“…Of the languages studied in [19], PROforma [34] and GLARE [35] are the only approaches that have two component sublanguages, one for the guideline acquisition phase, and another processed in an execution module (all other approaches require a custom-developed execution engine). The presented methodology can be seen as a similar approach for Asbru, but where the result of the translation goes beyond achieving a step-by-step interpretation of the guideline.…”

Recursive representation of periodicity and temporal reasoning

“…It is crucial to give support to all the abovementioned kinds of temporal information with a uniform domain-independent approach and hide the complexity of the "machinery" to the user. This goal is motivated by our ongoing work in the domain of guidelines automation ( [15,18,21,22], see also subsection 5.2). A first step in this direction has been made in [20], but with limitations that in some real-world cases it is necessary to overcome: in fact, while that approach can handle Ex.…”