Design and implementation of a framework to support the development of clinical guidelines
Introduction
Recent studies have shown the benefits of using clinical guidelines in the practice of medicine [1]. Utilizing guidelines such as standard care plans, critical pathways and protocols in various clinical settings may lead to a reduction of practice variability and patient care costs, while improving patient care [2]. Use of decision support systems that incorporate such guidelines offer promising possibilities for guideline implementation. According to the Institute of Medicine (IOM), these decision support systems are in fact crucial elements in long-term strategies for promoting the use of guidelines [3].
There have been numerous efforts to develop systems that support guideline based care in an automated fashion, covering a wide range of clinical settings and tasks [4]. Despite these efforts, only a few systems progressed beyond the prototype stage and the research laboratory. Building systems that are both effective in supporting clinicians and accepted by them has proven to be a difficult task. Yet, of the few systems that were evaluated by a controlled trial, majority of them showed impact [5]. This paper describes and discusses GASTON: a framework that facilitates all stages in the guideline development process, ranging from the definition of models that represent guidelines to the implementation of run-time systems that provide decision support, using the guidelines that were developed during the earlier stages. The GASTON framework consists of (1) a newly developed guideline representation formalism that uses the concepts of primitives, problem-solving methods (PSMs) and ontologies to represent guidelines of various complexity and granularity and different application domains; (2) a guideline authoring environment that enables guideline authors to define guidelines, based on the newly developed guideline representation formalism; and (3) a guideline execution environment that translates defined guidelines into a more efficient symbol-level representation, which can be read in and processed by an execution-time engine.
Section 2 of this paper defines a number of design criteria that were formulated regarding the aspects of guideline representation, guideline authoring and guideline execution and also describes the methods and materials that were used to develop the GASTON framework, according to the formulated design criteria. Section 3 describes the GASTON framework with examples in terms of the four stages that were identified in the guideline development process, along with the tools that were developed to support each stage. Section 4 presents a number of guidelines and decision support systems that were developed by means of the GASTON framework. Finally, Section 5 discusses various aspects of the guideline based decision support in general and the GASTON framework in particular.
Section snippets
Guideline representation formalisms
A very important aspect that has to be reckoned with when designing guideline based decision support systems is the issue of guideline representation. During the last decade, various guideline representation languages have been developed, each with their own formalisms and specifications. By analyzing a number of these, criteria were formulated for a guideline representation language [6], [7], [8]. These requirements include the possibility to represent temporal logic, branching and sequencing,
Overview
By using the techniques, described in the previous section, the GASTON guideline development methodology and supporting framework were developed. The framework consists of a suite of tools that support the various stages in guideline development. Fig. 1 shows the process view of the framework.
The process consists of four stages, each of which is reusable in other guideline development processes:
- •
Develop, derive or reuse application-specific domain and method ontologies.
- •
Develop or reuse libraries
Results
The methodology described in this paper was used to develop a number of guidelines and decision support systems that differ in granularity, complexity and application domain.
The CritICIS system is a real-time reminder system used in critical care environments such as Intensive Care Units. The domain ontology of this system is based on the IMPACT minimal standard data set, a set of medical terms describing the state of a patient in an intensive care unit (ICU) [44]. At present, the ontology
Discussion
Although the number of guideline-based decision-support systems increased rapidly during the last years, the number of systems that are actually used in daily practice is still very small. The use of a framework as described in this paper may increase the number of systems that are used in practice as it covers all stages in the guideline development process, from the guideline acquisition phase to the guideline execution phase. The use of primitives, PSMs ontologies and plugins facilitates
References (51)
- et al.
Effects of clinical guidelines on medical practice: a systematic review of rigorous evaluation
Lancet
(1993) Rationale for the Arden Syntax
Comput. Biomed. Res.
(1994)- et al.
Design of a clinical event monitor
Comput. Biomed. Res.
(1996) - et al.
The asgaard project: a task-specific framework for the application and critiquing of time-oriented clinical guidelines
Artif. Intell. Med.
(1998) Heuristic classification
Artif. Intell.
(1985)A translation approach to portable ontologies
Knowledge Acquisition
(1993)Temporal logics and real time expert systems
Comput. Meth. Prog. Biomed.
(1996)- et al.
A test ordering system with automated reminders for primary care based on practice guidelines
Int. J. Med. Inf.
(2000) Implementing Clinical Practice Guidelines: Can guidelines be used to improve clinical practice?
Effective Health Care
(1994)