|
|
Methods and tools for the development of computer-interpretable guidelines
|
|
 GASTON
|
|
A generic architecture for the design, development, validation and implementation of guideline-based medical decision support systems
|
|
| keywords |
Clinical Practice Guidelines, Guideline Representation, Guideline Acquisition, Guideline Execution, Decision Support Systems
|
| developed by |
Eindhoven University of Technology;
Maastricht University;
Medecs BV, Eindhoven, the Netherlands.
|
| introduced |
1997
|
| status |
In use / under continued development.
In 2001, the company Medecs was formed as a commercial spin-off of the Eindhoven University of Technology to ensure the continuity and further development of the Gaston framework.
|
| support |
Senter (Dutch Ministry of Economic Affairs).
|
| in use |
Gaston has been used to develop, implement and evaluate guidelines and guideline-based decision support systems in the areas of critical care, family practice, psychiatry, oncology, cardiology and chronic disease management (see also the reference section).
|
| tools |
|
|
| description |
Gaston is a methodology and a framework that facilitates the development and implementation of computer-interpretable guidelines and guideline-based decision support systems. Gaston has been developed during the last 7 years by a joint effort of the Department of medical Informatics of Maastricht University and the Signal Processing Systems group of the Eindhoven University of Technology. The overall goal of this approach is to improve the acceptance of computer-interpretable guidelines and decision support systems in daily care by facilitating all phases in the guideline development process. The central research questions of the Gaston project are:
- How to represent and share various types of guidelines using a formal and unambiguous representation.
- How to translate guidelines from a textual format into this formal representation.
- How to handle local adaptation and synchronization between (inter)national and local guidelines.
- How to evaluate guidelines and decision support systems in daily practice.
- How to interface guideline-based decision support systems with external patient information systems.
- How to provide decision support to a care provider in daily practice.
- How to handle real-time patient data sources such as patient monitors that contain streaming physiological data (e.g., heart rate or ECG).
The Gaston framework consists of
- A 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;
- A guideline authoring environment that enables guideline authors to define guidelines;
- A guideline execution environment that translates defined guidelines into a more efficient representation, which can be read in and processed by an execution-time engine.
The guideline representation formalism uses a frame-based model as an underlying mechanism. The formalism is non-monolithic, meaning that it can be extended with additional classes to capture new guideline characteristics.
Similar to the GLIF and EON approaches, the Gaston guideline authoring environment represents and visualizes guidelines by temporally sequenced graphs (flowcharts) of frame instances from the guideline model. During the authoring process, Gaston defines different roles a guideline author may play such as 1) the principal guideline author, who defines the control structure and initial contents of the guideline, 2) the local guideline author, who adapts the contents of the guideline to local standards and 3) the local information manager, who specifies communication and implementation details. As a result, guidelines in Gaston consists of various layers (depending on the guideline's complexity or application domain) that describe the control structure of a guideline (flow), its contents (e.g., actual decisions or actions), possible local adaptations, and communication/implementation details (e.g., the method of acquiring patient data or the form of decision support).
The Gaston approach defines various methods for the detection of various logical and procedural errors in guidelines. In addition, the framework also contains a simulation environment where developed guidelines and decision support systems can be tested and evaluated.
Finally, the framework contains a guideline execution environment that is able to execute guidelines and interface with external patient information systems. The execution environment consists of a core guideline execution engine, which can be extended with additional components (plugins) to communicate with patient information systems, medical databases and patient monitors.
|
| Screens |
|
[Click for complete screen.]
A ventilation guideline in the Gaston authoring environment.Here, the communication layer has been chosen to define the method of decision support (in this case, providing a message to a user). The authoring environment relies heavily on drag-and-drop techniques to build guidelines. Steps, conditions and actions are not entered as text, but constructed by selecting and items from the various panes (e.g., terminology-panel) on the left.
|
|
| current work |
|
Eindhoven University of Technology and Maastricht University are involved in various projects
to improve parts of the Gaston framework.
These projects concern topics related to verification, uncertainty, intentions, handling real-time (streaming) data, and the representation and execution of complex temporal criteria.
|
|
| references |
|
De Clercq PA, Blom JA, Hasman A, Korsten HHM. Design and implementation of a framework to support the development of clinical guidelines. Int J Med Inf 2001;64(2- 3):285-318.
[PubMed]
[ScienceDirect]
|
"
This paper describes and discusses a framework that facilitates the development of clinical guideline application tasks. The framework, named GASTON covers 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, based on 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 the guidelines of various complexity and granularity and different application domains, (2) a guideline authoring environment that enables guideline authors to define the 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. The paper describes a number of design criteria that were formulated regarding the aspects of guideline representation, guideline authoring and guideline execution and explains the framework by example in terms of the four stages that were identified in the guideline development process and the tools that were developed to support each stage. It also shows examples of systems that were developed by means of the GASTON framework.
" |
| De Clercq PA, Blom JA, Hasman A, Korsten HH.
GASTON: an architecture for the acquisition and execution of clinical guideline-application tasks.
Med Inform Internet Med. 2000 Oct-Dec;25(4):247-63.
[PubMed]
[]
|
"
Recently, studies have shown the benefits of using clinical guidelines in the practice of medicine. There have been numerous
efforts to develop clinical decision support systems that support guideline-based care in an automated fashion, covering a
wide range of clinical settings and tasks. Despite these efforts, only a few systems progressed beyond the prototype stage
and the research laboratory. For guideline-based clinical decision support systems to be successful, a balance must be made
between intuitive but imprecise representations usually encountered by most of today's systems and representations that
support a strong underlying clinical performance model. The project described in this paper tries to achieve such a balance.
It presents the GASTON architecture that contains a set of reusable software components for the application of guidelines,
including design-time components to facilitate the guideline authoring process based on guideline representation models along
with execution-time components for building decision support systems that incorporate these guidelines. This architecture was
used to develop several guideline representation models such as a rule-based representation to model rule-based guidelines and
guideline representation models that address more complex tasks. Also, decision support systems that incorporate these models
were developed with the architecture. For the representation and application of various classes of guidelines, rules were also
viewed as instances of more complex tasks. By identifying similar characteristics of sets of rules, we developed several tasks
such as a drug intera ction and drug contraindication task. Based on these models, we have developed and validated guidelines and decision support systems for use in several application domains such as intensive care, family physicians and psychiatry. In order to be able to represent more complex time-oriented plans, new guideline representation models are being developed.
" |
| De Clercq PA, Blom JA, Hasman A, Korsten HHM. The Application of Ontologies and Problem Solving Methods for the Development of Shareable Guidelines. Artif Intell Med 2001;22(1):1-22.
[PubMed]
[ScienceDirect]
|
"
Recently, studies have shown the benefits of using clinical guidelines in the practice of medicine. Computer-based clinical guidelines are increasingly applied in diverse areas such as policy development, utilization management, education, conduct of clinical trials, and workflow facilitation. This paper discusses some of the representations suggested in literature, discusses their weak and strong points, and demonstrates and discusses a new approach that extends earlier developed formalisms by combining primitives, ontologies and the use of problem-solving methods (PSMs). The approach is supported by a framework that facilitates the entire guideline authoring process. The paper demonstrates this framework and presents examples of guidelines, PSMs and systems that were developed by means of this approach. The overall goal of this approach is to improve the acceptance of shareable guidelines and decision support systems in daily care by facilitating the guideline acquisition and execution phases.
" |
| De Clercq PA, Hasman A. Experiences with the Development, Implementation and Evaluation of Automated Decision Support Systems. Medinfo. 2004;2004:1033-7.
[PubMed]
[]
|
"
A framework for the implementation of guidelines -GASTON- was developed. Its functions range from the definition of guidelines (using a GLIF like approach) to the implementation of a DSS that can be coupled to existing information systems. This paper discusses experiences with the development of three systems in different domains. It is concluded that the toolbox corresponding to the framework could be successfully used to develop these systems.
" |
|
| references - Gaston applications |
| De Clercq PA, Blom JA, Hasman A, Korsten HHM. A strategy for development of practice guidelines for the ICU using automated knowledge acquisition techniques. Int J Clin Monit Comput 1999;15:109-117.
[PubMed]
[]
|
"
OBJECTIVES: To implement practice guideline entry tools in a reminder system in order to provide decision support to health care workers in clinical care and emergency care environments. To design a knowledge acquisition environment that enables physicians to formulate, update, and verify guidelines without the assistance of a knowledge engineer. METHODS: We developed a knowledge acquisition environment for the Intensive Care Unit (ICU) consisting of 1) a graphical knowledge acquisition tool, 2) tools that perform logical and semantic tests on proposed guidelines, 3) a Patient Data Management System (PDMS) containing clinical patient data, and 4) an expert system that reminds ICU health care workers of inconsistencies between a treatment plan and implemented guidelines. Physicians enter the guidelines using the knowledge acquisition tool, after which consistency and correctness tests are performed on the guidelines. The guidelines are then transferred to the knowledge base of the reminder system and validated by applying the new guidelines to a large stored data set of previous patients. If the new guidelines are approved, they are exported to the reminder system that is used in daily practice. RESULTS: ICU physicians used the knowledge acquisition tool to enter 58 guidelines into the reminder system's knowledge base. These guidelines were tested on a data set consisting of 803 previously admitted patients. As a result, 27 guidelines fired at least once, generating 406 reminders in total. Of the 406 generated reminders, 356 (88%) were issued correctly and 50 (12%) were false alarms. The reminders that were issued correctly involved 3 situations: 1) the database contained inconsistent or incomplete information, 2) the actions or decisions of the health care workers were not the most appropriate ones, and 3) there was a potential risk involved. All false alarms were caused by the fact that the corresponding guidelines were not specific enough to handle certain exceptions. As a result of this analysis, the guidelines could be improved in such a way as to eliminate all false alarms. CONCLUSIONS: These first results demonstrate that this bottom-up knowledge acquisition strategy, implemented by the automated knowledge acquisition tools, enables medical specialists to improve the quality of computer support in an ICU without assistance of a knowledge engineer.
" |
| Bindels R, De Clercq PA, Winkens RAG, Hasman A. A test ordering system with automated reminders for primary care based on practice guidelines. Int J Med Inf 2000;58-59(1):219-33.
[PubMed]
[ScienceDirect]
|
"
In this article we describe a real-time automated reminder system that has been developed to change Family Physicians' (FP) test ordering behavior. The system focuses on the appropriateness of test requests. We aim at using the system as a substitute for written feedback by human experts. The reminder system consists of a knowledge base, an order entry system and modules to provide passive and active support in the form of reminders to FPs. The system generates critical comments about the rationality of the test requests at the moment the FP orders a test that is not in line with national or regional guidelines. For the first validation of the knowledge base we compared the comments of a human expert to the comments of the reminder system on three random samples of test requests. The overall agreement in the subsequent validation rounds was 46, 60 and 69%. The corrections made in the knowledge base after each validation round resulted in a reminder system with 149 reminders concerning various medical problems. Due to the corrections in the knowledge base the reminder system reacts better over the subsequent validation rounds.
" |
| De Clercq PA, Hasman A, Wolffenbuttel BH. A consumer health record for supporting the patient-centered management of chronic diseases. Med Inform Internet Med. 2003 Jun;28(2):117-27
[PubMed]
[]
|
"
OBJECTIVES: To design and implement a shareable consumer health record system to investigate whether the system can assist in the management of chronic diseases. METHODS: A toolkit was designed for constructing the consumer health record system in an evolutionary way. An ethnographic-like approach (formative evaluation) was used to let users (patients and care providers) assess the system leading to incremental changes in the system. RESULTS: The evaluation provided us with sufficient information about which parts of the system needed adaptation. The final consumer health record system was well accepted by patients and care providers. The system is Web-based and is used at home by patients having diabetes. Both care providers and patients enter data. The system can download the data from a glucose meter. It provides feedback to patients on the basis of entered data and incorporated guidelines. It also allows discussion forums. CONCLUSION: Formative evaluation is useful for obtaining feedback from users about prototype systems. Care providers and patients together worked with the consumer health record. Both parties appreciated the system. The approach described here can be used for developing systems for other chronic patient groups.
" |
| Van Oosterhout EMW, Talmon JL, De Clercq PA, Schouten HC, Jansen MPF, Hasman A. The PropeR way to support medical doctors in daily practice. Part I: developing the Protocol Based DSS. MIE 2003.
[PubMed]
[]
|
"
This paper describes the first phase of the development of a Protocol based Decision Support System (PDSS) that will be linked to an Electronic Patient Record system (EPR system). The protocol system will be pro-active: the physician will be automatically prompted from the EPR of a particular patient if the protocol that applies for that patient defines it necessary. The PropeR project studies the impact of a PDSS that is linked to an EPR on daily care processes. There are two areas of research: hospital and home care. This paper describes the application in the hospital. The protocol that is being computerized is a treatment protocol for Acute Myelogenous Leukaemia (AML) that also studies treatment alternatives (conventional versus experimental treatment). This paper based AML protocol has been translated into a formal representation. The KA-tool Gaston is used to make this representation. Twenty-eight subprotocols have been organized in a hierarchical structure with three levels. One of the aims of the project is to make a representation of the AML protocol that can be used in other organizations as well. The main problem we encountered is that the representation not only contains the content of the protocol, but also aspects of application of that protocol in daily care of the hospital and aspects of support. The solution to this problem is the creation of two layers of representation: the first layer is an exact copy of the protocol and thus sharable and the second layer focuses on the support of the protocol in the daily working processes and is mainly domain specific: for the University Hospital Maastricht. At the moment, this division into two layers is being discussed.
" |
|
van Hyfte DM, de Vries Robbe PF, Tjandra-Maga TB, van der Maas AA, Zitman FG. Towards a more rational use of psychoactive substances in clinical practice. Pharmacopsychiatry. 2001 Jan;34(1):13-8.
[PubMed]
[]
|
"
Complex knowledge and data intensive nature of the psychoactive drug selection and prescription process often makes for irrational and inconsistent use of psychoactive drugs in clinical practice. After describing the state of the art with respect to psychoactive drug prescription practices and selection processes, our aim is to analyze the advantages of computer support systems in assisting the clinician in his clinical decisions. Finally, we will review the neuropsychiatric expert systems developed for the neuropsychiatric domain. Suboptimal psychoactive drug therapy is common practice, which leads to hospital admissions, extended length of hospital stay, ineffective therapy and increased costs. Furthermore, the psychoactive drug selection process is a complex decision process, using up-to-date integrative knowledge of drugs from basic sciences to the clinical level. Due to the information load, the lack of appropriate up-to-date information at the point of clinical care and the problem of integrating and weighing all information relatively equally, it is questionable whether any clinician can manage such a complex situation with optimal effectiveness. As has been shown in a number of experiments, clinicians can benefit from computer-based systems that provide access to accurate, up-to-date information. We maintain that more rational use of psychoactive drugs in clinical practice is needed, and conclude that rational psychoactive drug prescription is a knowledge and data-intensive task requiring true expertise derived from clinical, pathophysiological and pharmacotherapeutic knowledge. We will be developing a Multidisciplinary Psychoactive Drug Selection advisor system, M-PADS, to support the integration of various types of biomedical information and deliver that integrated information supportive to evidence-based rational drug prescription in the practice of medicine for the drug treatment of individual patients
" |
|
|
| contact |
Paul de Clercq
Medecs
Horsten 2
5612 AX Eindhoven
The Netherlands
Tel.: +31 (0)40 247 4794
Fax : +31 (0)40 246 6508
E-mail : p.a.d.clercq medecs.nl
infomedecs.nl
|
| links |
|
|
| acknowledgements |
| Paul de Clercq, Medecs / Eindhoven University of Technology / Maastricht University |
| page history |
Entry on OpenClinical: 15 March 2004
Last main update: 24 March 2004; 29 March 2005
Design - template v0.3: 25 June 2005. |
|
|
|
|
Contact info