GASTON: an architecture for the acquisition and execution of clinical guideline-application tasks

Recently, studies have shown the benefits of using clinical guidelines in t he practice of medicine. There have been numerous efforts to develop clinic al decision support systems that support guideline-based care in an automat ed fashion, covering a wide range of clinical settings and tasks. Despite t hese efforts, only a few systems progressed beyond the prototype stage and the research laboratory. For guideline-based clinical decision support syst ems to be successful, a balance must be made between intuitive bur imprecis e representations usually encountered by most of today's systems and repres entations that support a strong underlying clinical performance model. The project described in this paper tries to achieve such a balance. It present s the GASTON architecture that contains a set of reusable software componen ts for the application of guidelines, including design-time components to f acilitate 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 de velop several guideline representation models such as a rule-based represen tation to model rule-based guidelines and guideline representation models t hat address more complex tasks. Also, decision support systems that incorpo rate these models were developed with the architecture. For the representat ion and application of various classes of guidelines, rules were also viewe d as instances of more complex tasks. By identifying similar characteristic s of sets of rules, we developed several tasks such as a drug interaction a nd drug contraindication task. Based on these models, we have developed and validated guidelines and decision support systems for use in several appli cation domains such as intensive care, family physicians and psychiatry. In order to be able to represent more complex time-oriented plans, new guidel ine representation models are being developed.