Guideline-based careflow systems

This paper describes a methodology for achieving an efficient implementatio n of clinical practice guidelines. Three main steps are illustrated: knowle dge representation, model simulation and implementation within a health car e organisation. The resulting system can be classified as a 'guideline-base d careflow management system'. It is based on computational formalisms repr esenting both medical and health care organisational knowledge. This aggreg ation allows the implementation of a guideline, not only as a simple remind er, but also as an 'organiser' that facilitates health care processes. As a matter of fact, the system not only suggests the tasks to be performed, bu t also the resource allocation. The methodology initially comprehends a gra phical editor, that allows an unambiguous representation of the guideline. Then the guideline is translated into a high-level Petri net. The resources , both human and technological necessary for performing guideline-based act ivities, are also represented by means of an organisational model. This all ows the running of the Petri net for simulating the implementation of the g uideline in the clinical setting. The purpose of the simulation is to valid ate the careflow model and to suggest the optimal resource allocation befor e the careflow system is installed. The final step is the careflow implemen tation. In this phase, we show that the 'workflow management' technology, w idely used in business process automation? may be transferred to the health care setting. This requires augmenting the typical workflow management sys tems with the flexibility and the uncertainty management, typical of the he alth care processes. For illustrating the proposed methodology, we consider a guideline for the management of patients with acute ischemic stroke. (C) 2000 Elsevier Science B.V. All rights reserved.