A strategy for developing practice guidelines for the ICU using automated knowledge acquisition techniques

Objectives. To implement practice guideline entry tools in a reminder syste m in order to provide decision support to health care workers in clinical c are and emergency care environments. To design a knowledge acquisition envi ronment that enables physicians to formulate, update, and verify guidelines without the assistance of a knowledge engineer. Methods.We developed a kno wledge acquisition environment for the Intensive Care Unit (ICU) consisting of 1) a graphical knowledge acquisition tool, 2) tools that perform logica l and semantic tests on proposed guidelines, 3) a Patient Data Management S ystem (PDMS) containing clinical patient data, and 4) an expert system that reminds ICU health care workers of inconsistencies between a treatment pla n and implemented guidelines. Physicians enter the guidelines using the kno wledge acquisition tool, after which consistency and correctness tests are performed on the guidelines. The guidelines are then transferred to the kno wledge base of the reminder system and validated by applying the new guidel ines 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 dai ly practice. Results. ICU physicians used the knowledge acquisition tool to enter 58 guidelines into the reminder system's knowledge base. These guide lines were tested on a data set consisting of 803 previously admitted patie nts. As a result, 27 guidelines fired at least once, generating 406 reminde rs in total. Of the 406 generated reminders, 356 (88%) were issued correctl y 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 n ot the most appropriate ones, and 3) there was a potential risk involved. A ll false alarms were caused by the fact that the corresponding guidelines w ere not specific enough to handle certain exceptions. As a result of this a nalysis, the guidelines could be improved in such a way as to eliminate all false alarms. Conclusions. These first results demonstrate that this botto m-up knowledge acquisition strategy, implemented by the automated knowledge acquisition tools, enables medical specialists to improve the quality of c omputer support in an ICU without assistance of a knowledge engineer.