Ea. Balas et al., AN EXPERT-SYSTEM FOR PERFORMANCE-BASED DIRECT DELIVERY OF PUBLISHED CLINICAL-EVIDENCE, Journal of the American Medical Informatics Association, 3(1), 1996, pp. 56-65
Citations number
21
Categorie Soggetti
Information Science & Library Science","Computer Science Information Systems","Information Science & Library Science","Medical Informatics
Objective: To develop a system for clinical performance improvement th
rough rule-based analysis of medical practice patterns and individuali
zed distribution of published scientific evidence. Methods: The Qualit
y Feedback Expert System (QFES) was developed by applying a Level-5 ex
pert system shell to generate clinical direct reports for performance
improvement. The system comprises three data and knowledge bases: 1) a
knowledge base of measurable clinical practice parameters; 2) a pract
ice pattern database of provider-specific numbers of patients and clin
ical activities; and 3) a management rule base comprising ''redline ru
les'' that identify providers whose practice styles vary significantly
. Clinical direct reports consist of a table of practice data highligh
ting individual utilization vs recommendation and selected pertinent s
tatements from medical literature. Results: The QFES supports integrat
ion of recommendations from several guidelines into a comprehensive an
d measurable quality improvement plan, analysis of actual practice pat
terns and comparison with accepted recommendations, and generation of
a confidential individualized direct report to those who significantly
deviate from clinical recommendations. The feasibility of the practic
e pattern analysis by the QFES was demonstrated in a sample of 182 uri
nary tract infection cases from a primary care clinic. In a set of cli
nical activities, four questions/procedures were associated with signi
ficant (p < 0.001) and unexplained variation. Conclusion: The QFES pro
vides a flexible tool for the implementation of clinical practice guid
elines in diverse and changing clinical areas without the need for spe
cial program development. Preliminary studies indicate utility in the
analysis of clinical practice variation and deviations. Using data obt
ained through a retrospective chart audit, the QFES was able to detect
overutilization, and to identify nonrandom differences in practice pa
tterns.