The use of knowledge-based systems to improve medical knowledge about urine analysis

Urine protein diagnostics has developed into a routine method for screening and monitoring kidney diseases. It is based on the quantitative measuremen t of total protein, albumin, alpha(1)-microglobulin, immunoglobulin G and a lpha(2)-macroglobulin (all related to urine creatinine), as well as a dipst ick screening. The excretion pattern of the marker proteins allows differen tiation of haematuria, leukocyturia and proteinuria and to assign them to p rerenal, renal and postrenal causes. In order to provide the clinical partn er not only with pure analytical results, but to support clinical decision making by an interpretative report, a urine protein expert system (UPES) ha s been developed. Based on a database containing more than 500 excretion pa tterns of patients with known diagnoses, a knowledge base was extracted. In its modules plausibility control, glomerular filtration rate, hematuria, l eukocyturia and proteinuria, IF-THEN-rules interpret the given patterns and select matching text elements. The knowledge base has been integrated in t he modem expert system shell WILAS, and the resulting interpretation system has been thoroughly verified and validated. An internal acceptance study r evealed that urine protein differentiation is widely accepted as a diagnost ic option and that its interpretation, provided with the help of UPES, is a ppreciated as a service. In an external study, the usability of UPES in rou tine and its knowledge representation was evaluated in Il centres consistin g of laboratories and nephrological partners. Over seven months, more than 500 cases were interpreted using UPES and documented by questionnaires. The discussion of the results at a user conference revealed that the problem o f analytical standardisation as well as the common definition of diagnostic terms by laboratory staff and clinicians play a crucial role for the use o f knowledge-based systems in laboratory medicine. Whereas the user interfac e of UPES was judged very heterogeneously, the correctness of the proposed interpretations was unanimously rated as "good". As a result of the evaluat ion, the user interface has been modernised. The knowledge base has been ex tended to address paediatric issues as well, and to take clinical informati on and previous findings into consideration. (C) 2000 Elsevier Science B.V. All rights reserved.