Christian Trendelenburg | PubMed Health

PubMed2004

Medical expert systems developed in j.MD, a Java based expert system shell: application in clinical laboratories.

Growing complexity of diagnostic tests, combined with increased workload, stringent laboratory accreditation demands, continuous shortening of turn-around-time and budget restrictions have forced laboratories to automate most of their iterative tasks. Introduction of artificial intelligence by means of expert systems has gained an important place in this automation process. Different parts of clinical laboratory activity can benefit from their implementation and the present project deals with one aspect, namely the clinical interpretation of diagnostic tests. This paper describes how j.MD, a new Java based expert system shell, was used to reprogram the expert system for interpretation of amylase isoenzyme patterns that has been in use for many years in our laboratory, and that was originally programmed in Pro.MD, a Prolog based expert system shell. One of the most important advantages of the j.MD system is its bidirectional link with the laboratory information system. This project shows how expert systems for the interpretation of complex diagnostic tests that demand specific expertise can become an integrated part of the automated clinical chemistry lab.

Alkaline Phosphatase↗

PubMed2003

Quality assurance for cerebrospinal fluid protein analysis: international consensus by an Internet-based group discussion.

A group of neurologists and clinical neurochemists representing twelve countries worked towards a consensus on laboratory techniques to improve the quality of analysis and interpretation of cerebrospinal fluid (CSF) proteins. Consensus was approached via a virtual Lotus Notes-based TeamRoom. This new approach respecting multicultural differences, common views, and minority opinions, is available in http://www.teamspace.net/ CSF, presenting the implicit, complementary version of this explicit, printed consensus. Three key recommendations were made: CSF and (appropriately diluted) serum samples should be analyzed together in one analytical run, i.e., with reference to the same calibration curve. Results are evaluated as CSF/serum quotients, taking into account the non-linear, hyperbolic relation between immunoglobulin (Ig)- and albumin-quotients rather than using the linear IgG index or IgG synthesis rate. Controls should include materials with values within the reference ranges (IgM: 0.5-1.5 mg/l; IgA: 1-3 mg/l; IgG: 10-30 mg/l and albumin: 100-300 mg/l). The physiological, methodological and clinical significance of CSF/serum quotients is reviewed. We confirmed the previous consensus on oligoclonal IgG, in particular the usefulness of the five typical interpretation patterns. The group compared current external and internal quality assurance schemes and encouraged all members to maintain national or local traditions. Values for acceptable imprecision in the CSF quality assurance are proposed.

Albumins↗