Peirs: Automated chemical pathology report interpretation by a pathologist-maintained expert system

Abstract

Provision of a comprehensive interpretative service is an important challenge facing chemical pathologists. Attempts to automate report interpretation using expert systems have been limited in the past by the difficulties of knowledge base maintenance. We have applied a novel knowledge acquisition technique, ripple down rules, in the development of PEIRS (Pathology Expert Interpretative Reporting System), a user-maintained expert system for automating chemical pathology report interpretation. PEIRS operates in batch mode, appending interpretative comments to hard-copy chemical pathology reports. We created over 1200 rules for thyroid (unction tests, arterial blood gases, urinary catecholamines, serum and urine human chorionic gonadotrophin (hCG) and other test sub-groups, in 12 months of operation. A staff pathologist performed all maintenance tasks, as part of his routine duties, without any need for computer programming or knowledge engineering skills. No clerical or other staff involvement was required. Duplication of rule addition for reports requiring multiple comments was the only limitation to coverage of other high volume test groups. PEIRS is the first expert system for the automated interpretation of a broad range of chemical pathology reports which operates in routine use without extra staffing requirements. Removal of traditional knowledge engineering constraints enables a flexible knowledge base which is easily updated by the pathologist. Expert systems based on ripple down rules should allow pathologists in all disciplines to provide a comprehensive automated interpretative service within the context of the total testing process.