Decision support in acute abdominal pain using an expert system for different knowledge bases

Abstract

This paper describes a knowledge-based system for the diagnosis of acute abdominal pain, in which scores and rule sets are integrated. The system is linked to a documentation program via a medical data dictionary and allows an on-line application of knowledge modules to clinical data. Different rule sets were generated by automatic rule generation (C4.5) from a prospective database. The rule sets and two published diagnostic scores were evaluated on a test set, resulting in a diagnostic accuracy of 57% for a general knowledge module and between 44 and 88% for specific knowledge modules. The program is fully functioning and has been evaluated carefully in 14 German hospitals.