A Knowledge Based System for Diagnosing Nosocomial Infections

This paper describes the design, implementation, and evaluation of a knowledge based prototype for diagnosing nosocomial infections. The prototype uses a consultative session to diagnose three major types of infection: urinary tract infection, bacteremia, and surgical wound infection. The system eva...

Full description

Saved in:
Bibliographic Details
Main Authors: Landry, Gail, Beyt, B. Eugene, Delcambre, Lois M. L.
Format: Conference Proceeding
Language:English
Subjects:
Clinical Decision Support. Computer-Aided Diagnosis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes the design, implementation, and evaluation of a knowledge based prototype for diagnosing nosocomial infections. The prototype uses a consultative session to diagnose three major types of infection: urinary tract infection, bacteremia, and surgical wound infection. The system evaluates the results of microbiology and laboratory testing, includes rules based on clinical events, and determines onset dates. The prototype was implemented in Prolog and was tested for its ability to confirm diagnosis in 51 cases of nosocomial infection.
ISSN:0195-4210