Decision support for infectious diseases—a working prototype

• Published in: International journal of medical informatics Vol. 64; no. 2; pp. 331 - 340
• Main Authors: Joch, J., Dudeck, J.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Shannon Elsevier Ireland Ltd 01.12.2001; Elsevier
• Subjects: Artificial Intelligence; Biological and medical sciences; Computerized management (medical records, files, hospital management); Computerized, statistical medical data processing and models in biomedicine; Cross Infection; Decision support system; Decision Support Systems, Clinical; Engines; Hospital Information Systems; Humans; Hygiene; Infection Control; Medical management aid. Diagnosis aid; Medical sciences; Nosocomial infections; Decision support system; Engines; Nosocomial infections; Human; Nosocomial infection; Vocabulary; Dictionaries; Prototype; Software development; Information system; Relational database; Search engine; Infection; Biomedical data processing; Computer system; Diagnostic aid; Medical application; Biomedical engineering
• ISSN: 1386-5056; 1872-8243
• DOI: 10.1016/S1386-5056(01)00209-X

This paper presents a decision support system for nosocomial infections and its integration in the large HIS of the University Hospital of Giessen. The system comprises five different engines and a data dictionary. It is designed to detect hospital acquired infections even in a situation where only a restricted amount of clinical data is available (the data is split up in different information systems). Furthermore the model prevents time consuming manual data entry. The five engines split the main task into: (1) a preselection, which sorts out patients who definitely do not have a nosocomial infection; (2) a rule based reasoning process which detects patients likely to have such an infection; (3) an alarm process which is responsible for the presentation of the alert; (4) an explanation process to follow up the reasoning; and (5) statistic tools to answer specific hygienic questions. A data dictionary supplies the controlled vocabulary, which is required to understand data structures used in the different clinical subsystems and may those with each other.