M.Sc. / Surgical patients admitted to an intensive care unit, are susceptible to infection by a large number of micro-organisms. Host defence mechanisms are breached by severe injuries or operations, or the use of life-support systems such as ventilators, catheters and endotracheal tubes. These organisms, some of which are resistant to antibiotics, can therefore invade sterile tissue. Although tissue samples from infected sites are sent to a laboratory to be analyzed, treatment of the patient has to commence before the results are known. Intelligent computer systems, of which expert systems are one of the most popular applications, can be utilized to support diagnostic and therapeutical decisions. This thesis describes the development of an expert system that supports clinical decision-making in the diagnosis and treatment of hospital-aquired pneumonia in an intensive care unit. Input data required by the expert system module are extracted from a data base with patient records. The data base and expert system module communicates by means of a program written in a conventional programming language. The system, which is only a prototype, can be extended to include additional expert system modules addressing other infections. Aquiring knowledge to be encoded in the expert system's knowledge base, remains a problem. In this case an existing scoring system that assigns weights to measurements and the outcomes of certain investigations, is used to obtain a score according to which pneumonia can be diagnosed. The infection is subsequently classified as one of several categories, according to existing guidelines. Appropriate therapy is recommended. The system can also consult a file containing sensitivities of bacteria for antibiotics for the unit, in order to facilitate the choice of drugs. The system has been implemented and tested with a few cases.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:uj/uj:9226 |
| Date | 14 August 2012 |
| Creators | Schoeman, Isabella Lodewina |
| Source Sets | South African National ETD Portal |
| Detected Language | English |
| Type | Thesis |
Page generated in 0.0023 seconds