Building a fuzzy expert system for assessing the severity of pneumonia
The paper describes the process of building a fuzzy expert system for assessing the severity of pneumonia. The use of fuzzy logic is an urgent direction in cases of incomplete certainty when making a medical diagnosis. Human health depends on making the right decision, as it can be difficult for a doctor to choose the correct diagnosis and treatment of pneumonia. To develop a medical expert system, we considered scales and algorithms for assessing the prognosis of the severity of community-acquired pneumonia PORT (PSI), CURB/CRB-65 and SMART-COP/SMART-CO. We strive to contribute the results of our research to the development of medical software products, namely, to increase the efficiency of medical services using artificial intelligence. Python and Prolog programming languages were used to develop the client-server application. The Django framework was used to develop the client part, and the PySwip module was used to process knowledge bases. The knowledge base of the expert system was developed using the SWI-Prolog software environment, which supports the necessary software libraries that provide the construction of the graphical shell of the expert system, as well as dynamic processing of fuzzy rules. The paper outlines the main stages of the life cycle of creating a system using fuzzy logic, which include all the key stages of system design. To test the knowledge base, a graphical interface of the system was developed using the XPCE cross-platform library, which is included in the SWI-Prolog software environment. The purpose of the study is to develop and implement a software module using fuzzy logical inference in a medical information system.
Expert systems; Fuzzy logic; Knowledge base; SWI-Prolog