A Fuzzy Inference Map approach to cope with uncertainty in modeling medical knowledge and making decisions

Article type: Research Article

Authors: Papageorgiou, Elpiniki I.

Affiliations: Department of Informatics and Computer Technology, Technological Educational Institute of Lamia, 3rd Old National road Lamia-Athens, 35100 Lamia, Greece. E-mail: [email protected]

Abstract: In this work, the Fuzzy Inference Map approach (also known as Fuzzy Cognitive Map) is investigated to handle with the problem of risk analysis and assessment of pulmonary infections during the patient admission into the hospital. A Fuzzy Inference Mapping is an artificial cognitive structure within which the relations between the elements of a mental landscape can be used to assess the impact of these elements. It has the advantageous features of representing medical knowledge in a symbolic manner, giving system's transparency, interpretability of results and easiness of use by non experts. Fuzzy Cognitive Map (FCM) proved by the literature as an appropriate reasoning tool to explicitly encode the knowledge and experience accumulated on the operation of a complex system. This study presents a first tool for making decisions in medical domain that will help physicians, through the design of the knowledge representation and reasoning using FCM to automate the decision making process in the case of infectious diseases prediction. After drawing the FCM model for pulmonary risk prediction, the Decision Making Trial and Evaluation Laboratory (DEMATEL) method is implemented to analyze the map and outrank the concepts according to their importance for physicians. A number of different scenarios concentrated on the pulmonary infections are examined to demonstrate the application of the proposed methodology and its prediction capabilities. This work proves that FCM can handle efficiently with uncertainty in modeling medical knowledge.

Keywords: Fuzzy cognitive maps, knowledge-based systems, modeling, knowledge representation, medical decision making, prediction

DOI: 10.3233/IDT-2011-0108

Journal: Intelligent Decision Technologies, vol. 5, no. 3, pp. 219-235, 2011