Date of Award





Master of Science


TSYS School of Computer Science


Medical diagnosis can be challenging because of a number of factors. Uncertainty in the diagnosis process arises from inaccuracy in the measurement of patient attributes, missing attribute data and limitation in the medical expert’s ability to define cause and effect relationships when there are multiple interrelated variables. Given this situation, a decision support system, which can help doctors come up with a more reliable diagnosis, can have a lot of potential. Decision trees are used in data mining for classification and regression. They are simple to understand and interpret as they can be visualized. But, one of the disadvantages of decision tree algorithms is that they deal with only crisp or exact values for data. Fuzzy logic is described as logic that is used to describe and formalize fuzzy or inexact information and perform reasoning using such information. Although both decision trees and fuzzy rule-based systems have been used for medical diagnosis, there have been few attempts to use fuzzy decision trees in combination with fuzzy rules. This study explored the application of fuzzy logic to help diagnose liver diseases based on blood test results. In this project, inference systems aimed at classifying patient data using a fuzzy decision tree and a fuzzy rule-based system were designed and implemented. Fuzzy decision tree was used to generate rules that formed the rule-base for the diagnostic inference system. Results from this study indicate that for the specific patient data set used in this experiment, the fuzzy decision tree-based inferencing out performed both the crisp decision tree and the fuzzy rule-based inferencing in classification accuracy.