Expert system in medicine and its application on pulmonary diseases

Abstract

Objective: Our aim is to develop a medical expert system for pulmonary diseases providing practitioners and medical students with the advantages of improving their ability, minimizing the error and cost in diagnosing and developing their medical knowledge.

Material and Methods: CLIPS  has been chosen as a programming environment for this study. A respiratory disease binary decision tree which helps us to create the system database which includes twenty-eight diseases is formed for the inference engine of this program.

Results: The evaluation of this program is based on hundred and eighty-nine patients’ data each is classified into three data types. These are patient’s history and physical findings, radiological data and laboratory data. The combination of them shapes four different data sets for each patient. The diagnosing result for each data set of each patient is compared with diagnosing of gold standards. If both results indicates the same disease this operation of the program is assumed as “accurate”, otherwise as “error”. These operations for the considered each data set are repeated for all patients’ data. The total number of accurate diagnosis is divided by the number of all patients and these accuracy rates are respectively 64.02%, 71.43%, 82.54% and 96.83%.

Conclusion: We can conclude that the accuracy of the system is enhanced with the increasing total number and type of data for each patient. Finally, further improvement on the performance and accuracy of the system may be obtained by designing the program with the self-learning ability.