Proceedings of the 5 Asian Mathematical Conference, Malaysia 2009
DESIGNING A DISEASE DIAGNOSIS SYSTEM BY USING FUZZY SET THEORY Ahmad Mahir R., Asaad A. Mahdi and Ali A. Salih School of Mathematical Sciences, Faculty of Science and Technology Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, MALAYSIA E-mail: firstname.lastname@example.org ; email@example.com ; firstname.lastname@example.org Abstract: Many diseases affecting millions of people every day. Information technology could be used to reduce the mortality rate and waiting time to see the specialist. As clinical decision making inherently requires reasoning under uncertainty, expert systems, fuzzy set theory and fuzzy logic are a highly suitable basis for developing knowledge based systems in medicine for tasks such as diagnosis of diseases, the optimal selection of medical treatments, and for real time monitoring of patient data. Our goal is to develop a methodology using fuzzy set theory to assist general practitioner in diagnosing and predicting patients condition from certain “ rules based on experience ”. Medical practitioner other than specialists may not have enough expertise or experience to deal with certain high risk diseases. With this system the patients with high risk factors or symptoms could be short listed to see the specialists for further treatment. The intuition is based on doctors ability to make initial judgment based on his study and experience . In this paper we designed a questionnaire to collect the data needed. We chose a random sample of 170 patient from clinics and hospitals. The questionnaire depends on three different sets . The first set is the diseases symptoms set, which contain information on symptoms of diseases such as fever, high temperature, headache, rash, vomiting, etc.. The second set is the diseases set ( chicken pox, Hepatitis B, etc.),and finally the patients set ( a sample of 49 patients), the next step was to form the membership functions for each symptom, and then the membership value was evaluated on the basis of the answers to the questions relative to the particular feature, for the start, only chicken pox and Hepatitis B were considered in the analysis, then the next step will be expanding to include four other diseases such as Dengue, Measles, Flu, and Infectious mononucleosis.
Key Words : Fuzzy sets, fuzzy max-min relations, Membership values, Medical diagnosis, Expert systems. 1. Introduction
Medical diagnosing is the art of determining a person's pathological status from an available set of findings (Steimann & Adlassnig,1997). It is a problem complicated by many factors and its solution involves literally all of a human's abilities including intuition and the subconscious, patients coming to the doctor showing symptoms and signs and the doctor will conclude which disease these phenomena mean. 2. Medical Knowledge The history of medical diagnosis is a history of intensive collaboration between physicians and mathematicians respectively (Seising et al.,1999), In the 1960s and 1970s various approaches to computerized diagnosis arose using Bayes rule, factor analysis, and decision analysis, On the other side artificial intelligence approaches came in to use, e.g., Dialog(Diagnostic Logic),and Pip(present illness program), which were programs to simulate the physicians reasoning in information gathering and diagnosis using databases in form of networks of symptoms and diagnoses. We use the term symptom for many information about patients state of health, signs laboratory test results, ultrasonic results, and x- ray findings. Based on this information a physician has to find a list of diagnostic possibilities for the patient, the certain information about relationship that exists between symptoms and symptoms, symptoms and diagnoses, diagnoses and diagnoses and more complex relationships of the combination of symptoms and diagnoses to a symptom or diagnoses, are formalization of what is called medical knowledge. In...
References: 1. 2. 3. 4. Klir,G,J. and Folger ,T.A. , (1988), fuzzy sets, uncertainty and information , Prentice Hall, New Jersey, p71-74. Nguyen, H.T., Prasad,N.R.,Walker,C.L.,Walker,E.A (2003), A first course in fuzzy and neural control, Chapman& Hall, p 117-119. Radha, R., and Rajagopalan,S.P., (2007), Fuzzy logic Approach for Diagnosis of Diabetics, information technology journal 6(1):96-102. Schuerz, M., Adlassnig, K-P, Lagor, C., Scheide, B. and Grabner, G.(1998), Definition of fuzzy sets representing medical concepts and acquisition of fuzzy relationships between them by semi-automatic procedures, medical information system. Seising,R., Schuh,C., and Adlassnig, K-P, (1999), Medical knowledge , fuzzy sets, and Expert systems. Seising , R,(2004), A history of medical diagnosis using fuzzy relation (draft paper, fuzziness in finland 04(fif04)) Unpublished paper. Steiman, F.,and Adlassnig, K-P, fuzzy medical diagnosis. Vig, R., Handa, N.M., Bali,H.K., Sridher, (2004), Fuzzy Diagnostic systems for Coronary Artery Disease. Vol 85
5. 6. 7. 8.
Please join StudyMode to read the full document