Rule Based Intelligent Diabetes Diagnosis System
It is known that expert systems have been used for many years. By courtesy of the advanced technology and the recent studies made on expert systems, this field of study has been gained popularity and many successful progresses have been made over time. As an evidence of this improvement we can discuss about the results shown by the expert system that gave us very close and sometimes exact values as human decision making.
The purpose of this study is to design diabetes diagnosis system. Acquiring right data is needed for the application of rules to this design. These rules determine whether a person is healthy or diabetes patient, along with its types such as type1 diabetes, type2 diabetes, gestational diabetes, and at risk. VP-Expert rule based system was used to design this diabetes diagnosis system, and this system passed many tests with success. System was tested on 15 patients and able to achieve exact results as doctors. System that we have designed can be used effectively and efficiently to determine diagnoses for diabetes especially in undeveloped and crowded countries where the number of doctors is not enough compared to the population. Due to the annual increasing number of patients, rule based intelligent system targets to reduce the dependence on doctors, and therefore it will help both doctors and patients to make more correct and quicker decisions.
KeywordsExpert system (ES) Diabetes mellitus (DM) VP expert Artificial intelligent (AI) Diabetes diagnose expert system (DDES) Certainty factors (CF)
- 1.Mishkoff, H.: Understanding artificial intelligence. Instrument learning Centre, Dallas, Texas (1985)Google Scholar
- 2.Zadeh, L.A.: Computing with words and perceptions a paradigm shift. In: 2009 Proceedings of the IEEE International Conference on Information Reuse and Integration, Las Vegas, Nevada, USA, pp. 450–452. IEEE Press (2009)Google Scholar
- 3.Sayedah, T., Tawfik, S., Zaki, Y.: Developing an expert system for diabetics’ treatment advices. Int. J. Hosp. Res. 2(3), 155–162 (2013)Google Scholar
- 6.Karray, F.O., de Silva, C.: Soft Computing and Intelligent Systems Design Pearson Education Limited, London, pp. 4–13, 223–224. British library (2004)Google Scholar
- 7.Griffin, N.L., Lewis, F.D.: A rule-based inference engine which is optimal and VLSI implementable. Technical report, Department of Computer Science, University of Kentucky (1989)Google Scholar
- 9.Jackson, P.: Introduction to Expert System Pearson Wesley Longman Limited, Harlow, pp. 2–9. Harlow Essex CM20 2Je, England (1999)Google Scholar
- 10.Jose, A., Prasad, A.: Design and Development of Rule Base Expert System for AACR: A Study of the Application of Artificial Intelligence Techniques in Library and Information Field. Saarbrucken VDM Verlag Publishers, Saarbrücken (2011)Google Scholar
- 12.Akter, M., Uddin, M.S., Hague, A.: Diagnosis and management of diabetes through knowledge based system. In: 2009 13th International Conference on Biomedical Engineering, pp. 1000–1003. Springer, Heidelberg (2009)Google Scholar
- 13.Zeki, T.S., Malakooti, M.V., Ataeipoor, Y., Tabibi, S.T.: An expert system for diabetes diagnosis. Am. Acad. Sch. Res. J. 4(5), 1 (2012)Google Scholar
- 14.Altıparmak, H.: Diabetes diagnose system by using VP expert thesis, Nicosia (2016)Google Scholar