Location-based Expert System for Diabetes Diagnosis
Keywords:Rule-based Expert System, Forward chaining, Backward chaining, Diabetes Diagnosis.
AbstractUsing expert systems in the medical field has been practiced continuously for the past decades. There are attempts of using expert systems for diabetes diagnosis. In this paper, we go further by proposing an expert system that not only diagnoses diabetes but also suggests the right medication depending on the location where the patient lives and on the symptoms of the patient and other effective factors. This system can be very helpful to many diabetic patients especially to those that are not aware of their disease type or how to control it. The system outputs a list of names of locally available brand names of the medications that suit the diabetes type of the patient and that don’t pose any danger on the health of the patient according to his/her symptoms, effective factors, and results of the patient’s medical tests. Our expert system is capable of reasoning using either forward chaining or backward chaining. The rules in the knowledge base are collected from various sources including trusted Internet websites like MAYO Clinic and FDA.org and articles published in scientific journals. In order to verify the content of the knowledge base, a medical expert and a pharmacist working in Kuwait were consulted.
Ahmad I.M., Alfonse M., Aref M. and Salem A.M. (2015). Reasoning Techniques for Diabetics Expert Systems. Science Direct: Procedia Computer Science Vol. 65, 813 – 820.
Buchmann B. and Duda, R. (1982). Principles of Rule-Based Expert Systems, Advances in Computers, Volume 22, DOI:10.1016/S0065-2458(08)60129-1
Choubey D.K., Paul S. and Dhandhenia V.K. (2017). Rule-based diagnosis system for diabetes. Biomedical Research Volume 28, Issue 12, 5196–5209.
Choubey D.K. and Paul S. (2016). Classification techniques for the diagnosis of diabetes: a review. International Journal of Biomedical Engineering and Technology Volume 21, Issue 1, 15-39.
De Tore A. W. (1989). An Introduction to Expert Systems, Journal of Insurance Medicine Volume 21, Issue 4, 233-236.
Dhivya A.D. and Felix A. (2018). A Fuzzy Rule-based Expert System for T2DM Diagnosis. International Journal of Engineering & Technology Volume 7, Issue 4, 432-435.
Garcia M., Gandhi A., Singh T., Duarte L., Shen R., Dantu M., Ponder S. and Ramirez H. (2001). Esdiabetes (an expert system in diabetes). Journal of Computing Sciences in Colleges Volume 16, Issue 3, 166-175.
Humar K. and Novruz A. (2008). Design of a hybrid system for diabetes and heart diseases, Expert Systems & Applications, Elsevier Volume 35, 82-89.
Margret A.S., Clara M.L., Jeevitha P. and Nandhini R.T. (2013). Design of a Diabetic Diagnosis System Using Rough Sets. Cybernetics and Information Technologies, Volume 13, Issue 3, 124-139.
Medication Guides, (2018). Drug Safety and Availability, US Food & Drug Administration, Retrieved on 8 Aug. 2018, https://www.fda.gov/drugs/drug-safety-and-availability/medication-guides
Prajapati H., Pal S.K. and Jain A. (2016). Expert System for Diagnosis of Diabetes: A Review. International Journal of Advances in Engineering & Technology Volume 9, Issue 5, 532-537.
Saleh, A. (2018). 420,000 diabetic patients in Kuwait, Kuwait tiles, Retrieved on 12 Dec. 2018, https://news.kuwaittimes.net/website/420000-diabetic-patients-in-kuwait/
Sharaa, A. (2019). 23% prevalence of diabetes in Kuwait. Kuwait Times, Issue:28/04/2019, Retrieved on 11/9/2019, https://news.kuwaittimes.net/website/23-prevalence-of-diabetes-in-kuwait-doctor
Sminkey L. (2016). Kuwait Profile, Diabetes country profiles 2016, World Health Organization, http://origin.who.int/diabetes/country-profiles/kwt_en.pdf
Vorvick L.J., Zieve D., Eltz D.R., Slon S. and Wang, N. (2019). Contraindication: MedlinePlus Medical Encyclopedia. MEDLINE. United States National Library of Medicine, Retrieved 6 Nov. 2019, https://medlineplus.gov/ency/article/002314.htm