الفهرس 
Thesis Motivation
Introduction to Diabetic InformaticsOnly 14 pages are availabe for public view
 |  | from | 135 |  |  |
| | | from | 135 | | |
Abstract
Diabetes is a serious health problem today. It is the single most important metabolic disease. It can affect nearly every organ system in the body. Diabetics find difficulty to observe a healthy lifestyle in their diets and eating patterns. Treatment of a diabetic requires a strict regimen that typically includes carefully calculated and controlled diet. Type-2 diabetes is becoming more common due to risk factors like older age, obesity, lack of exercise, family history of diabetes and heart diseases. Most of the people are unaware that they are in risk of or may even have type-2 diabetes. Type-2 diabetes is the most common form of diabetes.
On the other hand, Knowledge based expert systems (KBS) certainly became an essential tool for diagnosis and personalized treatments. They are widely used in domains where knowledge is more prevalent than data and that require heuristics and reasoning logic to derive new knowledge. The knowledge in a KBS is stored in a knowledge base that is separate from both the control and inference programs and can be represented by various formalisms, such as frames, Bayesian networks and production rules. Recently, expert systems technology provides efficient tools for diagnosing diabetes and hence providing a sufficient treatment. The research in diabetic systems is important for both medical staff and diabetes patients. An efficient tool for diagnosing diabetes and hence providing a sufficient treatment is urgently needed for helping both specialist doctors and patients.
Actually, many rural communities in Sudan have extremely limited access to diabetic diet centers. People travel long distances to clinics or medical facilities, and there is a shortage of medical experts in most of these facilities. This results in slow service, and patients end up waiting long hours without receiving any attention. Therefore, diabetic diet expert systems can play
V
a significant role in such cases where medical experts are not readily available.
Based on the pervious motivations, this thesis proposes an efficient expert system for diabetic Type-2 diet in Sudan. The proposed expert system went through many stages starting from requirement specification of the problem, addressing the technical difficulties, knowledge acquisition for the healthy food that helps diabetic people of Type-2 to monitor and control the proper diet, and challenges in the designing phase, implementation constrains and finally testing the developed Sudanese intelligent medical expert system.
Visual prolog was used for designing the graphical user interface and the implementation of the system. The Visual Programming Interface (VPI) is a high-level Application Programming Interface (API) and is designed to make it easy for Prolog applications to provide sophisticated user interfaces utilizing the graphical capabilities of today’s operating systems and display hardware. It makes possible to create portable source code. Rule base used as knowledge representation and backward chaining as inference engine.
Our results showed that the proposed intelligent expert system for diabetics type-2 could successfully connect all the gathered information during knowledge acquisition and performed inferences through its knowledge engine to supplement a meal planner of a recommended five meals a day for every patient. These are breakfast, lunch, snack1, dinner and snack2.These meals suggest appropriate diet using calories-based or serving-based for Sudanese diabetics. Therefore, the proposed expert system is a helpful tool that reduces the workload for physicians and provides diabetics with simple and valuable assistance.