Honours Project 2012

WELCOME

Acknowledgements

Welcome to the honours project site for Medical Advisor System. This Medical Advisor System is designed to give medical advice on diabetes. In addition, this system is designed to give advice on the following areas:




PROBLEM:


Diabetes mellitus is one of the most common chronic diseases in the world. The World Health Organisation (WHO) estimated that there are 1.3 million people living with diabetes in South Africa. The WHO predict that numbers will double by 2030. Recent surveys indicated that more than 80% of people with diabetes live in low and middle income countries. Research shows that many rural communities have extremely limited access to medical clinics. There is shortage of medical experts and medical facilities.

However, diabetes mellitus is characterized by the raise of sugar levels in the blood. It can be caused by insufficient insulin and/or resistance to insulin. Though the disease cannot be cured completely, it can be well managed or controlled by healthy lifestyle choices. There is a need for a practical nutritional advisor for people with diabetes.

For these reasons, there is a need for a medical advisor system, a system that is easily accessed and used by different users (sophisticated or novice). Although majority of the rural population has limited access to smart-phones, but the few that possess are able to bridge the gap. Regardless of the aforementioned argument, many clinics in rural areas have access to computers thus our system can be installed and can also be at their services.



AIM:


This project is divided into two phases. The aim of the first phase is to develop a prototype knowledge-based expert system for diabetes advice which emulates the decision making ability of a human diabetes expert. This system will be developed using the Java Expert System Shell (JESS). Jess is an expert system programming language. You can read more about Jess on the my blog. Read more about the knoeldge based system here. The aim of the second phase is to provide a speech-based interface to the diabetes expert system using speech recognition and speech synthesis. The interface was developed using Android. Read more about the speech based interface here . The figure below is an overview of the overall MAS system.