Intelligent diagnosis system for jaundice based on dynamic uncertain causality graph
by Nan Deng; Shichao Gengy; Shaorui Hao; Qin Zhang; Lanjuan Liz
International Journal of Information and Communication Technology (IJICT), Vol. 20, No. 4, 2022

Abstract: The healthcare system in China still has some defects such as the imbalance of medical resources. With the development of computer science, medical diagnostics digitisation has become possible. In this paper, a medical diagnosis system for jaundice based on dynamic uncertain causality graph (DUCG) is proposed. After a brief introduction to DUCG, a knowledge base of the DUCG for jaundice diagnosis is built. It can represent the experienced knowledge of human experts explicitly with graphical symbols. During the construction of the knowledge base, how to classify the medical diagnosis data in a structural and standard manner is important. In this paper, we propose to classify these data as four categories: general symptoms, medical signs, results of laboratory tests and results of imaging examinations. The first two form the general clinical information and the last two are further information. Each category can be further classified as sub-categories, so that users are easy to find the right position to fill the clinical information. Based on such designed DUCG medical software, 203 randomly selected jaundice related cases out of 3,985 case records of a hospital are tested. The final diagnostic accuracy of the system reaches 99.01%.

Online publication date: Wed, 01-Jun-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Information and Communication Technology (IJICT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com