Abstract
This research aims to describe a new design of data stream mining system that can analyze medical data stream and make real-time prediction. The motivation of the research is due to a growing concern of combining software technology and medical functions for the development of software application that can be used in medical field of chronic disease prognosis and diagnosis, children healthcare, diabetes diagnosis, and so forth. Most of the existing software technologies are case-based data mining systems. They only can analyze finite and structured data set and can only work well in their early years and can hardly meet today's medical requirement. In this paper, we describe a clinical-support-system based data stream mining technology; the design has taken into account all the shortcomings of the existing clinical support systems.
Highlights
Data Stream Mining is the process of extracting useful information from continuous, rapid data streams
The authors mainly focus on data stream classification, because clinical support systems usually require real-time medical prediction and classification based on multivariate data that have many attributes and terms
A new system is introduced that can analyze medical data streams and can make real-time prediction. This system is based on stream mining algorithm called
Summary
Data Stream Mining is the process of extracting useful information from continuous, rapid data streams. The authors mainly focus on data stream classification, because clinical support systems usually require real-time medical prediction and classification based on multivariate data that have many attributes and terms. Since about year 2000, there have been progressively a handful of decision tree algorithms for data stream mining emerged, such as Very Fast Decision Tree (VFDT) [1] and Concept Adapting Very Fast Decision Tree (CVFDT) [2] These decision trees may not be directly applied for medical use, many supporting tasks are needed, and they will be introduced in this paper. There are some defects in the above clinical decision support systems mainly on traditional data mining algorithms. Cannot handle data stream Difficulty to get the probability knowledge for possible diagnosis and not being practical for large complex systems given multiple symptoms Training process consume so much time that users cannot use the systems effectively It is difficult for experts to transfer their knowledge into distinct rules, and it needs many rules to make system effectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
