Predicting the outcome of a graft transplant with high level of accuracy is a challenging task. To answer the challenge, data mining can play a significant role. The goal of this study is to compare the performances and features of an Artificially Intelligent (AI)-based data mining technique namely Artificial Neural Network with Logistic Regression as a standard statistical data mining method to predict the outcome of kidney transplants over a 2-year horizon. The methodology employed utilizes a dataset made available to us from a kidney transplant database. The dataset embodies a number of important properties, which make it a good starting point for the purpose of this research. Results reveal that in most cases, the neural network technique outperforms logistic regression. This study highlights that in some situations, different techniques can potentially be integrated to improve the accuracy of predictions.

No abstract

No abstract

Social and health informatics has the potential of improving the general wellbeing and health of individuals. Although the structure and nature of health facilities and services in some countries may pose a challenge for a short while, such obstacles according to many studies will be streamlined in the near future. The widespread utilization and implementation of healthcare information system in the day-to-day health care operations will lead to cost effective clinical trials and selfhealthcare management. On the other hand, recent rapid development of computer technology in this area has introduced a data explosion challenge. This paper provides brief background information on Social Informatics and e-Health Systems. Follow by an overview of two hybrid intelligent techniques that might be utilized as a new generation of predictive analytics for big data particularly for knowledge discovery in big data and decision making processes in social systems.

Recent rapid development of computer technology has introduced a data explosion challenge. In addition, data mining and multi agent techniques are known as a very popular approach for dealing with complex datasets. Such a hybrid approach can be considered as an effective approach for the development of intelligent decision support systems in health domain. In this paper we propose an improved data mining and multi agent technique called DMMA, which uses a real time agent mining approach to mine large datasets in a distributed environment. This study found that the processing speed is improved as the result of the multi-agent mining approach, although there can be a corresponding marginal loss of accuracy. This loss of accuracy gap tends to close over time as more data becomes available.

No abstract

No abstract

No abstract