Predicting the Effects of Medical Waste in the Environment Using Artificial Neural Networks: A Case Study Qeethara Al-Shayea 1 and Ghaleb El-Refea 2 1 MIS Department, Al-Zaytoonah University of Jordan Amman, Jordan 2 Al Ain University of Science and Technology Abu Dhabi, United Arab Emirates Abstract Protection of the environment from medical waste hazards is becoming a serious problem. There is a big relation between medical waste and disease injury. The main idea of this study is predict the relation between medical wastes and diseases in Hashemite Kingdom of Jordan using Artificial Neural Networks (ANNs) model. There are six predictor parameters associated with solid and liquid wastes in the medical services sector which are affecting the diseases injury. This study deals with two types of diseases the first one is acute hepatitis and the other is typhoid. Generalized Regression Neural Network (GRNN) is used to predict the diseases injury. It is noticed a significant improvement in the prediction made by GRNN due to its generalization property. Results showed that all six parameters associated with solid and liquid medical wastes which have the largest regression value affect the acute hepatitis injuries and the typhoid injuries. It is also showed that the medical waste affected the typhoid injuries in large percentage so the regression is very large. Keywords: Regression, Artificial neural networks, General Regression Network, Prediction, Medical Wastes. 1. Introduction As in many other developing countries, the generation of regulated medical waste (RMW) in Jordan has increased significantly over the last few decades. Despite the serious impacts of RMW on humans and the environment, only minor attention has been directed to its proper handling and disposal [1]. The waste produced in the in the course of health care activities carries a higher potential for infection and injury than any other type of waste [2]. A. Puss, E. Giroult and P. Rushbrook [3] presented an overview of these environmental concerns from landfilling practices and their adverse environmental effects. In their paper, a number of remedial measures needed to minimize these environmental and socio- economic effects are suggested, with in total ten long term and eight short term measures for improving of the solid waste management system of Jordan. Awad et. al. [4] presented research under the assumption that wastes generated from hospitals in Jordan and Irbid were hazardous. Jahandideh et. al. [5] presented two predictor models including artificial neural networks and multiple linear regression were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. Al-Habash and Al-Zu'bi [6] proposed an Idea about the medical waste management in the health sector and its impact on the environment in Jordan, the right and the safe management which include, segregate, classify, collect, processing of these waste may contribute to achieve the main goal which is to reduce the hazardous effect on the local community. 2. Artificial Neural Networks An artificial neural network (ANN) is a computational model that attempts to account for the parallel nature of the human brain. An (ANN) is a network of highly interconnecting processing elements (neurons) operating in parallel. These elements are inspired by biological nervous systems. As in nature, the connections between elements largely determine the network function. A subgroup of processing element is called a layer in the network. The first layer is the input layer and the last layer is the output layer. Between the input and output layer, there may be additional layer(s) of units, called hidden layer(s). Fig. 1 represents the typical neural network. You can train a neural network to perform a particular function by adjusting the values of the connections (weights) between elements. Fig. 1 A typical neural network. IJCSI International Journal of Computer Science Issues, Vol. 10, Issue 1, No 3, January 2013 ISSN (Print): 1694-0784 | ISSN (Online): 1694-0814 www.IJCSI.org 258 Copyright (c) 2013 International Journal of Computer Science Issues. All Rights Reserved.