A Comparative Study in Predicting Colon Rectum Cancer using Auto Regressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) Models

Abstract

Colon Rectum Cancer is one of the leading cause of cancer deaths worldwide. In this paper, a comparative study is made for the prediction of Colon Rectum Cancer using Auto Regressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN). For more than twenty decades, Box Jenkin's Auto Regressive Integrated Moving Average (ARIMA) technique is one of the most sophisticated extrapolation method for prediction. It predicts the values in a time series as a linear combination of its own past values, past errors and current and past values by using the concept of time Series. Artificial Neural Network (ANN) is a modern Non Linear Technique used for prediction that involve learning and pattern recognition. Based on the data the model is was modeled is designed by using two techniques for a period of 50 years (from 1960 to 2010) and the Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error(RMSE) are obtained to evaluate the accuracy of the models. Results show that ANN model perform much better than the traditional ARIMA model. Since early detection of cancer is the key to improve survival rate, prediction of Colon Rectum Cancer will greatly facilitate the doctors in the diagnosis of the disease.