Knowledge Discovery from Confusion Matrix of Pruned CART in Imbalanced Microarray Data Ovarian Cancer Classification

Abstract

Purpose: The results of microarray data analysis is important in cancer diagnosis, especially in early stages asymptomatic cancers like ovarian cancer. One of the challenges in analyzing microarray data is the problem of imbalanced data. Unfortunately, research that carries out cancer classification from microarray data often ignores this challenge, so that it doesn’t use appropriate evaluation metrics. It makes the results biased towards the majority class. This study uses a popular evaluation metric “accuracy” and an evaluation metric that is suitable for imbalanced data “balanced accuracy (BA)” to gain information from the confusion matrix regarding accuracy and BA values in case of ovarian cancer classification.Methods: This study use Classification and Regression Tree (CART) as the classifier. CART optimized by pruning. CART optimal is determined from the results of CART complexity analysis and confusion matrix.Results: The confusion matrix and CART interpretations in this research show that CART with low complexity is still able to predict majority class respondents well. However, when none of the data in the minority class was classified correctly, the accuracy value was still quite high, namely 86.97% and 88.03% respectively at the training and testing stages, while the BA value at both stages was only 50%.Novelty: It is very important to ensure that the evaluation metrics used match the characteristics of the data being processed. This research illustrate the difference between accuracy and BA. It concluded that that classification of an imbalanced dataset without doing resampling can use BA as evaluation metric, because based on the results, BA is more fairly to both classes.