The impact of feature selection on medical document classification

Medical document classification is still one of the popular research problems inside text classification domain. Apart from some text data compiled from hospital records, most of the researchers in this field evaluate their classification methodologies on documents retrieved from MEDLINE database. OHSUMED is one of the widely used datasets containing MEDLINE documents as multi-labeled. In this study, the impact of feature selection on medical document classification is analyzed using two datasets containing MEDLINE documents. The performances of two different feature selection methods namely Gini Index and Distinguishing Feature Selector are analyzed using two pattern classifiers. These pattern classifiers are Bayesian network and C4.5 decision tree. As this study deals with single-label classification, a subset of documents inside OHSUMED and a self-constructed dataset is used for assessment of feature selection methods. Due to having low amount of documents for some categories in self-compiled dataset, only documents belonging to 10 different disease categories are used in the experiments for both datasets. Experimental results show that the combination of Distinguishing Feature Selector and Bayesian Network classifier gives more accurate results in most cases than the others.