Classification of Drug Effectiveness Based on Patient's Condition Using Text Mining With K-Nearest Neighbor

Abstract

A drug is an ingredient intended to be used in establishing the diagnosis, preventing, reducing, eliminating, and curing a disease or symptom of a disease. The magnitude of the effectiveness of the drug depends on the dosage and sensitivity of the organs of the body. Accuracy in the selection of drugs can be done in several ways, one of which is by conducting a condition analysis and drug review to find out the effectiveness of the drug to be used. Text Mining is one of the disciplines that can be used to extract information from a collection of documents under these conditions. In carrying out the text classification process there are several algorithms that can be used, one of which is the K-Nearest Neighbor (KNN) algorithm, this algorithm has the characteristic that is with an approach to finding cases by calculating the proximity of new cases to old cases. In this study, the dataset is divided into 2 parts, namely 70% training data, and 30% testing data. Based on the results of tests conducted in this study, the KNN algorithm produces an accuracy of 77.86%.The results of such accuracy are also influenced by the many training data used. The more data trained, the better the accuracy value.