Analysis Of Drug Data Mining With Clustering Technique Using K-Means Algorithm. Issue 1 (June 2021)

• Record Type: Journal Article
• Authors: Lia Hananto, April; Assiroj, Priati; Priyatna, Bayu; Nurhayati, ; Fauzi, Ahmad; Yuniar Rahman, Aviv; Shofiah Hilabi, Shofa
• Is Part Of: Journal of physics. Volume 1908:Issue 1(2021)
• Publication Date: 2021-06
• Subjects: Drug Data -- Data Mining -- Clustering Technique -- K-Means Algorithm.; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1908/1/012024
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Data processing is very important in the development of information technology. Almost all fields of work have information data. Data can be used to help analysis in work. At present, health information data is very important to be processed in order to help medical personnel to make decisions. So that the results of the right decision to help patients. Lately, drug data has been misused for information eliminating a depressed patient without a doctor's prescription with a total data of 53766. The results shown are very large. So it requires very much attention from the government. As a result of the deviation of information and applied to the patient will result in death. Therefore, research needs to be conducted to group data on drug data. The source of research data is obtained from the UCI Machine Learning Repository Education website. The method proposed in this research is data mining. This solution can help researchers in the analysis of these data. One technique in data mining with clustering is using the K-means algorithm. The variables used are drug name, condition, useful count. The first research results can classify three categories consisting of using the highest drugs, using medium drugs and using lace drugs. Then the accuracy of the data is obtained with condition 99.45% valid records 53471, drug name 100% with valid records 53766, useful count 100% with valid records 53766.