Title: K-means and DBSCAN for look-alike sound-alike medicines issue

Authors: Souad Moufok; Anas Mouattah; Khalid Hachemi

Addresses: Institute of Maintenance and Industrial Safety, University of Oran 2 Mohamed Ben Ahmed, B.P 1015 El M'naouer 31000 Oran, Algeria ' Institute of Maintenance and Industrial Safety, University of Oran 2 Mohamed Ben Ahmed, B.P 1015 El M'naouer 31000 Oran, Algeria ' Institute of Maintenance and Industrial Safety, University of Oran 2 Mohamed Ben Ahmed, B.P 1015 El M'naouer 31000 Oran, Algeria

Abstract: The goal of this study is to analyse the application of data mining techniques in clustering drug names based on their spelling similarity in order to reduce the occurrence of dispensing errors caused by look-alike sound-alike medicine confusion, as they considered one of the most common causes of dispensing errors. Two unsupervised data mining methods, k-means and DBSCAN, were used in conjunction with two similarity measures, BiSim and Levenshtein. The results of the study showed that the approach is effective in identifying potential confusable medicines, with BiSim-based k-means clustering being favoured with a silhouette score of 0.5.

Keywords: look-alike sound-alike; LASA; data mining; medication errors; dispensing errors; k-means; DBSCAN.

DOI: 10.1504/IJDMMM.2024.136215

International Journal of Data Mining, Modelling and Management, 2024 Vol.16 No.1, pp.49 - 65

Received: 21 Feb 2022
Received in revised form: 07 Feb 2023
Accepted: 26 Mar 2023
Published online: 22 Jan 2024 *