Leveraging Text-Mining Techniques On Electronic Medical Records to Analyze National Drug-insured Medication Use

Abstract

Processing electronic medical record (EMR) data has become a common practice among scientists for extracting valuable insights and studying diseases. Given the large volumes of text data in EMRs, efficient computerized text-mining techniques are necessary. As academics, we recognize that drug-used analysis from EMR data in Indonesia is currently limited. This study focuses on obtaining meaningful insights from EMR data to make positive recommendations for hospitals. The proposed method uses pattern-based Regular Expressions (regex) to extract drug names and a Levenshtein distance algorithm to check their compatibility. We developed the pattern based on analyzing Indonesia EMR data. The extracted drug names were compared to a list of selected drugs (National Drug-Insured/Fornas) that are required and must be provided at healthcare facilities in Indonesia. The Levenshtein distance threshold was set to two to decide whether the extracted drug names belonged to nationally drug-insured or not. Only about 11.09 – 16.11% of medications given by doctors are listed in the Fornas drug list. Between 2019 and 2021, there was an inaccuracy in the writing of prescriptions for Fornas drugs, with as many as 57.53% to 63.21% of drug names being written incorrectly. The results of this study indicate that the Levenshtein distance algorithm has promising potential for implementation in the Ministry of Health of Indonesia, with a precision rate of 97.07%.