Clustering algorithms for analysing electronic medical record: A mapping study

Abstract

Electronic Medical Records (EMRs) contain patients’ history related to their medication, vaccine, test results and insurance information. EMRs need to be stored to facilitate the application of clinical treatment and prevention protocols. Clustering algorithms automate the process of information extraction and support health data management. Hence, in this mapping study, we systematically examine the literature on clustering algorithms used for analysing EMRs. We focus on studies published in 2016-2021 to present an overview of clustering techniques used in these studies to analyse medical data. We found 27 studies on clustering techniques, clustering technique problems and the evaluation parameters for analysing EMRs. However, although several studies have focused on this topic, only a few have taken the significant step of examining the clustering techniques used for analysing medical data particularly electronic medical record. Our results highlight that three clustering techniques have been used to analyse medical data, namely, the partitioning, the hierarchical and the density-based algorithms. We identified several clustering technique problems and 10 different evaluation parameters. The results suggest that researchers should focus on analysing medical data that will drive data-driven decision-making by management and promote a data-driven culture to ensure health care quality.