Semantic clustering to augment qualitative content analysis in exploring reasons for emergency department transfer delays

Abstract

<p>The aim of the study was to explore emergency department transfer</p><p>delays and to assess the potential of using a semantic clustering approach to augment</p><p>the content analysis of transfer delay data. Data were collected over a period of 5</p><p>months from two hospitals. A set of (unique) phrases describing reasons for transfer</p><p>delays (n=333) were clustered using the k-means with 1) cluster centroids initiated</p><p>in an unsupervised fashion and 2) a semi-supervised version where the cluster</p><p>centroids were initiated with keywords. The unsupervised algorithm clustered 77 %</p><p>and the semi-supervised 86 % of the phrases to suitable clusters. We chose the better</p><p>performing approach to augment our content analysis. Three main categories for</p><p>transfer delays were found as a result. These included 1) insufficient staffing</p><p>resources, 2) transportation and bed issues, and 3) patient and care related reasons.</p><p>The findings inform the audit of organisational processes, accuracy of staffing and</p><p>workflow to reduce transfer delays. Future research should explore implications of </p><p>semantic clustering approaches to other narrative data sets in health service research.</p>