Curation and Analysis of MIMICEL -- An Event Log for MIMIC-IV Emergency Department
Jia Wei, Chun Ouyang, Bemali Wickramanayake, Zhipeng He, Keshara Perera, Catarina Moreira
TL;DR
This work introduces MIMICEL, an end-to-end event log for ED processes derived from MIMIC-IV-ED to enable process mining of emergency department patient flows. Following a systematic nine-step guideline, the authors map ED activities to event-log structures, producing both CSV and XES formats and validating quality with DaQAPO. The dataset supports analyses of acuity, length of stay, and overcrowding, revealing distinct process patterns across acuity levels and crowded vs non-crowded conditions. By providing a reproducible curation workflow and a richly annotated ED log, the study aims to improve ED efficiency analyses and catalyze process mining research in healthcare.
Abstract
The global issue of overcrowding in emergency departments (ED) necessitates the analysis of patient flow through ED to enhance efficiency and alleviate overcrowding. However, traditional analytical methods are time-consuming and costly. The healthcare industry is embracing process mining tools to analyse healthcare processes and patient flows. Process mining aims to discover, monitor, and enhance processes by obtaining knowledge from event log data. However, the availability of event logs is a prerequisite for applying process mining techniques. Hence, this paper aims to generate an event log for analysing processes in ED. In this study, we extract an event log from the MIMIC-IV-ED dataset and name it MIMICEL. MIMICEL captures the process of patient journey in ED, allowing for analysis of patient flows and improving ED efficiency. We present analyses conducted using MIMICEL to demonstrate the utility of the dataset. The curation of MIMICEL facilitates extensive use of MIMIC-IV-ED data for ED analysis using process mining techniques, while also providing the process mining research communities with a valuable dataset for study.