Curation and Analysis of MIMICEL -- An Event Log for MIMIC-IV Emergency Department

2025-05-26

AI Summary

Emergency departments (EDs) suffer from pervasive overcrowding, necessitating efficient process analysis methods. Traditional approaches are time-consuming and costly, while process mining requires standardized event logs—yet existing clinical databases (e.g., MIMIC-IV-ED) lack XES-compliant event logs. To address this gap, we present MIMICEL: the first open-source, standardized event log tailored for the MIMIC-IV ED dataset. Built using SQL and Python, MIMICEL enables systematic data extraction, clinically meaningful event modeling, and automated conversion to XES format. It integrates Heuristics Miner and Inductive Miner to support end-to-end process discovery. MIMICEL bridges a critical data infrastructure gap in ED process mining, substantially lowering the barrier to entry for workflow analysis. It facilitates bottleneck identification, pathway variation analysis, and other operational diagnostics—thereby providing a reusable, scalable foundation for improving ED efficiency and mitigating overcrowding.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Information Extraction
• Machine Learning: Time-Series/Data Streams

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Analyzing patient flow in emergency departments to reduce overcrowding
• Creating event log MIMICEL from MIMIC-IV-ED for process mining
• Enabling efficient ED analysis using process mining techniques

Innovation

• Extracts event log from MIMIC-IV-ED dataset
• Enables patient flow analysis via process mining
• Facilitates ED efficiency improvement with MIMICEL