Emergency department patient flow reveals bottlenecks and delays
Process Mining of Patient Flow in an Emergency Department: Bottlenecks, Variant Fragmentation, and Data-Driven Redesign
Databases
Summary
Emergency departments have very varied ways of treating patients, which makes it hard to know what causes long wait times. The authors studied detailed data from over 1,800 patient visits to find patterns and delays in care. They discovered many different ways patients are treated, with no single standard path, and found that urgent patients sometimes stay longer than those in critical condition. Based on these findings, they suggested ways to reorganize care to speed up patient discharge and improve flow.
What this means in practice
- •For hospital operations teams: Identify specific delays and bottlenecks in emergency care processes to guide targeted improvements in patient throughput.
- •For healthcare it specialists: Implement data processing and process mining techniques to automatically analyze hospital event logs for operational insights.
Tested on one dataset.
Authors
Iliano Fasolino
Abstract
Emergency departments (EDs) run some of the least standardized processes in healthcare, and long stays are often attributed to demand rather than measured on data. We analyze an anonymised event log of 1{,}820 ED stays (25{,}115 events) through a full process mining pipeline: preprocessing resolves burst logging and missing values, performance analysis quantifies flow at the case and transition level, and Inductive Miner with token-based conformance checking assesses process structure. The filtered log (1{,}754 cases, 16{,}376 events) exhibits a mean throughput of 6.58 hours with a heavy tail, 884 distinct control-flow variants whose most frequent one covers only 4.3\% of cases, and an inversion of clinical priority in which urgent patients (acuity 2, 8.03 h) stay 38\% longer than critical ones (acuity 1, 5.83 h). Perfect fitness (1.0) combined with low precision (0.71) reveals absence of normative pathways rather than deviance. Two redesign scenarios, acuity-based care pathways and anticipatory discharge, are derived with quantified targets.