Identification of avoidable patients at triage in a Paediatric Emergency Department: a decision support system using predictive analytics
Related Experiment Video
Updated: Jun 16, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
João Viana1,2, Júlio Souza3,4, Ruben Rocha5
1CINTESIS - Centre for Health Technology and Services Research, University of Porto, Porto, Portugal. joaoviana@med.up.pt.
Insights
A pruned decision tree model effectively identifies avoidable emergency department visits, offering a simple, interpretable solution to reduce patient crowding. This machine learning approach aids in optimizing patient flow and improving healthcare efficiency.
Area of Science:
- Emergency Medicine
- Health Informatics
- Machine Learning
Background:
- Emergency departments face significant overcrowding challenges.
- A fast-track system for non-urgent pediatric cases is being implemented.
- Optimizing patient flow is crucial for efficient emergency care.
Purpose of the Study:
- To develop an optimized Decision Support System (DSS) for directing patients to a fast-track pathway.
- To evaluate Machine Learning (ML) models for predicting avoidable emergency department visits.
- To balance predictive performance, model complexity, and interpretability.
Main Methods:
- Retrospective study of 507,708 pediatric emergency department visits (2014-2019).
- Trained and tested various ML models using triage information to predict visit avoidability.
- Compared model performance using metrics like Area Under the Curve (AUC).
Main Results:
- 41.6% of pediatric emergency visits were classified as avoidable.
- Most ML models achieved similar predictive performance (AUC 74%-80%), outperforming simple triage rules.
- A pruned decision tree demonstrated comparable results to more complex models.
Conclusions:
- The pruned decision tree offers a low-complexity, interpretable, and effective solution for identifying patients suitable for a fast-track system.
- ML-based DSS can significantly improve patient flow management in pediatric emergency departments.
- This research supports the practical application of machine learning in addressing emergency department overcrowding.
Background:
Crowding has been a longstanding issue in emergency departments. To address this, a fast-track system for avoidable patients is being implemented in the Paediatric Emergency Department where our study is conducted. Our goal is to develop an optimized Decision Support System that helps in directing patients to this fast track. We evaluated various Machine Learning models, focusing on a balance between complexity, predictive performance, and interpretability.
Methods:
This is a retrospective study considering all visits to a university-affiliated metropolitan hospital's PED between 2014 and 2019. Using information available at the time of triage, we trained several models to predict whether a visit is avoidable and should be directed to a fast-track area.
Results:
A total of 507,708 visits to the PED were used in the training and testing of the models. Regarding the outcome, 41.6% of the visits were considered avoidable. Except for the classification made by triage rules, i.e. considering levels 1,2, and 3 as non-avoidable and 4 and 5 as avoidable, all models had similar results in model's evaluation metrics, e.g. Area Under the Curve ranging from 74% to 80%.
Conclusions:
Regarding predictive performance, the pruned decision tree had evaluation metrics results that were comparable to the other ML models. Furthermore, it offers a low complexity and easy to implement solution. When considering interpretability, a paramount requisite in healthcare since it relates to the trustworthiness and transparency of the system, the pruned decision tree excels. Overall, this paper contributes to the growing body of research on the use of machine learning in healthcare. It highlights practical benefits for patients and healthcare systems of the use ML-based DSS in emergency medicine. Moreover, the obtained results can potentially help to design patients' flow management strategies in PED settings, which has been sought as a solution for addressing the long-standing problem of overcrowding.
More Related Videos
11:27A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
Published on: April 7, 2023
09:52Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
Published on: January 15, 2017