Related Experiment Video
Updated: Sep 4, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Development of a low-dimensional model to predict admissions from triage at a pediatric emergency department
Fiona Leonard1, John Gilligan2, Michael J Barrett3,4
1Business Intelligence Unit Children's Health Ireland at Crumlin Dublin Ireland.
Insights
A new low-dimensional model predicts pediatric emergency department (ED) outcomes using 8 key variables. This model can improve patient flow and is suitable for settings with limited electronic data.
Area of Science:
- Pediatric Emergency Medicine
- Health Informatics
- Predictive Analytics
Background:
- Improving patient flow in pediatric emergency departments (EDs) is crucial for efficient healthcare delivery.
- Limited electronic data in some hospital settings necessitates simpler predictive models.
- Early prediction of patient disposition (admission or discharge) can optimize resource allocation.
Purpose of the Study:
- To develop and internally validate a low-dimensional predictive model for pediatric ED outcomes.
- To identify key variables for predicting patient disposition using post-triage data.
- To enhance patient flow in pediatric EDs through early outcome prediction.
Main Methods:
- A prognostic study utilized data from 2017-2018 pediatric ED attendances.
- Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology was applied.
- Gradient Boosting Machine (GBM), logistic regression, and Naïve Bayes models were compared; variable importance from the highest AUC model informed the final low-dimensional model.
Main Results:
- The Gradient Boosting Machine (GBM) model achieved an Area Under the Curve (AUC) of 0.853.
- A low-dimensional model using 8 predictors (presenting complaint, triage category, referral source, registration month, location type, distance traveled, admission history, weekday) demonstrated an AUC of 0.835.
- Key predictors identified included presenting complaint, triage category, and referral source.
Conclusions:
- A predictive model utilizing 8 variables can accurately forecast admission and discharge probabilities early in the pediatric ED process.
- This low-dimensional approach offers a practical solution for improving patient flow, especially in data-limited environments.
- Further analysis of prediction errors (false positives/negatives) is recommended to refine model implementation.
Objectives:
This study aims to develop and internally validate a low-dimensional model to predict outcomes (admission or discharge) using commonly entered data up to the post-triage process to improve patient flow in the pediatric emergency department (ED). In hospital settings where electronic data are limited, a low-dimensional model with fewer variables may be easier to implement.
Methods:
This prognostic study included ED attendances in 2017 and 2018. The Cross Industry Standard Process for Data Mining methodology was followed. Eligibility criteria was applied to the data set, splitting into 70% train and 30% test. Sampling techniques were compared. Gradient boosting machine (GBM), logistic regression, and naïve Bayes models were created. Variables of importance were obtained from the model with the highest area under the curve (AUC) and used to create a low-dimensional model.
Results:
Eligible attendances totaled 72,229 (15% admission rate). The AUC was 0.853 (95% confidence interval [CI], 0.846-0.859) for GBM, 0.845 (95% CI, 0.838-0.852) for logistic regression and 0.813 (95% CI, 0.806-0.821) for naïve Bayes. Important predictors in the GBM model used to create a low-dimensional model were presenting complaint, triage category, referral source, registration month, location type (resuscitation/other), distance traveled, admission history, and weekday (AUC 0.835 [95% CI, 0.829-0.842]).
Conclusions:
Admission and discharge probability can be predicted early in a pediatric ED using 8 variables. Future work could analyze the false positives and false negatives to gain an understanding of the implementation of these predictions.
More Related Videos
09:52Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
Published on: January 15, 2017
05:16Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
Related Concept Videos
01:12Two-Compartment Open Model: Extravascular Administration
The absorption exponent (ka) indicates the speed at which the drug...
01:26Pharmacokinetic Models: Comparison and Selection Criterion
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
01:06Three-Compartment Open Model
01:15One-Compartment Open Model for Extravascular Administration: First-Order Absorption Model
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...