Predictive analytics for hospital admissions from the emergency department using triage information

Ozgur Araz, David Olson, Adrian Ramirez-Nafarrate

Research output: Contribution to journalArticle

Abstract

In this paper, we investigate the predictive factors of hospital admissions from the emergency department (ED) in various classification models and evaluate their performance. We analyze data from a major hospital in a metro area in the United States with an approximately 50,000 ED visits per year using logistic regression, artificial neural network, decision tree, random forest, support vector machine and extreme gradient boosting methods. The predictive accuracy of the models are evaluated in multiple experiments in which data volume on training and validation varied with multiple years of data. The data set also included a set of observations from a year when an influenza pandemic occurred, which made the data set statistically different. The extreme gradient boosting algorithm (XGBoost) gives the highest area under curve (AUC) statistic and it stands out as one of the fastest algorithms. However, a less sophisticated model, such as simple logistic regression model, also performs well in a reasonable computational time. We also evaluate performance of models with correct classification of patient admission from the emergency department. In our experiments, increasing data volume for model training and validation do not change performances of models significantly, since we have used a large number of observations in initial training and validation experiments. However, support vector machines (SVM) show notable decrease in AUC statistic while model accuracy of the XGBoost algorithm increases. In addition, increasing the data volume slightly increases the AUC statistic for the XGBoost algorithm (i.e., from 83% to 86%) while other methods show slight decreases. Using the most accurate and efficient predictive model for ED admissions would help hospitals design a decision support systems for efficient information flow from the triage at the ED to both outpatient and inpatient units in case of admissions, as basic administrative data with patient acuity information can provide predictions for bed capacity planning.

Original languageEnglish (US)
Pages (from-to)199-207
Number of pages9
JournalInternational Journal of Production Economics
Volume208
DOIs
StatePublished - Feb 1 2019

Fingerprint

Statistics
Support vector machines
Logistics
Predictive analytics
Emergency department
Admission
Experiments
Decision trees
Decision support systems
Neural networks
Planning
Experiment
Support vector machine
Boosting
Gradient
Logistic regression
Information flow
Capacity planning
Performance change
Outpatient

Keywords

  • AUC
  • Emergency department visits
  • Hospital admissions
  • Predictive analytics
  • Triage

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Economics and Econometrics
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Predictive analytics for hospital admissions from the emergency department using triage information. / Araz, Ozgur; Olson, David; Ramirez-Nafarrate, Adrian.

In: International Journal of Production Economics, Vol. 208, 01.02.2019, p. 199-207.

Research output: Contribution to journalArticle

@article{866431439a7140fb8c8ed5f47d709d42,
title = "Predictive analytics for hospital admissions from the emergency department using triage information",
abstract = "In this paper, we investigate the predictive factors of hospital admissions from the emergency department (ED) in various classification models and evaluate their performance. We analyze data from a major hospital in a metro area in the United States with an approximately 50,000 ED visits per year using logistic regression, artificial neural network, decision tree, random forest, support vector machine and extreme gradient boosting methods. The predictive accuracy of the models are evaluated in multiple experiments in which data volume on training and validation varied with multiple years of data. The data set also included a set of observations from a year when an influenza pandemic occurred, which made the data set statistically different. The extreme gradient boosting algorithm (XGBoost) gives the highest area under curve (AUC) statistic and it stands out as one of the fastest algorithms. However, a less sophisticated model, such as simple logistic regression model, also performs well in a reasonable computational time. We also evaluate performance of models with correct classification of patient admission from the emergency department. In our experiments, increasing data volume for model training and validation do not change performances of models significantly, since we have used a large number of observations in initial training and validation experiments. However, support vector machines (SVM) show notable decrease in AUC statistic while model accuracy of the XGBoost algorithm increases. In addition, increasing the data volume slightly increases the AUC statistic for the XGBoost algorithm (i.e., from 83{\%} to 86{\%}) while other methods show slight decreases. Using the most accurate and efficient predictive model for ED admissions would help hospitals design a decision support systems for efficient information flow from the triage at the ED to both outpatient and inpatient units in case of admissions, as basic administrative data with patient acuity information can provide predictions for bed capacity planning.",
keywords = "AUC, Emergency department visits, Hospital admissions, Predictive analytics, Triage",
author = "Ozgur Araz and David Olson and Adrian Ramirez-Nafarrate",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.ijpe.2018.11.024",
language = "English (US)",
volume = "208",
pages = "199--207",
journal = "International Journal of Production Economics",
issn = "0925-5273",
publisher = "Elsevier",

}

TY - JOUR

T1 - Predictive analytics for hospital admissions from the emergency department using triage information

AU - Araz, Ozgur

AU - Olson, David

AU - Ramirez-Nafarrate, Adrian

PY - 2019/2/1

Y1 - 2019/2/1

N2 - In this paper, we investigate the predictive factors of hospital admissions from the emergency department (ED) in various classification models and evaluate their performance. We analyze data from a major hospital in a metro area in the United States with an approximately 50,000 ED visits per year using logistic regression, artificial neural network, decision tree, random forest, support vector machine and extreme gradient boosting methods. The predictive accuracy of the models are evaluated in multiple experiments in which data volume on training and validation varied with multiple years of data. The data set also included a set of observations from a year when an influenza pandemic occurred, which made the data set statistically different. The extreme gradient boosting algorithm (XGBoost) gives the highest area under curve (AUC) statistic and it stands out as one of the fastest algorithms. However, a less sophisticated model, such as simple logistic regression model, also performs well in a reasonable computational time. We also evaluate performance of models with correct classification of patient admission from the emergency department. In our experiments, increasing data volume for model training and validation do not change performances of models significantly, since we have used a large number of observations in initial training and validation experiments. However, support vector machines (SVM) show notable decrease in AUC statistic while model accuracy of the XGBoost algorithm increases. In addition, increasing the data volume slightly increases the AUC statistic for the XGBoost algorithm (i.e., from 83% to 86%) while other methods show slight decreases. Using the most accurate and efficient predictive model for ED admissions would help hospitals design a decision support systems for efficient information flow from the triage at the ED to both outpatient and inpatient units in case of admissions, as basic administrative data with patient acuity information can provide predictions for bed capacity planning.

AB - In this paper, we investigate the predictive factors of hospital admissions from the emergency department (ED) in various classification models and evaluate their performance. We analyze data from a major hospital in a metro area in the United States with an approximately 50,000 ED visits per year using logistic regression, artificial neural network, decision tree, random forest, support vector machine and extreme gradient boosting methods. The predictive accuracy of the models are evaluated in multiple experiments in which data volume on training and validation varied with multiple years of data. The data set also included a set of observations from a year when an influenza pandemic occurred, which made the data set statistically different. The extreme gradient boosting algorithm (XGBoost) gives the highest area under curve (AUC) statistic and it stands out as one of the fastest algorithms. However, a less sophisticated model, such as simple logistic regression model, also performs well in a reasonable computational time. We also evaluate performance of models with correct classification of patient admission from the emergency department. In our experiments, increasing data volume for model training and validation do not change performances of models significantly, since we have used a large number of observations in initial training and validation experiments. However, support vector machines (SVM) show notable decrease in AUC statistic while model accuracy of the XGBoost algorithm increases. In addition, increasing the data volume slightly increases the AUC statistic for the XGBoost algorithm (i.e., from 83% to 86%) while other methods show slight decreases. Using the most accurate and efficient predictive model for ED admissions would help hospitals design a decision support systems for efficient information flow from the triage at the ED to both outpatient and inpatient units in case of admissions, as basic administrative data with patient acuity information can provide predictions for bed capacity planning.

KW - AUC

KW - Emergency department visits

KW - Hospital admissions

KW - Predictive analytics

KW - Triage

UR - http://www.scopus.com/inward/record.url?scp=85059326883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059326883&partnerID=8YFLogxK

U2 - 10.1016/j.ijpe.2018.11.024

DO - 10.1016/j.ijpe.2018.11.024

M3 - Article

VL - 208

SP - 199

EP - 207

JO - International Journal of Production Economics

JF - International Journal of Production Economics

SN - 0925-5273

ER -