Prediction of emergency department revisits using area-level social determinants of health measures and health information exchange information

Joshua Vest, Ofir Ben-Assuli

Research output: Contribution to journalArticle

Abstract

Introduction: Interoperable health information technologies, like electronic health records (EHR) and health information exchange (HIE), provide greater access to patient information from across multiple organizations. Also, an increasing number of public data sources exist to describe social determinant of health factors. These data may help better inform risk prediction models, but the relative importance or value of these data has not been established. This study assessed the performance of different classes of information individually, and in combination, in predicting emergency department (ED) revisits. Methods: In a sample of 279,611 adult ED encounters. We compared the performance of Two-Class Boosted Decision Trees machine learning algorithm using 5 classes of information: 1) social determinants of health measures only, 2) current visit EHR information only, 3) current and historical EHR information, 4) HIE information only, and 5) all available information combined. Results: The social determinants of health measure only model had the overall worst performance with an area under the curve AUC of 0.61. The model using all information classes together had the best performance (AUC = 0.732). The model using HIE information only performed better than all other single information class models. Conclusions: Broad information sources, which are reflective of patients’ reliance on multiple organizations for care, better support risk prediction modeling in the emergency department.

Original languageEnglish (US)
Pages (from-to)205-210
Number of pages6
JournalInternational Journal of Medical Informatics
Volume129
DOIs
StatePublished - Sep 1 2019
Externally publishedYes

Fingerprint

Social Determinants of Health
Electronic Health Records
Area Under Curve
Hospital Emergency Service
Organizations
Medical Informatics
Access to Information
Decision Trees
Information Storage and Retrieval
Health Information Exchange

Keywords

  • Emergency department
  • Emergency department revisits
  • Health information exchange
  • Machine learning
  • Risk prediction
  • Social determinants

ASJC Scopus subject areas

  • Health Informatics

Cite this

@article{344378e8fe604a839b0cca4093d72850,
title = "Prediction of emergency department revisits using area-level social determinants of health measures and health information exchange information",
abstract = "Introduction: Interoperable health information technologies, like electronic health records (EHR) and health information exchange (HIE), provide greater access to patient information from across multiple organizations. Also, an increasing number of public data sources exist to describe social determinant of health factors. These data may help better inform risk prediction models, but the relative importance or value of these data has not been established. This study assessed the performance of different classes of information individually, and in combination, in predicting emergency department (ED) revisits. Methods: In a sample of 279,611 adult ED encounters. We compared the performance of Two-Class Boosted Decision Trees machine learning algorithm using 5 classes of information: 1) social determinants of health measures only, 2) current visit EHR information only, 3) current and historical EHR information, 4) HIE information only, and 5) all available information combined. Results: The social determinants of health measure only model had the overall worst performance with an area under the curve AUC of 0.61. The model using all information classes together had the best performance (AUC = 0.732). The model using HIE information only performed better than all other single information class models. Conclusions: Broad information sources, which are reflective of patients’ reliance on multiple organizations for care, better support risk prediction modeling in the emergency department.",
keywords = "Emergency department, Emergency department revisits, Health information exchange, Machine learning, Risk prediction, Social determinants",
author = "Joshua Vest and Ofir Ben-Assuli",
year = "2019",
month = "9",
day = "1",
doi = "10.1016/j.ijmedinf.2019.06.013",
language = "English (US)",
volume = "129",
pages = "205--210",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Prediction of emergency department revisits using area-level social determinants of health measures and health information exchange information

AU - Vest, Joshua

AU - Ben-Assuli, Ofir

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Introduction: Interoperable health information technologies, like electronic health records (EHR) and health information exchange (HIE), provide greater access to patient information from across multiple organizations. Also, an increasing number of public data sources exist to describe social determinant of health factors. These data may help better inform risk prediction models, but the relative importance or value of these data has not been established. This study assessed the performance of different classes of information individually, and in combination, in predicting emergency department (ED) revisits. Methods: In a sample of 279,611 adult ED encounters. We compared the performance of Two-Class Boosted Decision Trees machine learning algorithm using 5 classes of information: 1) social determinants of health measures only, 2) current visit EHR information only, 3) current and historical EHR information, 4) HIE information only, and 5) all available information combined. Results: The social determinants of health measure only model had the overall worst performance with an area under the curve AUC of 0.61. The model using all information classes together had the best performance (AUC = 0.732). The model using HIE information only performed better than all other single information class models. Conclusions: Broad information sources, which are reflective of patients’ reliance on multiple organizations for care, better support risk prediction modeling in the emergency department.

AB - Introduction: Interoperable health information technologies, like electronic health records (EHR) and health information exchange (HIE), provide greater access to patient information from across multiple organizations. Also, an increasing number of public data sources exist to describe social determinant of health factors. These data may help better inform risk prediction models, but the relative importance or value of these data has not been established. This study assessed the performance of different classes of information individually, and in combination, in predicting emergency department (ED) revisits. Methods: In a sample of 279,611 adult ED encounters. We compared the performance of Two-Class Boosted Decision Trees machine learning algorithm using 5 classes of information: 1) social determinants of health measures only, 2) current visit EHR information only, 3) current and historical EHR information, 4) HIE information only, and 5) all available information combined. Results: The social determinants of health measure only model had the overall worst performance with an area under the curve AUC of 0.61. The model using all information classes together had the best performance (AUC = 0.732). The model using HIE information only performed better than all other single information class models. Conclusions: Broad information sources, which are reflective of patients’ reliance on multiple organizations for care, better support risk prediction modeling in the emergency department.

KW - Emergency department

KW - Emergency department revisits

KW - Health information exchange

KW - Machine learning

KW - Risk prediction

KW - Social determinants

UR - http://www.scopus.com/inward/record.url?scp=85067608383&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067608383&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2019.06.013

DO - 10.1016/j.ijmedinf.2019.06.013

M3 - Article

AN - SCOPUS:85067608383

VL - 129

SP - 205

EP - 210

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

ER -