ED revisits forecasting: Utilizing latent models

Ofir Ben-Assuli, Joshua R. Vest

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The potential impact of prediction methods is particularly relevant to emergency department (ED) settings which are characterized by complex and challenging conditions. Repeat ED visits are one such example of potential over-utilization over a longitudinal period that can in some cases be predicted. We tracked the ED revisit risk over time using a hidden Markov model (HMM) based on adult ED ten years encounters at a single US urban hospital. Given the HMM states, we performed prediction for future ED revisits. We applied Decision Jungle Trees and Logistic Regression prediction models. The data were combined from distributed sources (e.g. EHRs and HIE). The results show that integrating a pre-analysis of the diverse patients using latent class models and applying them to predictive classifiers performed well. The performance was better than without using pre-analysis of HMM. These findings suggest that one potential approach to improved risk prediction is to leverage the longitudinal nature of health care delivery.

Original languageEnglish (US)
Title of host publicationIntelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2
EditorsYaxin Bi, Rahul Bhatia, Supriya Kapoor
PublisherSpringer Verlag
Pages696-702
Number of pages7
ISBN (Print)9783030295127
DOIs
StatePublished - Jan 1 2020
EventIntelligent Systems Conference, IntelliSys 2019 - London, United Kingdom
Duration: Sep 5 2019Sep 6 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1038
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceIntelligent Systems Conference, IntelliSys 2019
CountryUnited Kingdom
CityLondon
Period9/5/199/6/19

Fingerprint

Electronic document exchange
Emergency rooms
Trellis codes
Health risks
Intelligent systems
Hidden Markov models
Decision trees
Health care
Logistics
Classifiers
Predictive analytics

Keywords

  • Electronic health records
  • Emergency department
  • Health information exchange
  • Hidden Markov Models
  • Predictive analytics
  • Revisit

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Ben-Assuli, O., & Vest, J. R. (2020). ED revisits forecasting: Utilizing latent models. In Y. Bi, R. Bhatia, & S. Kapoor (Eds.), Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2 (pp. 696-702). (Advances in Intelligent Systems and Computing; Vol. 1038). Springer Verlag. https://doi.org/10.1007/978-3-030-29513-4_52

ED revisits forecasting : Utilizing latent models. / Ben-Assuli, Ofir; Vest, Joshua R.

Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2. ed. / Yaxin Bi; Rahul Bhatia; Supriya Kapoor. Springer Verlag, 2020. p. 696-702 (Advances in Intelligent Systems and Computing; Vol. 1038).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ben-Assuli, O & Vest, JR 2020, ED revisits forecasting: Utilizing latent models. in Y Bi, R Bhatia & S Kapoor (eds), Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2. Advances in Intelligent Systems and Computing, vol. 1038, Springer Verlag, pp. 696-702, Intelligent Systems Conference, IntelliSys 2019, London, United Kingdom, 9/5/19. https://doi.org/10.1007/978-3-030-29513-4_52
Ben-Assuli O, Vest JR. ED revisits forecasting: Utilizing latent models. In Bi Y, Bhatia R, Kapoor S, editors, Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2. Springer Verlag. 2020. p. 696-702. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-29513-4_52
Ben-Assuli, Ofir ; Vest, Joshua R. / ED revisits forecasting : Utilizing latent models. Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2. editor / Yaxin Bi ; Rahul Bhatia ; Supriya Kapoor. Springer Verlag, 2020. pp. 696-702 (Advances in Intelligent Systems and Computing).
@inproceedings{85d6d2e79bd4479288bad7bbf5d40445,
title = "ED revisits forecasting: Utilizing latent models",
abstract = "The potential impact of prediction methods is particularly relevant to emergency department (ED) settings which are characterized by complex and challenging conditions. Repeat ED visits are one such example of potential over-utilization over a longitudinal period that can in some cases be predicted. We tracked the ED revisit risk over time using a hidden Markov model (HMM) based on adult ED ten years encounters at a single US urban hospital. Given the HMM states, we performed prediction for future ED revisits. We applied Decision Jungle Trees and Logistic Regression prediction models. The data were combined from distributed sources (e.g. EHRs and HIE). The results show that integrating a pre-analysis of the diverse patients using latent class models and applying them to predictive classifiers performed well. The performance was better than without using pre-analysis of HMM. These findings suggest that one potential approach to improved risk prediction is to leverage the longitudinal nature of health care delivery.",
keywords = "Electronic health records, Emergency department, Health information exchange, Hidden Markov Models, Predictive analytics, Revisit",
author = "Ofir Ben-Assuli and Vest, {Joshua R.}",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-29513-4_52",
language = "English (US)",
isbn = "9783030295127",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "696--702",
editor = "Yaxin Bi and Rahul Bhatia and Supriya Kapoor",
booktitle = "Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2",

}

TY - GEN

T1 - ED revisits forecasting

T2 - Utilizing latent models

AU - Ben-Assuli, Ofir

AU - Vest, Joshua R.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - The potential impact of prediction methods is particularly relevant to emergency department (ED) settings which are characterized by complex and challenging conditions. Repeat ED visits are one such example of potential over-utilization over a longitudinal period that can in some cases be predicted. We tracked the ED revisit risk over time using a hidden Markov model (HMM) based on adult ED ten years encounters at a single US urban hospital. Given the HMM states, we performed prediction for future ED revisits. We applied Decision Jungle Trees and Logistic Regression prediction models. The data were combined from distributed sources (e.g. EHRs and HIE). The results show that integrating a pre-analysis of the diverse patients using latent class models and applying them to predictive classifiers performed well. The performance was better than without using pre-analysis of HMM. These findings suggest that one potential approach to improved risk prediction is to leverage the longitudinal nature of health care delivery.

AB - The potential impact of prediction methods is particularly relevant to emergency department (ED) settings which are characterized by complex and challenging conditions. Repeat ED visits are one such example of potential over-utilization over a longitudinal period that can in some cases be predicted. We tracked the ED revisit risk over time using a hidden Markov model (HMM) based on adult ED ten years encounters at a single US urban hospital. Given the HMM states, we performed prediction for future ED revisits. We applied Decision Jungle Trees and Logistic Regression prediction models. The data were combined from distributed sources (e.g. EHRs and HIE). The results show that integrating a pre-analysis of the diverse patients using latent class models and applying them to predictive classifiers performed well. The performance was better than without using pre-analysis of HMM. These findings suggest that one potential approach to improved risk prediction is to leverage the longitudinal nature of health care delivery.

KW - Electronic health records

KW - Emergency department

KW - Health information exchange

KW - Hidden Markov Models

KW - Predictive analytics

KW - Revisit

UR - http://www.scopus.com/inward/record.url?scp=85072827805&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072827805&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-29513-4_52

DO - 10.1007/978-3-030-29513-4_52

M3 - Conference contribution

AN - SCOPUS:85072827805

SN - 9783030295127

T3 - Advances in Intelligent Systems and Computing

SP - 696

EP - 702

BT - Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 2

A2 - Bi, Yaxin

A2 - Bhatia, Rahul

A2 - Kapoor, Supriya

PB - Springer Verlag

ER -