Processing electronic medical records to improve predictive analytics outcomes for hospital readmissions

Hamed M. Zolbanin, Dursun Delen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Hospital readmissions are costly but largely preventable. In recent years, many researchers have used predictive analytics to build models that can minimize the adverse economic and social consequences of readmissions in chronic diseases. Most of these studies, however, have focused on improving the results either through the development of better models or through employing richer data sets. A very small number of them have focused on a comprehensive data preprocessing to improve the efficacy of analytics methods for better predictions. In this study, we propose a new data processing approach that extracts individual- and database-level historical information from the medical records to improve the performance of readmission analytics. We test and validate this method using two rather large data sets that belong to chronic diseases with the highest rates of hospital readmissions. We conclude that proper processing of large clinical data sets with analytics and big data technologies can provide competitive advantages to health care organizations.

Original languageEnglish
Pages (from-to)98-110
Number of pages13
JournalDecision Support Systems
Volume112
DOIs
StatePublished - 1 Aug 2018
Externally publishedYes

Fingerprint

Electronic medical equipment
Patient Readmission
Electronic Health Records
Chronic Disease
Processing
Health care
Economics
Medical Records
Research Personnel
Organizations
Databases
Technology
Delivery of Health Care
Datasets
Predictive analytics
Electronic medical record
Big data
Chronic disease

Keywords

  • Big data technologies
  • Data processing
  • Electronic medical records
  • Hospital readmissions
  • Predictive analytics

Cite this

@article{69f8779199b44edb9acf3b9cf23c72ee,
title = "Processing electronic medical records to improve predictive analytics outcomes for hospital readmissions",
abstract = "Hospital readmissions are costly but largely preventable. In recent years, many researchers have used predictive analytics to build models that can minimize the adverse economic and social consequences of readmissions in chronic diseases. Most of these studies, however, have focused on improving the results either through the development of better models or through employing richer data sets. A very small number of them have focused on a comprehensive data preprocessing to improve the efficacy of analytics methods for better predictions. In this study, we propose a new data processing approach that extracts individual- and database-level historical information from the medical records to improve the performance of readmission analytics. We test and validate this method using two rather large data sets that belong to chronic diseases with the highest rates of hospital readmissions. We conclude that proper processing of large clinical data sets with analytics and big data technologies can provide competitive advantages to health care organizations.",
keywords = "Big data technologies, Data processing, Electronic medical records, Hospital readmissions, Predictive analytics",
author = "Zolbanin, {Hamed M.} and Dursun Delen",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.dss.2018.06.010",
language = "English",
volume = "112",
pages = "98--110",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",

}

Processing electronic medical records to improve predictive analytics outcomes for hospital readmissions. / Zolbanin, Hamed M.; Delen, Dursun.

In: Decision Support Systems, Vol. 112, 01.08.2018, p. 98-110.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Processing electronic medical records to improve predictive analytics outcomes for hospital readmissions

AU - Zolbanin, Hamed M.

AU - Delen, Dursun

PY - 2018/8/1

Y1 - 2018/8/1

N2 - Hospital readmissions are costly but largely preventable. In recent years, many researchers have used predictive analytics to build models that can minimize the adverse economic and social consequences of readmissions in chronic diseases. Most of these studies, however, have focused on improving the results either through the development of better models or through employing richer data sets. A very small number of them have focused on a comprehensive data preprocessing to improve the efficacy of analytics methods for better predictions. In this study, we propose a new data processing approach that extracts individual- and database-level historical information from the medical records to improve the performance of readmission analytics. We test and validate this method using two rather large data sets that belong to chronic diseases with the highest rates of hospital readmissions. We conclude that proper processing of large clinical data sets with analytics and big data technologies can provide competitive advantages to health care organizations.

AB - Hospital readmissions are costly but largely preventable. In recent years, many researchers have used predictive analytics to build models that can minimize the adverse economic and social consequences of readmissions in chronic diseases. Most of these studies, however, have focused on improving the results either through the development of better models or through employing richer data sets. A very small number of them have focused on a comprehensive data preprocessing to improve the efficacy of analytics methods for better predictions. In this study, we propose a new data processing approach that extracts individual- and database-level historical information from the medical records to improve the performance of readmission analytics. We test and validate this method using two rather large data sets that belong to chronic diseases with the highest rates of hospital readmissions. We conclude that proper processing of large clinical data sets with analytics and big data technologies can provide competitive advantages to health care organizations.

KW - Big data technologies

KW - Data processing

KW - Electronic medical records

KW - Hospital readmissions

KW - Predictive analytics

UR - http://www.scopus.com/inward/record.url?scp=85049485403&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2018.06.010

DO - 10.1016/j.dss.2018.06.010

M3 - Article

AN - SCOPUS:85049485403

VL - 112

SP - 98

EP - 110

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

ER -