Learning bundled care opportunities from electronic medical records

You Chen, Abel N. Kho, David Liebovitz, Catherine Ivory, Sarah Osmundson, Jiang Bian, Bradley A. Malin

Research output: Contribution to journalArticle

Abstract

Objective The traditional fee-for-service approach to healthcare can lead to the management of a patient's conditions in a siloed manner, inducing various negative consequences. It has been recognized that a bundled approach to healthcare - one that manages a collection of health conditions together - may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. In this study, we investigate if a data-driven approach can automatically learn potential bundles. Methods We designed a framework to infer health condition collections (HCCs) based on the similarity of their clinical workflows, according to electronic medical record (EMR) utilization. We evaluated the framework with data from over 16,500 inpatient stays from Northwestern Memorial Hospital in Chicago, Illinois. The plausibility of the inferred HCCs for bundled care was assessed through an online survey of a panel of five experts, whose responses were analyzed via an analysis of variance (ANOVA) at a 95% confidence level. We further assessed the face validity of the HCCs using evidence in the published literature. Results The framework inferred four HCCs, indicative of (1) fetal abnormalities, (2) late pregnancies, (3) prostate problems, and (4) chronic diseases, with congestive heart failure featuring prominently. Each HCC was substantiated with evidence in the literature and was deemed plausible for bundled care by the experts at a statistically significant level. Conclusions The findings suggest that an automated EMR data-driven framework conducted can provide a basis for discovering bundled care opportunities. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation.

LanguageEnglish (US)
Pages1-10
Number of pages10
JournalJournal of Biomedical Informatics
Volume77
DOIs
StatePublished - Jan 1 2018

Fingerprint

Electronic medical equipment
Electronic Health Records
Health
Learning
Delivery of Health Care
Fee-for-Service Plans
Workflow
Cost Savings
Analysis of variance (ANOVA)
Reproducibility of Results
Inpatients
Prostate
Analysis of Variance
Chronic Disease
Heart Failure
Pregnancy
Costs

Keywords

  • Bundled care
  • Clinical phenotyping
  • Data mining
  • Electronic medical record
  • Network analysis
  • Phenotype clusters
  • Topic modeling
  • Workflow

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Chen, Y., Kho, A. N., Liebovitz, D., Ivory, C., Osmundson, S., Bian, J., & Malin, B. A. (2018). Learning bundled care opportunities from electronic medical records. Journal of Biomedical Informatics, 77, 1-10. DOI: 10.1016/j.jbi.2017.11.014
Chen, You ; Kho, Abel N. ; Liebovitz, David ; Ivory, Catherine ; Osmundson, Sarah ; Bian, Jiang ; Malin, Bradley A./ Learning bundled care opportunities from electronic medical records. In: Journal of Biomedical Informatics. 2018 ; Vol. 77. pp. 1-10
@article{d50a539944ee401cb01bbd59fdaadcde,
title = "Learning bundled care opportunities from electronic medical records",
abstract = "Objective The traditional fee-for-service approach to healthcare can lead to the management of a patient's conditions in a siloed manner, inducing various negative consequences. It has been recognized that a bundled approach to healthcare - one that manages a collection of health conditions together - may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. In this study, we investigate if a data-driven approach can automatically learn potential bundles. Methods We designed a framework to infer health condition collections (HCCs) based on the similarity of their clinical workflows, according to electronic medical record (EMR) utilization. We evaluated the framework with data from over 16,500 inpatient stays from Northwestern Memorial Hospital in Chicago, Illinois. The plausibility of the inferred HCCs for bundled care was assessed through an online survey of a panel of five experts, whose responses were analyzed via an analysis of variance (ANOVA) at a 95\{%} confidence level. We further assessed the face validity of the HCCs using evidence in the published literature. Results The framework inferred four HCCs, indicative of (1) fetal abnormalities, (2) late pregnancies, (3) prostate problems, and (4) chronic diseases, with congestive heart failure featuring prominently. Each HCC was substantiated with evidence in the literature and was deemed plausible for bundled care by the experts at a statistically significant level. Conclusions The findings suggest that an automated EMR data-driven framework conducted can provide a basis for discovering bundled care opportunities. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation.",
keywords = "Bundled care, Clinical phenotyping, Data mining, Electronic medical record, Network analysis, Phenotype clusters, Topic modeling, Workflow",
author = "You Chen and Kho, {Abel N.} and David Liebovitz and Catherine Ivory and Sarah Osmundson and Jiang Bian and Malin, {Bradley A.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.jbi.2017.11.014",
language = "English (US)",
volume = "77",
pages = "1--10",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

Chen, Y, Kho, AN, Liebovitz, D, Ivory, C, Osmundson, S, Bian, J & Malin, BA 2018, 'Learning bundled care opportunities from electronic medical records' Journal of Biomedical Informatics, vol 77, pp. 1-10. DOI: 10.1016/j.jbi.2017.11.014

Learning bundled care opportunities from electronic medical records. / Chen, You; Kho, Abel N.; Liebovitz, David; Ivory, Catherine; Osmundson, Sarah; Bian, Jiang; Malin, Bradley A.

In: Journal of Biomedical Informatics, Vol. 77, 01.01.2018, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Learning bundled care opportunities from electronic medical records

AU - Chen,You

AU - Kho,Abel N.

AU - Liebovitz,David

AU - Ivory,Catherine

AU - Osmundson,Sarah

AU - Bian,Jiang

AU - Malin,Bradley A.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Objective The traditional fee-for-service approach to healthcare can lead to the management of a patient's conditions in a siloed manner, inducing various negative consequences. It has been recognized that a bundled approach to healthcare - one that manages a collection of health conditions together - may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. In this study, we investigate if a data-driven approach can automatically learn potential bundles. Methods We designed a framework to infer health condition collections (HCCs) based on the similarity of their clinical workflows, according to electronic medical record (EMR) utilization. We evaluated the framework with data from over 16,500 inpatient stays from Northwestern Memorial Hospital in Chicago, Illinois. The plausibility of the inferred HCCs for bundled care was assessed through an online survey of a panel of five experts, whose responses were analyzed via an analysis of variance (ANOVA) at a 95% confidence level. We further assessed the face validity of the HCCs using evidence in the published literature. Results The framework inferred four HCCs, indicative of (1) fetal abnormalities, (2) late pregnancies, (3) prostate problems, and (4) chronic diseases, with congestive heart failure featuring prominently. Each HCC was substantiated with evidence in the literature and was deemed plausible for bundled care by the experts at a statistically significant level. Conclusions The findings suggest that an automated EMR data-driven framework conducted can provide a basis for discovering bundled care opportunities. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation.

AB - Objective The traditional fee-for-service approach to healthcare can lead to the management of a patient's conditions in a siloed manner, inducing various negative consequences. It has been recognized that a bundled approach to healthcare - one that manages a collection of health conditions together - may enable greater efficacy and cost savings. However, it is not always evident which sets of conditions should be managed in a bundled manner. In this study, we investigate if a data-driven approach can automatically learn potential bundles. Methods We designed a framework to infer health condition collections (HCCs) based on the similarity of their clinical workflows, according to electronic medical record (EMR) utilization. We evaluated the framework with data from over 16,500 inpatient stays from Northwestern Memorial Hospital in Chicago, Illinois. The plausibility of the inferred HCCs for bundled care was assessed through an online survey of a panel of five experts, whose responses were analyzed via an analysis of variance (ANOVA) at a 95% confidence level. We further assessed the face validity of the HCCs using evidence in the published literature. Results The framework inferred four HCCs, indicative of (1) fetal abnormalities, (2) late pregnancies, (3) prostate problems, and (4) chronic diseases, with congestive heart failure featuring prominently. Each HCC was substantiated with evidence in the literature and was deemed plausible for bundled care by the experts at a statistically significant level. Conclusions The findings suggest that an automated EMR data-driven framework conducted can provide a basis for discovering bundled care opportunities. Still, translating such findings into actual care management will require further refinement, implementation, and evaluation.

KW - Bundled care

KW - Clinical phenotyping

KW - Data mining

KW - Electronic medical record

KW - Network analysis

KW - Phenotype clusters

KW - Topic modeling

KW - Workflow

UR - http://www.scopus.com/inward/record.url?scp=85035807171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035807171&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2017.11.014

DO - 10.1016/j.jbi.2017.11.014

M3 - Article

VL - 77

SP - 1

EP - 10

JO - Journal of Biomedical Informatics

T2 - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -

Chen Y, Kho AN, Liebovitz D, Ivory C, Osmundson S, Bian J et al. Learning bundled care opportunities from electronic medical records. Journal of Biomedical Informatics. 2018 Jan 1;77:1-10. Available from, DOI: 10.1016/j.jbi.2017.11.014