Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications

Jeremy L. Warner, Amin Zollanvari, Quan Ding, Peijin Zhang, Graham M. Snyder, Gil Alterovitz

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Objective To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR). Materials and methods 24 580 adults from the multiparameter intelligent monitoring in intensive care V.6 (MIMIC II) EHR database of critically ill patients were analyzed, with significant temporal associations visualized as a map of associations between hospital length of stay (LOS) and ICD-9-CM codes. An expanded phenotype, using ICD-9-CM, microbiology, and computerized physician order entry data, was defined for hospital-acquired Clostridium difficile (HA-CDI). LOS, estimated costs, 30-day post-discharge mortality, and antecedent medication provider order entry were evaluated for HA-CDI cases compared to randomly selected controls. Results Temporal phenome analysis revealed 191 significant codes (p value, adjusted for false discovery rate, ≤0.05). HA-CDI was identified in 414 cases, and was associated with longer median LOS, 20 versus 9 days, and adjusted HR 0.33 (95% CI 0.28 to 0.39). This prolongation carries an estimated annual incremental cost increase of US$1.2-2.0 billion in the USA alone. Discussion Comprehensive EHR data have made largescale phenome-based analysis feasible. Time-dependent pathological disease states have dynamic phenomic evolution, which may be captured through visual analytical approaches. Although MIMIC II is a single institutional retrospective database, our approach should be portable to other EHR data sources, including prospective 'learning healthcare systems'. For example, interventions to prevent HA-CDI could be dynamically evaluated using the same techniques. Conclusions The new visual analytical method described in this paper led directly to the identification of numerous hospital-acquired conditions, which could be further explored through an expanded phenotype definition.

Original languageEnglish
JournalJournal of the American Medical Informatics Association
Volume20
Issue numberE2
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Clostridium difficile
Electronic Health Records
Length of Stay
International Classification of Diseases
Phenotype
Medical Order Entry Systems
Iatrogenic Disease
Databases
Costs and Cost Analysis
Information Storage and Retrieval
Critical Care
Microbiology
Critical Illness
Learning
Delivery of Health Care
Mortality

ASJC Scopus subject areas

  • Health Informatics

Cite this

Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications. / Warner, Jeremy L.; Zollanvari, Amin; Ding, Quan; Zhang, Peijin; Snyder, Graham M.; Alterovitz, Gil.

In: Journal of the American Medical Informatics Association, Vol. 20, No. E2, 2013.

Research output: Contribution to journalArticle

@article{62d31481114e421baaecb74260800e23,
title = "Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications",
abstract = "Objective To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR). Materials and methods 24 580 adults from the multiparameter intelligent monitoring in intensive care V.6 (MIMIC II) EHR database of critically ill patients were analyzed, with significant temporal associations visualized as a map of associations between hospital length of stay (LOS) and ICD-9-CM codes. An expanded phenotype, using ICD-9-CM, microbiology, and computerized physician order entry data, was defined for hospital-acquired Clostridium difficile (HA-CDI). LOS, estimated costs, 30-day post-discharge mortality, and antecedent medication provider order entry were evaluated for HA-CDI cases compared to randomly selected controls. Results Temporal phenome analysis revealed 191 significant codes (p value, adjusted for false discovery rate, ≤0.05). HA-CDI was identified in 414 cases, and was associated with longer median LOS, 20 versus 9 days, and adjusted HR 0.33 (95{\%} CI 0.28 to 0.39). This prolongation carries an estimated annual incremental cost increase of US$1.2-2.0 billion in the USA alone. Discussion Comprehensive EHR data have made largescale phenome-based analysis feasible. Time-dependent pathological disease states have dynamic phenomic evolution, which may be captured through visual analytical approaches. Although MIMIC II is a single institutional retrospective database, our approach should be portable to other EHR data sources, including prospective 'learning healthcare systems'. For example, interventions to prevent HA-CDI could be dynamically evaluated using the same techniques. Conclusions The new visual analytical method described in this paper led directly to the identification of numerous hospital-acquired conditions, which could be further explored through an expanded phenotype definition.",
author = "Warner, {Jeremy L.} and Amin Zollanvari and Quan Ding and Peijin Zhang and Snyder, {Graham M.} and Gil Alterovitz",
year = "2013",
doi = "10.1136/amiajnl-2013-001861",
language = "English",
volume = "20",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "E2",

}

TY - JOUR

T1 - Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications

AU - Warner, Jeremy L.

AU - Zollanvari, Amin

AU - Ding, Quan

AU - Zhang, Peijin

AU - Snyder, Graham M.

AU - Alterovitz, Gil

PY - 2013

Y1 - 2013

N2 - Objective To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR). Materials and methods 24 580 adults from the multiparameter intelligent monitoring in intensive care V.6 (MIMIC II) EHR database of critically ill patients were analyzed, with significant temporal associations visualized as a map of associations between hospital length of stay (LOS) and ICD-9-CM codes. An expanded phenotype, using ICD-9-CM, microbiology, and computerized physician order entry data, was defined for hospital-acquired Clostridium difficile (HA-CDI). LOS, estimated costs, 30-day post-discharge mortality, and antecedent medication provider order entry were evaluated for HA-CDI cases compared to randomly selected controls. Results Temporal phenome analysis revealed 191 significant codes (p value, adjusted for false discovery rate, ≤0.05). HA-CDI was identified in 414 cases, and was associated with longer median LOS, 20 versus 9 days, and adjusted HR 0.33 (95% CI 0.28 to 0.39). This prolongation carries an estimated annual incremental cost increase of US$1.2-2.0 billion in the USA alone. Discussion Comprehensive EHR data have made largescale phenome-based analysis feasible. Time-dependent pathological disease states have dynamic phenomic evolution, which may be captured through visual analytical approaches. Although MIMIC II is a single institutional retrospective database, our approach should be portable to other EHR data sources, including prospective 'learning healthcare systems'. For example, interventions to prevent HA-CDI could be dynamically evaluated using the same techniques. Conclusions The new visual analytical method described in this paper led directly to the identification of numerous hospital-acquired conditions, which could be further explored through an expanded phenotype definition.

AB - Objective To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR). Materials and methods 24 580 adults from the multiparameter intelligent monitoring in intensive care V.6 (MIMIC II) EHR database of critically ill patients were analyzed, with significant temporal associations visualized as a map of associations between hospital length of stay (LOS) and ICD-9-CM codes. An expanded phenotype, using ICD-9-CM, microbiology, and computerized physician order entry data, was defined for hospital-acquired Clostridium difficile (HA-CDI). LOS, estimated costs, 30-day post-discharge mortality, and antecedent medication provider order entry were evaluated for HA-CDI cases compared to randomly selected controls. Results Temporal phenome analysis revealed 191 significant codes (p value, adjusted for false discovery rate, ≤0.05). HA-CDI was identified in 414 cases, and was associated with longer median LOS, 20 versus 9 days, and adjusted HR 0.33 (95% CI 0.28 to 0.39). This prolongation carries an estimated annual incremental cost increase of US$1.2-2.0 billion in the USA alone. Discussion Comprehensive EHR data have made largescale phenome-based analysis feasible. Time-dependent pathological disease states have dynamic phenomic evolution, which may be captured through visual analytical approaches. Although MIMIC II is a single institutional retrospective database, our approach should be portable to other EHR data sources, including prospective 'learning healthcare systems'. For example, interventions to prevent HA-CDI could be dynamically evaluated using the same techniques. Conclusions The new visual analytical method described in this paper led directly to the identification of numerous hospital-acquired conditions, which could be further explored through an expanded phenotype definition.

UR - http://www.scopus.com/inward/record.url?scp=84890370603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890370603&partnerID=8YFLogxK

U2 - 10.1136/amiajnl-2013-001861

DO - 10.1136/amiajnl-2013-001861

M3 - Article

C2 - 23907284

AN - SCOPUS:84890370603

VL - 20

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - E2

ER -