Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis

Adler Perotte, Rajesh Ranganath, Jamie S. Hirsch, David Blei, Noémie Elhadad

Research output: Contribution to journalArticle

Abstract

Background: As adoption of electronic health records continues to increase, there is an opportunity to incorporate clinical documentation as well as laboratory values and demographics into risk prediction modeling. Objective: The authors develop a risk prediction model for chronic kidney disease (CKD) progression from stage III to stage IV that includes longitudinal data and features drawn from clinical documentation. Methods: The study cohort consisted of 2908 primary-care clinic patients who had at least three visits prior to January 1, 2013 and developed CKD stage III during their documented history. Development and validation cohorts were randomly selected from this cohort and the study datasets included longitudinal inpatient and outpatient data from these populations. Time series analysis (Kalman filter) and survival analysis (Cox proportional hazards) were combined to produce a range of risk models. These models were evaluated using concordance, a discriminatory statistic. Results: A risk model incorporating longitudinal data on clinical documentation and laboratory test results (concordance 0.849) predicts progression from state III CKD to stage IV CKD more accurately when compared to a similar model without laboratory test results (concordance 0.733, P<.001), a model that only considers the most recent laboratory test results (concordance 0.819, P<.031) and a model based on estimated glomerular filtration rate (concordance 0.779, P<.001). Conclusions: A risk prediction model that takes longitudinal laboratory test results and clinical documentation into consideration can predict CKD progression from stage III to stage IV more accurately than three models that do not take all of these variables into consideration.

Original languageEnglish (US)
Pages (from-to)872-880
Number of pages9
JournalJournal of the American Medical Informatics Association
Volume22
Issue number4
DOIs
StatePublished - Jan 1 2015

Fingerprint

Electronic Health Records
Chronic Renal Insufficiency
Disease Progression
Documentation
Cohort Studies
Survival Analysis
Glomerular Filtration Rate
Inpatients
Primary Health Care
Outpatients
History
Demography
Population

Keywords

  • Electronic health records
  • Risk prediction
  • Survival analysis
  • Topic modeling

ASJC Scopus subject areas

  • Health Informatics

Cite this

Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis. / Perotte, Adler; Ranganath, Rajesh; Hirsch, Jamie S.; Blei, David; Elhadad, Noémie.

In: Journal of the American Medical Informatics Association, Vol. 22, No. 4, 01.01.2015, p. 872-880.

Research output: Contribution to journalArticle

Perotte, Adler ; Ranganath, Rajesh ; Hirsch, Jamie S. ; Blei, David ; Elhadad, Noémie. / Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis. In: Journal of the American Medical Informatics Association. 2015 ; Vol. 22, No. 4. pp. 872-880.
@article{86ae295014fb4b61a6d955f2312090ab,
title = "Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis",
abstract = "Background: As adoption of electronic health records continues to increase, there is an opportunity to incorporate clinical documentation as well as laboratory values and demographics into risk prediction modeling. Objective: The authors develop a risk prediction model for chronic kidney disease (CKD) progression from stage III to stage IV that includes longitudinal data and features drawn from clinical documentation. Methods: The study cohort consisted of 2908 primary-care clinic patients who had at least three visits prior to January 1, 2013 and developed CKD stage III during their documented history. Development and validation cohorts were randomly selected from this cohort and the study datasets included longitudinal inpatient and outpatient data from these populations. Time series analysis (Kalman filter) and survival analysis (Cox proportional hazards) were combined to produce a range of risk models. These models were evaluated using concordance, a discriminatory statistic. Results: A risk model incorporating longitudinal data on clinical documentation and laboratory test results (concordance 0.849) predicts progression from state III CKD to stage IV CKD more accurately when compared to a similar model without laboratory test results (concordance 0.733, P<.001), a model that only considers the most recent laboratory test results (concordance 0.819, P<.031) and a model based on estimated glomerular filtration rate (concordance 0.779, P<.001). Conclusions: A risk prediction model that takes longitudinal laboratory test results and clinical documentation into consideration can predict CKD progression from stage III to stage IV more accurately than three models that do not take all of these variables into consideration.",
keywords = "Electronic health records, Risk prediction, Survival analysis, Topic modeling",
author = "Adler Perotte and Rajesh Ranganath and Hirsch, {Jamie S.} and David Blei and No{\'e}mie Elhadad",
year = "2015",
month = "1",
day = "1",
doi = "10.1093/jamia/ocv024",
language = "English (US)",
volume = "22",
pages = "872--880",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis

AU - Perotte, Adler

AU - Ranganath, Rajesh

AU - Hirsch, Jamie S.

AU - Blei, David

AU - Elhadad, Noémie

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Background: As adoption of electronic health records continues to increase, there is an opportunity to incorporate clinical documentation as well as laboratory values and demographics into risk prediction modeling. Objective: The authors develop a risk prediction model for chronic kidney disease (CKD) progression from stage III to stage IV that includes longitudinal data and features drawn from clinical documentation. Methods: The study cohort consisted of 2908 primary-care clinic patients who had at least three visits prior to January 1, 2013 and developed CKD stage III during their documented history. Development and validation cohorts were randomly selected from this cohort and the study datasets included longitudinal inpatient and outpatient data from these populations. Time series analysis (Kalman filter) and survival analysis (Cox proportional hazards) were combined to produce a range of risk models. These models were evaluated using concordance, a discriminatory statistic. Results: A risk model incorporating longitudinal data on clinical documentation and laboratory test results (concordance 0.849) predicts progression from state III CKD to stage IV CKD more accurately when compared to a similar model without laboratory test results (concordance 0.733, P<.001), a model that only considers the most recent laboratory test results (concordance 0.819, P<.031) and a model based on estimated glomerular filtration rate (concordance 0.779, P<.001). Conclusions: A risk prediction model that takes longitudinal laboratory test results and clinical documentation into consideration can predict CKD progression from stage III to stage IV more accurately than three models that do not take all of these variables into consideration.

AB - Background: As adoption of electronic health records continues to increase, there is an opportunity to incorporate clinical documentation as well as laboratory values and demographics into risk prediction modeling. Objective: The authors develop a risk prediction model for chronic kidney disease (CKD) progression from stage III to stage IV that includes longitudinal data and features drawn from clinical documentation. Methods: The study cohort consisted of 2908 primary-care clinic patients who had at least three visits prior to January 1, 2013 and developed CKD stage III during their documented history. Development and validation cohorts were randomly selected from this cohort and the study datasets included longitudinal inpatient and outpatient data from these populations. Time series analysis (Kalman filter) and survival analysis (Cox proportional hazards) were combined to produce a range of risk models. These models were evaluated using concordance, a discriminatory statistic. Results: A risk model incorporating longitudinal data on clinical documentation and laboratory test results (concordance 0.849) predicts progression from state III CKD to stage IV CKD more accurately when compared to a similar model without laboratory test results (concordance 0.733, P<.001), a model that only considers the most recent laboratory test results (concordance 0.819, P<.031) and a model based on estimated glomerular filtration rate (concordance 0.779, P<.001). Conclusions: A risk prediction model that takes longitudinal laboratory test results and clinical documentation into consideration can predict CKD progression from stage III to stage IV more accurately than three models that do not take all of these variables into consideration.

KW - Electronic health records

KW - Risk prediction

KW - Survival analysis

KW - Topic modeling

UR - http://www.scopus.com/inward/record.url?scp=84940373302&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940373302&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocv024

DO - 10.1093/jamia/ocv024

M3 - Article

C2 - 25896647

AN - SCOPUS:84940373302

VL - 22

SP - 872

EP - 880

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 4

ER -