Predicting all-cause readmissions using electronic health record data from the entire hospitalization: Model development and comparison

Oanh Kieu Nguyen, Anil N. Makam, Christopher Clark, Song Zhang, Bin Xie, Ferdinand Velasco, Ruben Amarasingham, Ethan A. Halm

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

BACKGROUND: Incorporating clinical information from the full hospital course may improve prediction of 30-day readmissions. OBJECTIVE: To develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare "full-stay" model performance to a "first day" and 2 other validated models, LACE (includes Length of stay, Acute [nonelective] admission status, Charlson Comorbidity Index, and Emergency department visits in the past year), and HOSPITAL (includes Hemoglobin at discharge, discharge from Oncology service, Sodium level at discharge, Procedure during index hospitalization, Index hospitalization Type [nonelective], number of Admissions in the past year, and Length of stay). DESIGN: Observational cohort study. SUBJECTS: All medicine discharges between November 2009 and October 2010 from 6 hospitals in North Texas, including safety net, teaching, and nonteaching sites. MEASURES: Thirty-day nonelective readmissions were ascertained from 75 regional hospitals. RESULTS: Among 32,922 admissions (validation = 16,430), 12.7% were readmitted. In addition to many first-day factors, we identified hospital-acquired Clostridium difficile infection (adjusted odds ratio [AOR]: 2.03, 95% confidence interval [CI]: 1.18-3.48), vital sign instability on discharge (AOR: 1.25, 95% CI: 1.15-1.36), hyponatremia on discharge (AOR: 1.34, 95% CI: 1.18-1.51), and length of stay (AOR: 1.06, 95% CI: 1.04-1.07) as significant predictors. The full-stay model had better discrimination than other models though the improvement was modest (C statistic 0.69 vs 0.64-0.67). It was also modestly better in identifying patients at highest risk for readmission (likelihood ratio +2.4 vs. 1.8-2.1) and in reclassifying individuals (net reclassification index 0.02-0.06). CONCLUSIONS: Incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions. Given limited improvement in prediction despite incorporation of data on hospital complications, clinical instabilities, and trajectory, our findings suggest that many factors influencing readmissions remain unaccounted for. Further improvements in readmission models will likely require accounting for psychosocial and behavioral factors not currently captured by EHRs. Journal of Hospital Medicine 2016.

Original languageEnglish (US)
JournalJournal of Hospital Medicine
DOIs
StateAccepted/In press - 2016

Fingerprint

Electronic Health Records
Length of Stay
Hospitalization
Odds Ratio
Confidence Intervals
Hospital Medicine
Clostridium Infections
Clostridium difficile
Hyponatremia
Vital Signs
Observational Studies
Hospital Emergency Service
Comorbidity
Teaching
Hemoglobins
Cohort Studies
Sodium
Medicine
Psychology
Safety

ASJC Scopus subject areas

  • Health Policy
  • Assessment and Diagnosis
  • Care Planning
  • Fundamentals and skills
  • Leadership and Management

Cite this

Predicting all-cause readmissions using electronic health record data from the entire hospitalization : Model development and comparison. / Nguyen, Oanh Kieu; Makam, Anil N.; Clark, Christopher; Zhang, Song; Xie, Bin; Velasco, Ferdinand; Amarasingham, Ruben; Halm, Ethan A.

In: Journal of Hospital Medicine, 2016.

Research output: Contribution to journalArticle

@article{bd263a900159412ebd029136992f4bc9,
title = "Predicting all-cause readmissions using electronic health record data from the entire hospitalization: Model development and comparison",
abstract = "BACKGROUND: Incorporating clinical information from the full hospital course may improve prediction of 30-day readmissions. OBJECTIVE: To develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare {"}full-stay{"} model performance to a {"}first day{"} and 2 other validated models, LACE (includes Length of stay, Acute [nonelective] admission status, Charlson Comorbidity Index, and Emergency department visits in the past year), and HOSPITAL (includes Hemoglobin at discharge, discharge from Oncology service, Sodium level at discharge, Procedure during index hospitalization, Index hospitalization Type [nonelective], number of Admissions in the past year, and Length of stay). DESIGN: Observational cohort study. SUBJECTS: All medicine discharges between November 2009 and October 2010 from 6 hospitals in North Texas, including safety net, teaching, and nonteaching sites. MEASURES: Thirty-day nonelective readmissions were ascertained from 75 regional hospitals. RESULTS: Among 32,922 admissions (validation = 16,430), 12.7{\%} were readmitted. In addition to many first-day factors, we identified hospital-acquired Clostridium difficile infection (adjusted odds ratio [AOR]: 2.03, 95{\%} confidence interval [CI]: 1.18-3.48), vital sign instability on discharge (AOR: 1.25, 95{\%} CI: 1.15-1.36), hyponatremia on discharge (AOR: 1.34, 95{\%} CI: 1.18-1.51), and length of stay (AOR: 1.06, 95{\%} CI: 1.04-1.07) as significant predictors. The full-stay model had better discrimination than other models though the improvement was modest (C statistic 0.69 vs 0.64-0.67). It was also modestly better in identifying patients at highest risk for readmission (likelihood ratio +2.4 vs. 1.8-2.1) and in reclassifying individuals (net reclassification index 0.02-0.06). CONCLUSIONS: Incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions. Given limited improvement in prediction despite incorporation of data on hospital complications, clinical instabilities, and trajectory, our findings suggest that many factors influencing readmissions remain unaccounted for. Further improvements in readmission models will likely require accounting for psychosocial and behavioral factors not currently captured by EHRs. Journal of Hospital Medicine 2016.",
author = "Nguyen, {Oanh Kieu} and Makam, {Anil N.} and Christopher Clark and Song Zhang and Bin Xie and Ferdinand Velasco and Ruben Amarasingham and Halm, {Ethan A.}",
year = "2016",
doi = "10.1002/jhm.2568",
language = "English (US)",
journal = "Journal of hospital medicine (Online)",
issn = "1553-5606",
publisher = "John Wiley and Sons Inc.",

}

TY - JOUR

T1 - Predicting all-cause readmissions using electronic health record data from the entire hospitalization

T2 - Model development and comparison

AU - Nguyen, Oanh Kieu

AU - Makam, Anil N.

AU - Clark, Christopher

AU - Zhang, Song

AU - Xie, Bin

AU - Velasco, Ferdinand

AU - Amarasingham, Ruben

AU - Halm, Ethan A.

PY - 2016

Y1 - 2016

N2 - BACKGROUND: Incorporating clinical information from the full hospital course may improve prediction of 30-day readmissions. OBJECTIVE: To develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare "full-stay" model performance to a "first day" and 2 other validated models, LACE (includes Length of stay, Acute [nonelective] admission status, Charlson Comorbidity Index, and Emergency department visits in the past year), and HOSPITAL (includes Hemoglobin at discharge, discharge from Oncology service, Sodium level at discharge, Procedure during index hospitalization, Index hospitalization Type [nonelective], number of Admissions in the past year, and Length of stay). DESIGN: Observational cohort study. SUBJECTS: All medicine discharges between November 2009 and October 2010 from 6 hospitals in North Texas, including safety net, teaching, and nonteaching sites. MEASURES: Thirty-day nonelective readmissions were ascertained from 75 regional hospitals. RESULTS: Among 32,922 admissions (validation = 16,430), 12.7% were readmitted. In addition to many first-day factors, we identified hospital-acquired Clostridium difficile infection (adjusted odds ratio [AOR]: 2.03, 95% confidence interval [CI]: 1.18-3.48), vital sign instability on discharge (AOR: 1.25, 95% CI: 1.15-1.36), hyponatremia on discharge (AOR: 1.34, 95% CI: 1.18-1.51), and length of stay (AOR: 1.06, 95% CI: 1.04-1.07) as significant predictors. The full-stay model had better discrimination than other models though the improvement was modest (C statistic 0.69 vs 0.64-0.67). It was also modestly better in identifying patients at highest risk for readmission (likelihood ratio +2.4 vs. 1.8-2.1) and in reclassifying individuals (net reclassification index 0.02-0.06). CONCLUSIONS: Incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions. Given limited improvement in prediction despite incorporation of data on hospital complications, clinical instabilities, and trajectory, our findings suggest that many factors influencing readmissions remain unaccounted for. Further improvements in readmission models will likely require accounting for psychosocial and behavioral factors not currently captured by EHRs. Journal of Hospital Medicine 2016.

AB - BACKGROUND: Incorporating clinical information from the full hospital course may improve prediction of 30-day readmissions. OBJECTIVE: To develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare "full-stay" model performance to a "first day" and 2 other validated models, LACE (includes Length of stay, Acute [nonelective] admission status, Charlson Comorbidity Index, and Emergency department visits in the past year), and HOSPITAL (includes Hemoglobin at discharge, discharge from Oncology service, Sodium level at discharge, Procedure during index hospitalization, Index hospitalization Type [nonelective], number of Admissions in the past year, and Length of stay). DESIGN: Observational cohort study. SUBJECTS: All medicine discharges between November 2009 and October 2010 from 6 hospitals in North Texas, including safety net, teaching, and nonteaching sites. MEASURES: Thirty-day nonelective readmissions were ascertained from 75 regional hospitals. RESULTS: Among 32,922 admissions (validation = 16,430), 12.7% were readmitted. In addition to many first-day factors, we identified hospital-acquired Clostridium difficile infection (adjusted odds ratio [AOR]: 2.03, 95% confidence interval [CI]: 1.18-3.48), vital sign instability on discharge (AOR: 1.25, 95% CI: 1.15-1.36), hyponatremia on discharge (AOR: 1.34, 95% CI: 1.18-1.51), and length of stay (AOR: 1.06, 95% CI: 1.04-1.07) as significant predictors. The full-stay model had better discrimination than other models though the improvement was modest (C statistic 0.69 vs 0.64-0.67). It was also modestly better in identifying patients at highest risk for readmission (likelihood ratio +2.4 vs. 1.8-2.1) and in reclassifying individuals (net reclassification index 0.02-0.06). CONCLUSIONS: Incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions. Given limited improvement in prediction despite incorporation of data on hospital complications, clinical instabilities, and trajectory, our findings suggest that many factors influencing readmissions remain unaccounted for. Further improvements in readmission models will likely require accounting for psychosocial and behavioral factors not currently captured by EHRs. Journal of Hospital Medicine 2016.

UR - http://www.scopus.com/inward/record.url?scp=84959294828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959294828&partnerID=8YFLogxK

U2 - 10.1002/jhm.2568

DO - 10.1002/jhm.2568

M3 - Article

C2 - 26929062

AN - SCOPUS:84990213423

JO - Journal of hospital medicine (Online)

JF - Journal of hospital medicine (Online)

SN - 1553-5606

ER -