Predicting 30-day pneumonia readmissions using electronic health record data

Anil N. Makam, Oanh Kieu Nguyen, Christopher Clark, Song Zhang, Bin Xie, Mark Weinreich, Eric M. Mortensen, Ethan A. Halm

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

BACKGROUND: Readmissions after hospitalization for pneumonia are common, but the few risk-prediction models have poor to modest predictive ability. Data routinely collected in the electronic health record (EHR) may improve prediction. OBJECTIVE: To develop pneumonia-specific readmission risk-prediction models using EHR data from the first day and from the entire hospital stay (“full stay”). DESIGN: Observational cohort study using stepwise-backward selection and cross-validation. SUBJECTS: Consecutive pneumonia hospitalizations from 6 diverse hospitals in north Texas from 2009-2010. MEASURES: All-cause nonelective 30-day readmissions, ascertained from 75 regional hospitals. RESULTS: Of 1463 patients, 13.6% were readmitted. The first-day pneumonia-specific model included sociodemographic factors, prior hospitalizations, thrombocytosis, and a modified pneumonia severity index; the full-stay model included disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index calculated using values from the day of discharge as additional predictors. The full-stay pneumonia-specific model outperformed the first-day model (C statistic 0.731 vs 0.695; P = 0.02; net reclassification index = 0.08). Compared to a validated multi-condition readmission model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores, the full-stay pneumonia-specific model had better discrimination (C statistic range 0.604-0.681; P < 0.01 for all comparisons), predicted a broader range of risk, and better reclassified individuals by their true risk (net reclassification index range, 0.09-0.18). CONCLUSIONS: EHR data collected from the entire hospitalization can accurately predict readmission risk among patients hospitalized for pneumonia. This approach outperforms a first-day pneumonia-specific model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores.

Original languageEnglish (US)
Pages (from-to)209-216
Number of pages8
JournalJournal of Hospital Medicine
Volume12
Issue number4
DOIs
StatePublished - Apr 1 2017

Fingerprint

Electronic Health Records
Pneumonia
Hospitalization
Centers for Medicare and Medicaid Services (U.S.)
Thrombocytosis
Vital Signs
Observational Studies
Length of Stay

ASJC Scopus subject areas

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

Cite this

Predicting 30-day pneumonia readmissions using electronic health record data. / Makam, Anil N.; Nguyen, Oanh Kieu; Clark, Christopher; Zhang, Song; Xie, Bin; Weinreich, Mark; Mortensen, Eric M.; Halm, Ethan A.

In: Journal of Hospital Medicine, Vol. 12, No. 4, 01.04.2017, p. 209-216.

Research output: Contribution to journalArticle

@article{3e2f7f22ae434d55a5aa220a122d6b6e,
title = "Predicting 30-day pneumonia readmissions using electronic health record data",
abstract = "BACKGROUND: Readmissions after hospitalization for pneumonia are common, but the few risk-prediction models have poor to modest predictive ability. Data routinely collected in the electronic health record (EHR) may improve prediction. OBJECTIVE: To develop pneumonia-specific readmission risk-prediction models using EHR data from the first day and from the entire hospital stay (“full stay”). DESIGN: Observational cohort study using stepwise-backward selection and cross-validation. SUBJECTS: Consecutive pneumonia hospitalizations from 6 diverse hospitals in north Texas from 2009-2010. MEASURES: All-cause nonelective 30-day readmissions, ascertained from 75 regional hospitals. RESULTS: Of 1463 patients, 13.6{\%} were readmitted. The first-day pneumonia-specific model included sociodemographic factors, prior hospitalizations, thrombocytosis, and a modified pneumonia severity index; the full-stay model included disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index calculated using values from the day of discharge as additional predictors. The full-stay pneumonia-specific model outperformed the first-day model (C statistic 0.731 vs 0.695; P = 0.02; net reclassification index = 0.08). Compared to a validated multi-condition readmission model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores, the full-stay pneumonia-specific model had better discrimination (C statistic range 0.604-0.681; P < 0.01 for all comparisons), predicted a broader range of risk, and better reclassified individuals by their true risk (net reclassification index range, 0.09-0.18). CONCLUSIONS: EHR data collected from the entire hospitalization can accurately predict readmission risk among patients hospitalized for pneumonia. This approach outperforms a first-day pneumonia-specific model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores.",
author = "Makam, {Anil N.} and Nguyen, {Oanh Kieu} and Christopher Clark and Song Zhang and Bin Xie and Mark Weinreich and Mortensen, {Eric M.} and Halm, {Ethan A.}",
year = "2017",
month = "4",
day = "1",
doi = "10.12788/jhm.2711",
language = "English (US)",
volume = "12",
pages = "209--216",
journal = "Journal of hospital medicine (Online)",
issn = "1553-5606",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Predicting 30-day pneumonia readmissions using electronic health record data

AU - Makam, Anil N.

AU - Nguyen, Oanh Kieu

AU - Clark, Christopher

AU - Zhang, Song

AU - Xie, Bin

AU - Weinreich, Mark

AU - Mortensen, Eric M.

AU - Halm, Ethan A.

PY - 2017/4/1

Y1 - 2017/4/1

N2 - BACKGROUND: Readmissions after hospitalization for pneumonia are common, but the few risk-prediction models have poor to modest predictive ability. Data routinely collected in the electronic health record (EHR) may improve prediction. OBJECTIVE: To develop pneumonia-specific readmission risk-prediction models using EHR data from the first day and from the entire hospital stay (“full stay”). DESIGN: Observational cohort study using stepwise-backward selection and cross-validation. SUBJECTS: Consecutive pneumonia hospitalizations from 6 diverse hospitals in north Texas from 2009-2010. MEASURES: All-cause nonelective 30-day readmissions, ascertained from 75 regional hospitals. RESULTS: Of 1463 patients, 13.6% were readmitted. The first-day pneumonia-specific model included sociodemographic factors, prior hospitalizations, thrombocytosis, and a modified pneumonia severity index; the full-stay model included disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index calculated using values from the day of discharge as additional predictors. The full-stay pneumonia-specific model outperformed the first-day model (C statistic 0.731 vs 0.695; P = 0.02; net reclassification index = 0.08). Compared to a validated multi-condition readmission model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores, the full-stay pneumonia-specific model had better discrimination (C statistic range 0.604-0.681; P < 0.01 for all comparisons), predicted a broader range of risk, and better reclassified individuals by their true risk (net reclassification index range, 0.09-0.18). CONCLUSIONS: EHR data collected from the entire hospitalization can accurately predict readmission risk among patients hospitalized for pneumonia. This approach outperforms a first-day pneumonia-specific model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores.

AB - BACKGROUND: Readmissions after hospitalization for pneumonia are common, but the few risk-prediction models have poor to modest predictive ability. Data routinely collected in the electronic health record (EHR) may improve prediction. OBJECTIVE: To develop pneumonia-specific readmission risk-prediction models using EHR data from the first day and from the entire hospital stay (“full stay”). DESIGN: Observational cohort study using stepwise-backward selection and cross-validation. SUBJECTS: Consecutive pneumonia hospitalizations from 6 diverse hospitals in north Texas from 2009-2010. MEASURES: All-cause nonelective 30-day readmissions, ascertained from 75 regional hospitals. RESULTS: Of 1463 patients, 13.6% were readmitted. The first-day pneumonia-specific model included sociodemographic factors, prior hospitalizations, thrombocytosis, and a modified pneumonia severity index; the full-stay model included disposition status, vital sign instabilities on discharge, and an updated pneumonia severity index calculated using values from the day of discharge as additional predictors. The full-stay pneumonia-specific model outperformed the first-day model (C statistic 0.731 vs 0.695; P = 0.02; net reclassification index = 0.08). Compared to a validated multi-condition readmission model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores, the full-stay pneumonia-specific model had better discrimination (C statistic range 0.604-0.681; P < 0.01 for all comparisons), predicted a broader range of risk, and better reclassified individuals by their true risk (net reclassification index range, 0.09-0.18). CONCLUSIONS: EHR data collected from the entire hospitalization can accurately predict readmission risk among patients hospitalized for pneumonia. This approach outperforms a first-day pneumonia-specific model, the Centers for Medicare and Medicaid Services pneumonia model, and 2 commonly used pneumonia severity of illness scores.

UR - http://www.scopus.com/inward/record.url?scp=85037552485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037552485&partnerID=8YFLogxK

U2 - 10.12788/jhm.2711

DO - 10.12788/jhm.2711

M3 - Article

VL - 12

SP - 209

EP - 216

JO - Journal of hospital medicine (Online)

JF - Journal of hospital medicine (Online)

SN - 1553-5606

IS - 4

ER -