Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs: Preliminary results

Marta L. Render, Deborah E. Welsh, Marin Kollef, James H. Lott, Siu Hui, Morris Weinberger, Joel Tsevat, Rodney A. Hayward, Timothy P. Hofer

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Objective: To evaluate the feasibility of an automated intensive care unit (ICU) risk adjustment tool (acronym: SISVistA) developed by selecting a subset of predictor variables from the Acute Physiology and Chronic Health Evaluation (APACHE) III available in the existing computerized database of the Department of Veterans Affairs (VA) healthcare system and modifying the APACHE diagnostic and comorbidity approach. Design: Retrospective cohort study. Setting: Six ICUs in three Ohio Veterans Affairs hospitals. Patient Selection: The first ICU admission of all patients from February 1996 through July 1997. Outcome Measure: Mortality at hospital discharge. Methods: The predictor variables, including age, comorbidity, diagnosis, admission source (direct or transfer), and laboratory results (from the ± 24-hr period surrounding admission), were extracted from computerized VA databases, and APACHE III weights were applied using customized software. The weights of all laboratory variables were added and treated as a single variable in the model. A logistic regression model was fitted to predict the outcome and the model was validated using a boot-strapping technique (1,000 repetitions). Main Results: The analysis included all 4,651 eligible cases (442 deaths). The cohort was predominantly male (97.5%) and elderly (63.6 ± 12.0 yrs). In multivariate analysis, significant predictors of hospital mortality included age (odds ratio [OR], 1.06; 95% confidence interval [CI], 1.04-1.09), comorbidity (OR, 1.11; 95% CI, 1.08-1.15), total laboratory score (OR, 1.07; 95% CI, 1.06-1.08), direct ICU admission (OR, 0.39; 95% CI, 0.31-0.49), and several broad ICU diagnostic categories. The SISVistA model had excellent discrimination and calibration (C statistic = 0.86, goodness-of-fit statistics; p > .20). The area under the receiver operating characteristic curve of the validated model was 0.86. Conclusions: Using common data elements often found in hospital computer systems, SISVistA predicts hospital mortality among patients in Ohio VA ICUs. This preliminary study supports the development of an automated ICU risk prediction system on a more diverse population.

Original languageEnglish
Pages (from-to)3540-3546
Number of pages7
JournalCritical Care Medicine
Volume28
Issue number10
StatePublished - 2000

Fingerprint

Veterans
Intensive Care Units
APACHE
Hospital Mortality
Odds Ratio
Confidence Intervals
Comorbidity
Logistic Models
Databases
Veterans Hospitals
Risk Adjustment
Weights and Measures
Patient Admission
Computer Systems
ROC Curve
Patient Selection
Calibration
Cohort Studies
Software
Multivariate Analysis

Keywords

  • Informatics
  • Intensive care unit
  • Mortality
  • Outcome
  • Severity adjustment

ASJC Scopus subject areas

  • Critical Care and Intensive Care Medicine

Cite this

Render, M. L., Welsh, D. E., Kollef, M., Lott, J. H., Hui, S., Weinberger, M., ... Hofer, T. P. (2000). Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs: Preliminary results. Critical Care Medicine, 28(10), 3540-3546.

Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs : Preliminary results. / Render, Marta L.; Welsh, Deborah E.; Kollef, Marin; Lott, James H.; Hui, Siu; Weinberger, Morris; Tsevat, Joel; Hayward, Rodney A.; Hofer, Timothy P.

In: Critical Care Medicine, Vol. 28, No. 10, 2000, p. 3540-3546.

Research output: Contribution to journalArticle

Render, ML, Welsh, DE, Kollef, M, Lott, JH, Hui, S, Weinberger, M, Tsevat, J, Hayward, RA & Hofer, TP 2000, 'Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs: Preliminary results', Critical Care Medicine, vol. 28, no. 10, pp. 3540-3546.
Render, Marta L. ; Welsh, Deborah E. ; Kollef, Marin ; Lott, James H. ; Hui, Siu ; Weinberger, Morris ; Tsevat, Joel ; Hayward, Rodney A. ; Hofer, Timothy P. / Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs : Preliminary results. In: Critical Care Medicine. 2000 ; Vol. 28, No. 10. pp. 3540-3546.
@article{d83247ad102f42799667ab379b102942,
title = "Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs: Preliminary results",
abstract = "Objective: To evaluate the feasibility of an automated intensive care unit (ICU) risk adjustment tool (acronym: SISVistA) developed by selecting a subset of predictor variables from the Acute Physiology and Chronic Health Evaluation (APACHE) III available in the existing computerized database of the Department of Veterans Affairs (VA) healthcare system and modifying the APACHE diagnostic and comorbidity approach. Design: Retrospective cohort study. Setting: Six ICUs in three Ohio Veterans Affairs hospitals. Patient Selection: The first ICU admission of all patients from February 1996 through July 1997. Outcome Measure: Mortality at hospital discharge. Methods: The predictor variables, including age, comorbidity, diagnosis, admission source (direct or transfer), and laboratory results (from the ± 24-hr period surrounding admission), were extracted from computerized VA databases, and APACHE III weights were applied using customized software. The weights of all laboratory variables were added and treated as a single variable in the model. A logistic regression model was fitted to predict the outcome and the model was validated using a boot-strapping technique (1,000 repetitions). Main Results: The analysis included all 4,651 eligible cases (442 deaths). The cohort was predominantly male (97.5{\%}) and elderly (63.6 ± 12.0 yrs). In multivariate analysis, significant predictors of hospital mortality included age (odds ratio [OR], 1.06; 95{\%} confidence interval [CI], 1.04-1.09), comorbidity (OR, 1.11; 95{\%} CI, 1.08-1.15), total laboratory score (OR, 1.07; 95{\%} CI, 1.06-1.08), direct ICU admission (OR, 0.39; 95{\%} CI, 0.31-0.49), and several broad ICU diagnostic categories. The SISVistA model had excellent discrimination and calibration (C statistic = 0.86, goodness-of-fit statistics; p > .20). The area under the receiver operating characteristic curve of the validated model was 0.86. Conclusions: Using common data elements often found in hospital computer systems, SISVistA predicts hospital mortality among patients in Ohio VA ICUs. This preliminary study supports the development of an automated ICU risk prediction system on a more diverse population.",
keywords = "Informatics, Intensive care unit, Mortality, Outcome, Severity adjustment",
author = "Render, {Marta L.} and Welsh, {Deborah E.} and Marin Kollef and Lott, {James H.} and Siu Hui and Morris Weinberger and Joel Tsevat and Hayward, {Rodney A.} and Hofer, {Timothy P.}",
year = "2000",
language = "English",
volume = "28",
pages = "3540--3546",
journal = "Critical Care Medicine",
issn = "0090-3493",
publisher = "Lippincott Williams and Wilkins",
number = "10",

}

TY - JOUR

T1 - Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs

T2 - Preliminary results

AU - Render, Marta L.

AU - Welsh, Deborah E.

AU - Kollef, Marin

AU - Lott, James H.

AU - Hui, Siu

AU - Weinberger, Morris

AU - Tsevat, Joel

AU - Hayward, Rodney A.

AU - Hofer, Timothy P.

PY - 2000

Y1 - 2000

N2 - Objective: To evaluate the feasibility of an automated intensive care unit (ICU) risk adjustment tool (acronym: SISVistA) developed by selecting a subset of predictor variables from the Acute Physiology and Chronic Health Evaluation (APACHE) III available in the existing computerized database of the Department of Veterans Affairs (VA) healthcare system and modifying the APACHE diagnostic and comorbidity approach. Design: Retrospective cohort study. Setting: Six ICUs in three Ohio Veterans Affairs hospitals. Patient Selection: The first ICU admission of all patients from February 1996 through July 1997. Outcome Measure: Mortality at hospital discharge. Methods: The predictor variables, including age, comorbidity, diagnosis, admission source (direct or transfer), and laboratory results (from the ± 24-hr period surrounding admission), were extracted from computerized VA databases, and APACHE III weights were applied using customized software. The weights of all laboratory variables were added and treated as a single variable in the model. A logistic regression model was fitted to predict the outcome and the model was validated using a boot-strapping technique (1,000 repetitions). Main Results: The analysis included all 4,651 eligible cases (442 deaths). The cohort was predominantly male (97.5%) and elderly (63.6 ± 12.0 yrs). In multivariate analysis, significant predictors of hospital mortality included age (odds ratio [OR], 1.06; 95% confidence interval [CI], 1.04-1.09), comorbidity (OR, 1.11; 95% CI, 1.08-1.15), total laboratory score (OR, 1.07; 95% CI, 1.06-1.08), direct ICU admission (OR, 0.39; 95% CI, 0.31-0.49), and several broad ICU diagnostic categories. The SISVistA model had excellent discrimination and calibration (C statistic = 0.86, goodness-of-fit statistics; p > .20). The area under the receiver operating characteristic curve of the validated model was 0.86. Conclusions: Using common data elements often found in hospital computer systems, SISVistA predicts hospital mortality among patients in Ohio VA ICUs. This preliminary study supports the development of an automated ICU risk prediction system on a more diverse population.

AB - Objective: To evaluate the feasibility of an automated intensive care unit (ICU) risk adjustment tool (acronym: SISVistA) developed by selecting a subset of predictor variables from the Acute Physiology and Chronic Health Evaluation (APACHE) III available in the existing computerized database of the Department of Veterans Affairs (VA) healthcare system and modifying the APACHE diagnostic and comorbidity approach. Design: Retrospective cohort study. Setting: Six ICUs in three Ohio Veterans Affairs hospitals. Patient Selection: The first ICU admission of all patients from February 1996 through July 1997. Outcome Measure: Mortality at hospital discharge. Methods: The predictor variables, including age, comorbidity, diagnosis, admission source (direct or transfer), and laboratory results (from the ± 24-hr period surrounding admission), were extracted from computerized VA databases, and APACHE III weights were applied using customized software. The weights of all laboratory variables were added and treated as a single variable in the model. A logistic regression model was fitted to predict the outcome and the model was validated using a boot-strapping technique (1,000 repetitions). Main Results: The analysis included all 4,651 eligible cases (442 deaths). The cohort was predominantly male (97.5%) and elderly (63.6 ± 12.0 yrs). In multivariate analysis, significant predictors of hospital mortality included age (odds ratio [OR], 1.06; 95% confidence interval [CI], 1.04-1.09), comorbidity (OR, 1.11; 95% CI, 1.08-1.15), total laboratory score (OR, 1.07; 95% CI, 1.06-1.08), direct ICU admission (OR, 0.39; 95% CI, 0.31-0.49), and several broad ICU diagnostic categories. The SISVistA model had excellent discrimination and calibration (C statistic = 0.86, goodness-of-fit statistics; p > .20). The area under the receiver operating characteristic curve of the validated model was 0.86. Conclusions: Using common data elements often found in hospital computer systems, SISVistA predicts hospital mortality among patients in Ohio VA ICUs. This preliminary study supports the development of an automated ICU risk prediction system on a more diverse population.

KW - Informatics

KW - Intensive care unit

KW - Mortality

KW - Outcome

KW - Severity adjustment

UR - http://www.scopus.com/inward/record.url?scp=0033791715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033791715&partnerID=8YFLogxK

M3 - Article

C2 - 11057814

AN - SCOPUS:0033791715

VL - 28

SP - 3540

EP - 3546

JO - Critical Care Medicine

JF - Critical Care Medicine

SN - 0090-3493

IS - 10

ER -