Development and validation of severe hypoxemia associated risk prediction model in 1,000 mechanically ventilated patients*

Sonal R. Pannu, Pablo Moreno Franco, Guangxi Li, Michael Malinchoc, Gregory Wilson, Ognjen Gajic

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

MEASUREMENTS AND MAIN RESULTS: Mechanically ventilated ICU patients were screened for severe hypoxemic respiratory failure (Murray lung injury score of ≥ 3). Survival to hospital discharge was the dependent variable. Clinical predictors within 24 hours of onset of severe hypoxemia were considered as the independent variables. An area under the curve and a Hosmer-Lemeshow goodness-of-fit test were used to assess discrimination and calibration. A logistic regression model was developed in the derivation cohort (2005-2007). The model was validated in an independent cohort (2008-2010). Among 79,341 screened patients, 1,032 met inclusion criteria. Mortality was 41% in the derivation cohort (n = 464) and 35% in the validation cohort (n = 568). The final model included hematologic malignancy, cirrhosis, aspiration, estimated dead space, oxygenation index, pH, and vasopressor use. The area under the curve of the model was 0.85 (0.82-0.89) and 0.79 (0.75-0.82) in the derivation and validation cohorts, respectively, and showed good calibration. A modified model, including only physiologic variables, performed similarly. It had comparable performance in patients with acute respiratory distress syndrome and outperformed previous prognostic models.

CONCLUSIONS: A model using comorbid conditions and physiologic variables on the day of developing severe hypoxemic respiratory failure can predict hospital mortality.

OBJECTIVES: Patients with severe, persistent hypoxemic respiratory failure have a higher mortality. Early identification is critical for informing clinical decisions, using rescue strategies, and enrollment in clinical trials. The objective of this investigation was to develop and validate a prediction model to accurately and timely identify patients with severe hypoxemic respiratory failure at high risk of death, in whom novel rescue strategies can be efficiently evaluated.

DESIGN: Electronic medical record analysis.

SETTING: Medical, surgical, and mixed ICU setting at a tertiary care institution.

PATIENTS: Mechanically-ventilated ICU patients.

Original languageEnglish (US)
Pages (from-to)308-317
Number of pages10
JournalCritical Care Medicine
Volume43
Issue number2
DOIs
StatePublished - Feb 1 2015

Fingerprint

Respiratory Insufficiency
Calibration
Area Under Curve
Logistic Models
Mortality
Electronic Health Records
Adult Respiratory Distress Syndrome
Lung Injury
Hematologic Neoplasms
Tertiary Healthcare
Hospital Mortality
Hypoxia
Fibrosis
Clinical Trials
Survival

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Development and validation of severe hypoxemia associated risk prediction model in 1,000 mechanically ventilated patients*. / Pannu, Sonal R.; Moreno Franco, Pablo; Li, Guangxi; Malinchoc, Michael; Wilson, Gregory; Gajic, Ognjen.

In: Critical Care Medicine, Vol. 43, No. 2, 01.02.2015, p. 308-317.

Research output: Contribution to journalArticle

Pannu, Sonal R. ; Moreno Franco, Pablo ; Li, Guangxi ; Malinchoc, Michael ; Wilson, Gregory ; Gajic, Ognjen. / Development and validation of severe hypoxemia associated risk prediction model in 1,000 mechanically ventilated patients*. In: Critical Care Medicine. 2015 ; Vol. 43, No. 2. pp. 308-317.
@article{0431331f926c485aa61cf6556a2c51bc,
title = "Development and validation of severe hypoxemia associated risk prediction model in 1,000 mechanically ventilated patients*",
abstract = "MEASUREMENTS AND MAIN RESULTS: Mechanically ventilated ICU patients were screened for severe hypoxemic respiratory failure (Murray lung injury score of ≥ 3). Survival to hospital discharge was the dependent variable. Clinical predictors within 24 hours of onset of severe hypoxemia were considered as the independent variables. An area under the curve and a Hosmer-Lemeshow goodness-of-fit test were used to assess discrimination and calibration. A logistic regression model was developed in the derivation cohort (2005-2007). The model was validated in an independent cohort (2008-2010). Among 79,341 screened patients, 1,032 met inclusion criteria. Mortality was 41{\%} in the derivation cohort (n = 464) and 35{\%} in the validation cohort (n = 568). The final model included hematologic malignancy, cirrhosis, aspiration, estimated dead space, oxygenation index, pH, and vasopressor use. The area under the curve of the model was 0.85 (0.82-0.89) and 0.79 (0.75-0.82) in the derivation and validation cohorts, respectively, and showed good calibration. A modified model, including only physiologic variables, performed similarly. It had comparable performance in patients with acute respiratory distress syndrome and outperformed previous prognostic models.CONCLUSIONS: A model using comorbid conditions and physiologic variables on the day of developing severe hypoxemic respiratory failure can predict hospital mortality.OBJECTIVES: Patients with severe, persistent hypoxemic respiratory failure have a higher mortality. Early identification is critical for informing clinical decisions, using rescue strategies, and enrollment in clinical trials. The objective of this investigation was to develop and validate a prediction model to accurately and timely identify patients with severe hypoxemic respiratory failure at high risk of death, in whom novel rescue strategies can be efficiently evaluated.DESIGN: Electronic medical record analysis.SETTING: Medical, surgical, and mixed ICU setting at a tertiary care institution.PATIENTS: Mechanically-ventilated ICU patients.",
author = "Pannu, {Sonal R.} and {Moreno Franco}, Pablo and Guangxi Li and Michael Malinchoc and Gregory Wilson and Ognjen Gajic",
year = "2015",
month = "2",
day = "1",
doi = "10.1097/CCM.0000000000000671",
language = "English (US)",
volume = "43",
pages = "308--317",
journal = "Critical Care Medicine",
issn = "0090-3493",
publisher = "Lippincott Williams and Wilkins",
number = "2",

}

TY - JOUR

T1 - Development and validation of severe hypoxemia associated risk prediction model in 1,000 mechanically ventilated patients*

AU - Pannu, Sonal R.

AU - Moreno Franco, Pablo

AU - Li, Guangxi

AU - Malinchoc, Michael

AU - Wilson, Gregory

AU - Gajic, Ognjen

PY - 2015/2/1

Y1 - 2015/2/1

N2 - MEASUREMENTS AND MAIN RESULTS: Mechanically ventilated ICU patients were screened for severe hypoxemic respiratory failure (Murray lung injury score of ≥ 3). Survival to hospital discharge was the dependent variable. Clinical predictors within 24 hours of onset of severe hypoxemia were considered as the independent variables. An area under the curve and a Hosmer-Lemeshow goodness-of-fit test were used to assess discrimination and calibration. A logistic regression model was developed in the derivation cohort (2005-2007). The model was validated in an independent cohort (2008-2010). Among 79,341 screened patients, 1,032 met inclusion criteria. Mortality was 41% in the derivation cohort (n = 464) and 35% in the validation cohort (n = 568). The final model included hematologic malignancy, cirrhosis, aspiration, estimated dead space, oxygenation index, pH, and vasopressor use. The area under the curve of the model was 0.85 (0.82-0.89) and 0.79 (0.75-0.82) in the derivation and validation cohorts, respectively, and showed good calibration. A modified model, including only physiologic variables, performed similarly. It had comparable performance in patients with acute respiratory distress syndrome and outperformed previous prognostic models.CONCLUSIONS: A model using comorbid conditions and physiologic variables on the day of developing severe hypoxemic respiratory failure can predict hospital mortality.OBJECTIVES: Patients with severe, persistent hypoxemic respiratory failure have a higher mortality. Early identification is critical for informing clinical decisions, using rescue strategies, and enrollment in clinical trials. The objective of this investigation was to develop and validate a prediction model to accurately and timely identify patients with severe hypoxemic respiratory failure at high risk of death, in whom novel rescue strategies can be efficiently evaluated.DESIGN: Electronic medical record analysis.SETTING: Medical, surgical, and mixed ICU setting at a tertiary care institution.PATIENTS: Mechanically-ventilated ICU patients.

AB - MEASUREMENTS AND MAIN RESULTS: Mechanically ventilated ICU patients were screened for severe hypoxemic respiratory failure (Murray lung injury score of ≥ 3). Survival to hospital discharge was the dependent variable. Clinical predictors within 24 hours of onset of severe hypoxemia were considered as the independent variables. An area under the curve and a Hosmer-Lemeshow goodness-of-fit test were used to assess discrimination and calibration. A logistic regression model was developed in the derivation cohort (2005-2007). The model was validated in an independent cohort (2008-2010). Among 79,341 screened patients, 1,032 met inclusion criteria. Mortality was 41% in the derivation cohort (n = 464) and 35% in the validation cohort (n = 568). The final model included hematologic malignancy, cirrhosis, aspiration, estimated dead space, oxygenation index, pH, and vasopressor use. The area under the curve of the model was 0.85 (0.82-0.89) and 0.79 (0.75-0.82) in the derivation and validation cohorts, respectively, and showed good calibration. A modified model, including only physiologic variables, performed similarly. It had comparable performance in patients with acute respiratory distress syndrome and outperformed previous prognostic models.CONCLUSIONS: A model using comorbid conditions and physiologic variables on the day of developing severe hypoxemic respiratory failure can predict hospital mortality.OBJECTIVES: Patients with severe, persistent hypoxemic respiratory failure have a higher mortality. Early identification is critical for informing clinical decisions, using rescue strategies, and enrollment in clinical trials. The objective of this investigation was to develop and validate a prediction model to accurately and timely identify patients with severe hypoxemic respiratory failure at high risk of death, in whom novel rescue strategies can be efficiently evaluated.DESIGN: Electronic medical record analysis.SETTING: Medical, surgical, and mixed ICU setting at a tertiary care institution.PATIENTS: Mechanically-ventilated ICU patients.

UR - http://www.scopus.com/inward/record.url?scp=84925354079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925354079&partnerID=8YFLogxK

U2 - 10.1097/CCM.0000000000000671

DO - 10.1097/CCM.0000000000000671

M3 - Article

C2 - 25318386

AN - SCOPUS:84925354079

VL - 43

SP - 308

EP - 317

JO - Critical Care Medicine

JF - Critical Care Medicine

SN - 0090-3493

IS - 2

ER -