A predictive model to identify hospitalized cancer patients at risk for 30-day mortality based on admission criteria via the electronic medical record

Kavitha J. Ramchandran*, Joseph W. Shega, Jamie Von Roenn, Mark Schumacher, Eytan Szmuilowicz, Alfred Rademaker, Bing Bing Weitner, Pooja D. Loftus, Isabella M. Chu, Sigmund Weitzman

*Corresponding author for this work

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

BACKGROUND This study sought to develop a predictive model for 30-day mortality in hospitalized cancer patients, by using admission information available through the electronic medical record. METHODS Observational cohort study of 3062 patients admitted to the oncology service from August 1, 2008, to July 31, 2009. Matched numbers of patients were in the derivation and validation cohorts (1531 patients). Data were obtained on day 1 of admission and included demographic information, vital signs, and laboratory data. Survival data were obtained from the Social Security Death Index. RESULTS The 30-day mortality rate of the derivation and validation samples were 9.5% and 9.7% respectively. Significant predictive variables in the multivariate analysis included age (P <.0001), assistance with activities of daily living (ADLs; P =.022), admission type (elective/emergency) (P =.059), oxygen use (P <.0001), and vital signs abnormalities including pulse oximetry (P =.0004), temperature (P =.017), and heart rate (P =.0002). A logistic regression model was developed to predict death within 30 days: Score = 18.2897 + 0.6013*(admit type) + 0.4518*(ADL) + 0.0325*(admit age) - 0.1458*(temperature) + 0.019*(heart rate) - 0.0983*(pulse oximetry) - 0.0123 (systolic blood pressure) + 0.8615*(O2 use). The largest sum of sensitivity (63%) and specificity (78%) was at -2.09 (area under the curve = -0.789). A total of 25.32% (100 of 395) of patients with a score above -2.09 died, whereas 4.31% (49 of 1136) of patients below -2.09 died. Sensitivity and positive predictive value in the derivation and validation samples compared favorably. CONCLUSIONS Clinical factors available via the electronic medical record within 24 hours of hospital admission can be used to identify cancer patients at risk for 30-day mortality. These patients would benefit from discussion of preferences for care at the end of life.

Original languageEnglish (US)
Pages (from-to)2074-2080
Number of pages7
JournalCancer
Volume119
Issue number11
DOIs
StatePublished - Jun 1 2013

Fingerprint

Electronic Health Records
Mortality
Activities of Daily Living
Neoplasms
Oximetry
Vital Signs
Heart Rate
Logistic Models
Blood Pressure
Temperature
Terminal Care
Social Security
Patient Admission
Area Under Curve
Observational Studies
Emergencies
Cohort Studies
Multivariate Analysis
Demography
Oxygen

Keywords

  • Advance Care Planning
  • Cancer
  • Electronic Medical Record
  • Hospitalized
  • Palliative Care
  • Prognosis

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Ramchandran, Kavitha J. ; Shega, Joseph W. ; Von Roenn, Jamie ; Schumacher, Mark ; Szmuilowicz, Eytan ; Rademaker, Alfred ; Weitner, Bing Bing ; Loftus, Pooja D. ; Chu, Isabella M. ; Weitzman, Sigmund. / A predictive model to identify hospitalized cancer patients at risk for 30-day mortality based on admission criteria via the electronic medical record. In: Cancer. 2013 ; Vol. 119, No. 11. pp. 2074-2080.
@article{21287295ffbf49e0892c8e2a3187e23c,
title = "A predictive model to identify hospitalized cancer patients at risk for 30-day mortality based on admission criteria via the electronic medical record",
abstract = "BACKGROUND This study sought to develop a predictive model for 30-day mortality in hospitalized cancer patients, by using admission information available through the electronic medical record. METHODS Observational cohort study of 3062 patients admitted to the oncology service from August 1, 2008, to July 31, 2009. Matched numbers of patients were in the derivation and validation cohorts (1531 patients). Data were obtained on day 1 of admission and included demographic information, vital signs, and laboratory data. Survival data were obtained from the Social Security Death Index. RESULTS The 30-day mortality rate of the derivation and validation samples were 9.5{\%} and 9.7{\%} respectively. Significant predictive variables in the multivariate analysis included age (P <.0001), assistance with activities of daily living (ADLs; P =.022), admission type (elective/emergency) (P =.059), oxygen use (P <.0001), and vital signs abnormalities including pulse oximetry (P =.0004), temperature (P =.017), and heart rate (P =.0002). A logistic regression model was developed to predict death within 30 days: Score = 18.2897 + 0.6013*(admit type) + 0.4518*(ADL) + 0.0325*(admit age) - 0.1458*(temperature) + 0.019*(heart rate) - 0.0983*(pulse oximetry) - 0.0123 (systolic blood pressure) + 0.8615*(O2 use). The largest sum of sensitivity (63{\%}) and specificity (78{\%}) was at -2.09 (area under the curve = -0.789). A total of 25.32{\%} (100 of 395) of patients with a score above -2.09 died, whereas 4.31{\%} (49 of 1136) of patients below -2.09 died. Sensitivity and positive predictive value in the derivation and validation samples compared favorably. CONCLUSIONS Clinical factors available via the electronic medical record within 24 hours of hospital admission can be used to identify cancer patients at risk for 30-day mortality. These patients would benefit from discussion of preferences for care at the end of life.",
keywords = "Advance Care Planning, Cancer, Electronic Medical Record, Hospitalized, Palliative Care, Prognosis",
author = "Ramchandran, {Kavitha J.} and Shega, {Joseph W.} and {Von Roenn}, Jamie and Mark Schumacher and Eytan Szmuilowicz and Alfred Rademaker and Weitner, {Bing Bing} and Loftus, {Pooja D.} and Chu, {Isabella M.} and Sigmund Weitzman",
year = "2013",
month = "6",
day = "1",
doi = "10.1002/cncr.27974",
language = "English (US)",
volume = "119",
pages = "2074--2080",
journal = "Cancer",
issn = "0008-543X",
publisher = "John Wiley and Sons Inc.",
number = "11",

}

A predictive model to identify hospitalized cancer patients at risk for 30-day mortality based on admission criteria via the electronic medical record. / Ramchandran, Kavitha J.; Shega, Joseph W.; Von Roenn, Jamie; Schumacher, Mark; Szmuilowicz, Eytan; Rademaker, Alfred; Weitner, Bing Bing; Loftus, Pooja D.; Chu, Isabella M.; Weitzman, Sigmund.

In: Cancer, Vol. 119, No. 11, 01.06.2013, p. 2074-2080.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A predictive model to identify hospitalized cancer patients at risk for 30-day mortality based on admission criteria via the electronic medical record

AU - Ramchandran, Kavitha J.

AU - Shega, Joseph W.

AU - Von Roenn, Jamie

AU - Schumacher, Mark

AU - Szmuilowicz, Eytan

AU - Rademaker, Alfred

AU - Weitner, Bing Bing

AU - Loftus, Pooja D.

AU - Chu, Isabella M.

AU - Weitzman, Sigmund

PY - 2013/6/1

Y1 - 2013/6/1

N2 - BACKGROUND This study sought to develop a predictive model for 30-day mortality in hospitalized cancer patients, by using admission information available through the electronic medical record. METHODS Observational cohort study of 3062 patients admitted to the oncology service from August 1, 2008, to July 31, 2009. Matched numbers of patients were in the derivation and validation cohorts (1531 patients). Data were obtained on day 1 of admission and included demographic information, vital signs, and laboratory data. Survival data were obtained from the Social Security Death Index. RESULTS The 30-day mortality rate of the derivation and validation samples were 9.5% and 9.7% respectively. Significant predictive variables in the multivariate analysis included age (P <.0001), assistance with activities of daily living (ADLs; P =.022), admission type (elective/emergency) (P =.059), oxygen use (P <.0001), and vital signs abnormalities including pulse oximetry (P =.0004), temperature (P =.017), and heart rate (P =.0002). A logistic regression model was developed to predict death within 30 days: Score = 18.2897 + 0.6013*(admit type) + 0.4518*(ADL) + 0.0325*(admit age) - 0.1458*(temperature) + 0.019*(heart rate) - 0.0983*(pulse oximetry) - 0.0123 (systolic blood pressure) + 0.8615*(O2 use). The largest sum of sensitivity (63%) and specificity (78%) was at -2.09 (area under the curve = -0.789). A total of 25.32% (100 of 395) of patients with a score above -2.09 died, whereas 4.31% (49 of 1136) of patients below -2.09 died. Sensitivity and positive predictive value in the derivation and validation samples compared favorably. CONCLUSIONS Clinical factors available via the electronic medical record within 24 hours of hospital admission can be used to identify cancer patients at risk for 30-day mortality. These patients would benefit from discussion of preferences for care at the end of life.

AB - BACKGROUND This study sought to develop a predictive model for 30-day mortality in hospitalized cancer patients, by using admission information available through the electronic medical record. METHODS Observational cohort study of 3062 patients admitted to the oncology service from August 1, 2008, to July 31, 2009. Matched numbers of patients were in the derivation and validation cohorts (1531 patients). Data were obtained on day 1 of admission and included demographic information, vital signs, and laboratory data. Survival data were obtained from the Social Security Death Index. RESULTS The 30-day mortality rate of the derivation and validation samples were 9.5% and 9.7% respectively. Significant predictive variables in the multivariate analysis included age (P <.0001), assistance with activities of daily living (ADLs; P =.022), admission type (elective/emergency) (P =.059), oxygen use (P <.0001), and vital signs abnormalities including pulse oximetry (P =.0004), temperature (P =.017), and heart rate (P =.0002). A logistic regression model was developed to predict death within 30 days: Score = 18.2897 + 0.6013*(admit type) + 0.4518*(ADL) + 0.0325*(admit age) - 0.1458*(temperature) + 0.019*(heart rate) - 0.0983*(pulse oximetry) - 0.0123 (systolic blood pressure) + 0.8615*(O2 use). The largest sum of sensitivity (63%) and specificity (78%) was at -2.09 (area under the curve = -0.789). A total of 25.32% (100 of 395) of patients with a score above -2.09 died, whereas 4.31% (49 of 1136) of patients below -2.09 died. Sensitivity and positive predictive value in the derivation and validation samples compared favorably. CONCLUSIONS Clinical factors available via the electronic medical record within 24 hours of hospital admission can be used to identify cancer patients at risk for 30-day mortality. These patients would benefit from discussion of preferences for care at the end of life.

KW - Advance Care Planning

KW - Cancer

KW - Electronic Medical Record

KW - Hospitalized

KW - Palliative Care

KW - Prognosis

UR - http://www.scopus.com/inward/record.url?scp=84878017967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878017967&partnerID=8YFLogxK

U2 - 10.1002/cncr.27974

DO - 10.1002/cncr.27974

M3 - Article

VL - 119

SP - 2074

EP - 2080

JO - Cancer

JF - Cancer

SN - 0008-543X

IS - 11

ER -