Predictive modeling for the prevention of hospital-acquired pressure ulcers.

Tae Youn Kim, Norma Lang

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A one-to-one case control study was conducted on a pre-existing dataset to examine a predictive model with a set of risk factors for pressure ulcer development in acute care settings. Various techniques were used to select the most relevant predictors from ten subsets of a pre-existing dataset. The predictors identified were further examined using ten additional subsets by measuring sensitivities, specificities, positive/negative predictive values, and the areas under the ROC (receiver operating characteristic) curves. The best components for identifying at-risk patients consisted of three Braden subscales and five risk factors routinely collected through electronic health records. Entering these eight predictors into the logistic regression model yielded a sensitivity of 92%, a specificity of 67%, and an area under the ROC curve of 89%. Further evaluation, however, is needed to explore the validity of the model.

Original languageEnglish (US)
Pages (from-to)434-438
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
StatePublished - 2006
Externally publishedYes

Fingerprint

Pressure Ulcer
ROC Curve
Logistic Models
Electronic Health Records
Case-Control Studies
Sensitivity and Specificity
Datasets

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{637d3c6591644f4db4d1a0d915be7553,
title = "Predictive modeling for the prevention of hospital-acquired pressure ulcers.",
abstract = "A one-to-one case control study was conducted on a pre-existing dataset to examine a predictive model with a set of risk factors for pressure ulcer development in acute care settings. Various techniques were used to select the most relevant predictors from ten subsets of a pre-existing dataset. The predictors identified were further examined using ten additional subsets by measuring sensitivities, specificities, positive/negative predictive values, and the areas under the ROC (receiver operating characteristic) curves. The best components for identifying at-risk patients consisted of three Braden subscales and five risk factors routinely collected through electronic health records. Entering these eight predictors into the logistic regression model yielded a sensitivity of 92{\%}, a specificity of 67{\%}, and an area under the ROC curve of 89{\%}. Further evaluation, however, is needed to explore the validity of the model.",
author = "Kim, {Tae Youn} and Norma Lang",
year = "2006",
language = "English (US)",
pages = "434--438",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Predictive modeling for the prevention of hospital-acquired pressure ulcers.

AU - Kim, Tae Youn

AU - Lang, Norma

PY - 2006

Y1 - 2006

N2 - A one-to-one case control study was conducted on a pre-existing dataset to examine a predictive model with a set of risk factors for pressure ulcer development in acute care settings. Various techniques were used to select the most relevant predictors from ten subsets of a pre-existing dataset. The predictors identified were further examined using ten additional subsets by measuring sensitivities, specificities, positive/negative predictive values, and the areas under the ROC (receiver operating characteristic) curves. The best components for identifying at-risk patients consisted of three Braden subscales and five risk factors routinely collected through electronic health records. Entering these eight predictors into the logistic regression model yielded a sensitivity of 92%, a specificity of 67%, and an area under the ROC curve of 89%. Further evaluation, however, is needed to explore the validity of the model.

AB - A one-to-one case control study was conducted on a pre-existing dataset to examine a predictive model with a set of risk factors for pressure ulcer development in acute care settings. Various techniques were used to select the most relevant predictors from ten subsets of a pre-existing dataset. The predictors identified were further examined using ten additional subsets by measuring sensitivities, specificities, positive/negative predictive values, and the areas under the ROC (receiver operating characteristic) curves. The best components for identifying at-risk patients consisted of three Braden subscales and five risk factors routinely collected through electronic health records. Entering these eight predictors into the logistic regression model yielded a sensitivity of 92%, a specificity of 67%, and an area under the ROC curve of 89%. Further evaluation, however, is needed to explore the validity of the model.

UR - http://www.scopus.com/inward/record.url?scp=34547106402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547106402&partnerID=8YFLogxK

M3 - Article

SP - 434

EP - 438

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -