Predictive Bayesian Network Model Using Electronic Patient Records for Prevention of Hospital-Acquired Pressure Ulcers.
10.4040/jkan.2011.41.3.423
- Author:
In Sook CHO
1
;
Eunja CHUNG
Author Information
1. Department of Nursing, Inha University, Incheon, Korea. insook.cho@inha.ac.kr
- Publication Type:Original Article ; English Abstract
- Keywords:
Pressure ulcer;
Bayesian prediction;
Logistic models;
Risk assessment;
Data mining
- MeSH:
Adult;
Aged;
Area Under Curve;
Bayes Theorem;
Cohort Studies;
Female;
Humans;
Logistic Models;
Male;
Medical Records;
Middle Aged;
*Predictive Value of Tests;
Pressure Ulcer/epidemiology/*prevention & control;
Retrospective Studies;
Risk Assessment
- From:Journal of Korean Academy of Nursing
2011;41(3):423-431
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
PURPOSE: The study was designed to determine the discriminating ability of a Bayesian network (BN) for predicting risk for pressure ulcers. METHODS: Analysis was done using a retrospective cohort, nursing records representing 21,114 hospital days, 3,348 patients at risk for ulcers, admitted to the intensive care unit of a tertiary teaching hospital between January 2004 and January 2007. A BN model and two logistic regression (LR) versions, model-I and -II, were compared, varying the nature, number and quality of input variables. Classification competence and case coverage of the models were tested and compared using a threefold cross validation method. RESULTS: Average incidence of ulcers was 6.12%. Of the two LR models, model-I demonstrated better indexes of statistical model fits. The BN model had a sensitivity of 81.95%, specificity of 75.63%, positive and negative predictive values of 35.62% and 96.22% respectively. The area under the receiver operating characteristic (AUROC) was 85.01% implying moderate to good overall performance, which was similar to LR model-I. However, regarding case coverage, the BN model was 100% compared to 15.88% of LR. CONCLUSION: Discriminating ability of the BN model was found to be acceptable and case coverage proved to be excellent for clinical use.
