Dheeraj Raju1, Xiaogang Su2, Patricia A Patrician3, Lori A Loan4, Mary S McCarthy4. 1. School of Nursing, University of Alabama at Birmingham, United States. Electronic address: seeth001@uab.edu. 2. University of Texas at El Paso, United States. 3. School of Nursing, University of Alabama at Birmingham, United States. 4. Center for Nursing Science & Clinical Inquiry, Madigan Army Medical Center, Tacoma, United States.
Abstract
BACKGROUND: Pressure ulcers are associated with a nearly three-fold increase in in-hospital mortality. It is essential to investigate how other factors besides the Braden scale could enhance the prediction of pressure ulcers. Data mining modeling techniques can be beneficial to conduct this type of analysis. Data mining techniques have been applied extensively in health care, but are not widely used in nursing research. PURPOSE: To remedy this methodological gap, this paper will review, explain, and compare several data mining models to examine patient level factors associated with pressure ulcers based on a four year study from military hospitals in the United States. METHODS: The variables included in the analysis are easily accessible demographic information and medical measurements. Logistic regression, decision trees, random forests, and multivariate adaptive regression splines were compared based on their performance and interpretability. RESULTS: The random forests model had the highest accuracy (C-statistic) with the following variables, in order of importance, ranked highest in predicting pressure ulcers: days in the hospital, serum albumin, age, blood urea nitrogen, and total Braden score. CONCLUSION: Data mining, particularly, random forests are useful in predictive modeling. It is important for hospitals and health care systems to use their own data over time for pressure ulcer risk prediction, to develop risk models based upon more than the total Braden score, and specific to their patient population.
BACKGROUND: Pressure ulcers are associated with a nearly three-fold increase in in-hospital mortality. It is essential to investigate how other factors besides the Braden scale could enhance the prediction of pressure ulcers. Data mining modeling techniques can be beneficial to conduct this type of analysis. Data mining techniques have been applied extensively in health care, but are not widely used in nursing research. PURPOSE: To remedy this methodological gap, this paper will review, explain, and compare several data mining models to examine patient level factors associated with pressure ulcers based on a four year study from military hospitals in the United States. METHODS: The variables included in the analysis are easily accessible demographic information and medical measurements. Logistic regression, decision trees, random forests, and multivariate adaptive regression splines were compared based on their performance and interpretability. RESULTS: The random forests model had the highest accuracy (C-statistic) with the following variables, in order of importance, ranked highest in predicting pressure ulcers: days in the hospital, serum albumin, age, blood ureanitrogen, and total Braden score. CONCLUSION: Data mining, particularly, random forests are useful in predictive modeling. It is important for hospitals and health care systems to use their own data over time for pressure ulcer risk prediction, to develop risk models based upon more than the total Braden score, and specific to their patient population.
Authors: Daniel T Linnen; Patricia Kipnis; June Rondinelli; John D Greene; Vincent Liu; Gabriel J Escobar Journal: Nurs Res Date: 2018 Jul/Aug Impact factor: 2.381
Authors: Tanekkia M Taylor-Clark; Pauline A Swiger; Colleen V Anusiewicz; Lori A Loan; Danielle M Olds; Sara T Breckenridge-Sproat; Dheeraj Raju; Patricia A Patrician Journal: J Nurs Adm Date: 2022-02-01 Impact factor: 1.737
Authors: June Rondinelli; Stephen Zuniga; Patricia Kipnis; Lina Najib Kawar; Vincent Liu; Gabriel J Escobar Journal: Nurs Res Date: 2018 Jan/Feb Impact factor: 2.381