Development of a Bayesian model to estimate health care outcomes in the severely wounded
Alexander Stojadinovic1, John Eberhardt2, Trevor S Brown3, Jason S Hawksworth4, Frederick Gage3, Douglas K Tadaki3, Jonathan A Forsberg5, Thomas A Davis3, Benjamin K Potter5, James R Dunne6, E A Elster31Combat Wound Initiative Program, 4Department of Surgery, Walter Reed Army Medical Center, Washing...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Dove Medical Press
2010-08-01
|
Series: | Journal of Multidisciplinary Healthcare |
Online Access: | http://www.dovepress.com/development-of-a-bayesian-model-to-estimate-health-care-outcomes-in-th-a5047 |
_version_ | 1811236028306948096 |
---|---|
author | Alexander Stojadinovic John Eberhardt Trevor S Brown et al |
author_facet | Alexander Stojadinovic John Eberhardt Trevor S Brown et al |
author_sort | Alexander Stojadinovic |
collection | DOAJ |
description | Alexander Stojadinovic1, John Eberhardt2, Trevor S Brown3, Jason S Hawksworth4, Frederick Gage3, Douglas K Tadaki3, Jonathan A Forsberg5, Thomas A Davis3, Benjamin K Potter5, James R Dunne6, E A Elster31Combat Wound Initiative Program, 4Department of Surgery, Walter Reed Army Medical Center, Washington, DC, USA; 2DecisionQ Corporation, Washington, DC, USA; 3Regenerative Medicine Department, Combat Casualty Care, Naval Medical Research Center, Silver Spring, MD, USA; 5Integrated Department of Orthopaedics and Rehabilitation, 6Department of Surgery, National Naval Medical Center, Bethesda, MD, USABackground: Graphical probabilistic models have the ability to provide insights as to how clinical factors are conditionally related. These models can be used to help us understand factors influencing health care outcomes and resource utilization, and to estimate morbidity and clinical outcomes in trauma patient populations.Study design: Thirty-two combat casualties with severe extremity injuries enrolled in a prospective observational study were analyzed using step-wise machine-learned Bayesian belief network (BBN) and step-wise logistic regression (LR). Models were evaluated using 10-fold cross-validation to calculate area-under-the-curve (AUC) from receiver operating characteristics (ROC) curves.Results: Our BBN showed important associations between various factors in our data set that could not be developed using standard regression methods. Cross-validated ROC curve analysis showed that our BBN model was a robust representation of our data domain and that LR models trained on these findings were also robust: hospital-acquired infection (AUC: LR, 0.81; BBN, 0.79), intensive care unit length of stay (AUC: LR, 0.97; BBN, 0.81), and wound healing (AUC: LR, 0.91; BBN, 0.72) showed strong AUC.Conclusions: A BBN model can effectively represent clinical outcomes and biomarkers in patients hospitalized after severe wounding, and is confirmed by 10-fold ­cross-validation and further confirmed through logistic regression modeling. The method warrants further development and independent validation in other, more diverse patient populations.Keywords: combat, wounds, probabilistic model, Bayesian belief network, outcomes |
first_indexed | 2024-04-12T12:02:27Z |
format | Article |
id | doaj.art-4d0ceb6c8a24474a8dc2d719c2e8f953 |
institution | Directory Open Access Journal |
issn | 1178-2390 |
language | English |
last_indexed | 2024-04-12T12:02:27Z |
publishDate | 2010-08-01 |
publisher | Dove Medical Press |
record_format | Article |
series | Journal of Multidisciplinary Healthcare |
spelling | doaj.art-4d0ceb6c8a24474a8dc2d719c2e8f9532022-12-22T03:33:48ZengDove Medical PressJournal of Multidisciplinary Healthcare1178-23902010-08-012010default125135Development of a Bayesian model to estimate health care outcomes in the severely woundedAlexander StojadinovicJohn EberhardtTrevor S Brownet alAlexander Stojadinovic1, John Eberhardt2, Trevor S Brown3, Jason S Hawksworth4, Frederick Gage3, Douglas K Tadaki3, Jonathan A Forsberg5, Thomas A Davis3, Benjamin K Potter5, James R Dunne6, E A Elster31Combat Wound Initiative Program, 4Department of Surgery, Walter Reed Army Medical Center, Washington, DC, USA; 2DecisionQ Corporation, Washington, DC, USA; 3Regenerative Medicine Department, Combat Casualty Care, Naval Medical Research Center, Silver Spring, MD, USA; 5Integrated Department of Orthopaedics and Rehabilitation, 6Department of Surgery, National Naval Medical Center, Bethesda, MD, USABackground: Graphical probabilistic models have the ability to provide insights as to how clinical factors are conditionally related. These models can be used to help us understand factors influencing health care outcomes and resource utilization, and to estimate morbidity and clinical outcomes in trauma patient populations.Study design: Thirty-two combat casualties with severe extremity injuries enrolled in a prospective observational study were analyzed using step-wise machine-learned Bayesian belief network (BBN) and step-wise logistic regression (LR). Models were evaluated using 10-fold cross-validation to calculate area-under-the-curve (AUC) from receiver operating characteristics (ROC) curves.Results: Our BBN showed important associations between various factors in our data set that could not be developed using standard regression methods. Cross-validated ROC curve analysis showed that our BBN model was a robust representation of our data domain and that LR models trained on these findings were also robust: hospital-acquired infection (AUC: LR, 0.81; BBN, 0.79), intensive care unit length of stay (AUC: LR, 0.97; BBN, 0.81), and wound healing (AUC: LR, 0.91; BBN, 0.72) showed strong AUC.Conclusions: A BBN model can effectively represent clinical outcomes and biomarkers in patients hospitalized after severe wounding, and is confirmed by 10-fold ­cross-validation and further confirmed through logistic regression modeling. The method warrants further development and independent validation in other, more diverse patient populations.Keywords: combat, wounds, probabilistic model, Bayesian belief network, outcomeshttp://www.dovepress.com/development-of-a-bayesian-model-to-estimate-health-care-outcomes-in-th-a5047 |
spellingShingle | Alexander Stojadinovic John Eberhardt Trevor S Brown et al Development of a Bayesian model to estimate health care outcomes in the severely wounded Journal of Multidisciplinary Healthcare |
title | Development of a Bayesian model to estimate health care outcomes in the severely wounded |
title_full | Development of a Bayesian model to estimate health care outcomes in the severely wounded |
title_fullStr | Development of a Bayesian model to estimate health care outcomes in the severely wounded |
title_full_unstemmed | Development of a Bayesian model to estimate health care outcomes in the severely wounded |
title_short | Development of a Bayesian model to estimate health care outcomes in the severely wounded |
title_sort | development of a bayesian model to estimate health care outcomes in the severely wounded |
url | http://www.dovepress.com/development-of-a-bayesian-model-to-estimate-health-care-outcomes-in-th-a5047 |
work_keys_str_mv | AT alexanderstojadinovic developmentofabayesianmodeltoestimatehealthcareoutcomesintheseverelywounded AT johneberhardt developmentofabayesianmodeltoestimatehealthcareoutcomesintheseverelywounded AT trevorsbrown developmentofabayesianmodeltoestimatehealthcareoutcomesintheseverelywounded AT etal developmentofabayesianmodeltoestimatehealthcareoutcomesintheseverelywounded |