Predicting hospital-acquired infections by scoring system with simple parameters

Ying Jui Chang, Min Li Yeh, Yu Chuan Li, Chien Yeh Hsu, Chao Cheng Lin, Meng Shiuan Hsu, Wen Ta Chiu

研究成果: 雜誌貢獻文章

21 引文 (Scopus)

摘要

Background: Hospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously. Methodology/Principal Findings: A total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations. Conclusions: We developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings.

原文英語
文章編號e23137
期刊PLoS One
6
發行號8
DOIs
出版狀態已發佈 - 八月 24 2011

指紋

cross infection
Cross Infection
Logistic Models
Logistics
neural networks
Area Under Curve
Neural networks
catheters
electronics
Electronic Health Records
Health
medical equipment
economic costs
hemodialysis
prediction
Inpatients
enteral feeding
Hospitalization
Central Venous Catheterization
infection

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

引用此文

Chang, Y. J., Yeh, M. L., Li, Y. C., Hsu, C. Y., Lin, C. C., Hsu, M. S., & Chiu, W. T. (2011). Predicting hospital-acquired infections by scoring system with simple parameters. PLoS One, 6(8), [e23137]. https://doi.org/10.1371/journal.pone.0023137

Predicting hospital-acquired infections by scoring system with simple parameters. / Chang, Ying Jui; Yeh, Min Li; Li, Yu Chuan; Hsu, Chien Yeh; Lin, Chao Cheng; Hsu, Meng Shiuan; Chiu, Wen Ta.

於: PLoS One, 卷 6, 編號 8, e23137, 24.08.2011.

研究成果: 雜誌貢獻文章

Chang, YJ, Yeh, ML, Li, YC, Hsu, CY, Lin, CC, Hsu, MS & Chiu, WT 2011, 'Predicting hospital-acquired infections by scoring system with simple parameters', PLoS One, 卷 6, 編號 8, e23137. https://doi.org/10.1371/journal.pone.0023137
Chang, Ying Jui ; Yeh, Min Li ; Li, Yu Chuan ; Hsu, Chien Yeh ; Lin, Chao Cheng ; Hsu, Meng Shiuan ; Chiu, Wen Ta. / Predicting hospital-acquired infections by scoring system with simple parameters. 於: PLoS One. 2011 ; 卷 6, 編號 8.
@article{69becb19c45843728d80646d3481d666,
title = "Predicting hospital-acquired infections by scoring system with simple parameters",
abstract = "Background: Hospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously. Methodology/Principal Findings: A total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations. Conclusions: We developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings.",
author = "Chang, {Ying Jui} and Yeh, {Min Li} and Li, {Yu Chuan} and Hsu, {Chien Yeh} and Lin, {Chao Cheng} and Hsu, {Meng Shiuan} and Chiu, {Wen Ta}",
year = "2011",
month = "8",
day = "24",
doi = "10.1371/journal.pone.0023137",
language = "English",
volume = "6",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "8",

}

TY - JOUR

T1 - Predicting hospital-acquired infections by scoring system with simple parameters

AU - Chang, Ying Jui

AU - Yeh, Min Li

AU - Li, Yu Chuan

AU - Hsu, Chien Yeh

AU - Lin, Chao Cheng

AU - Hsu, Meng Shiuan

AU - Chiu, Wen Ta

PY - 2011/8/24

Y1 - 2011/8/24

N2 - Background: Hospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously. Methodology/Principal Findings: A total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations. Conclusions: We developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings.

AB - Background: Hospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously. Methodology/Principal Findings: A total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations. Conclusions: We developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings.

UR - http://www.scopus.com/inward/record.url?scp=80051999222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051999222&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0023137

DO - 10.1371/journal.pone.0023137

M3 - Article

C2 - 21887234

AN - SCOPUS:80051999222

VL - 6

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 8

M1 - e23137

ER -