랜덤 포리스트를 이용한 비제어 급성 출혈성 쇼크의 흰쥐에서의 생존 예측
A Survival Prediction Model of Rats in Uncontrolled Acute Hemorrhagic Shock Using the Random Forest Classifier
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Hemorrhagic shock is a primary cause of deaths resulting from injury in the world. Although many studies have tried to diagnose accurately hemorrhagic shock in the early stage, such attempts were not successful due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in acute hemorrhagic shock using a random forest (RF) model. Heart rate (HR), mean arterial pressure (MAP),respiration rate (RR), lactate concentration (LC), and peripheral perfusion (PP) measured in rats were used as input variables for the RF model and its performance was compared with that of a logistic regression (LR) model. Before constructing the models, we performed 5-fold cross validation for RF variable selection, and forward stepwise variable selection for the LR model to examine which variables were important for the models. For the LR model, sensitivity,specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 0.83, 0.95,0.88, and 0.96, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.97, 0.95, 0.96, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.
Abstract
Hemorrhagic shock is a primary cause of deaths resulting from injury in the world. Although many studies have tried to diagnose accurately hemorrhagic shock in the early stage, such attempts were not successful due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in acute hemorrhagic shock using a random forest (RF) model. Heart rate (HR), mean arterial pressure (MAP),respiration rate (RR), lactate concentration (LC), and peripheral perfusion (PP) measured in rats were used as input variables for the RF model and its performance was compared with that of a logistic regression (LR) model. Before constructing the models, we performed 5-fold cross validation for RF variable selection, and forward stepwise variable selection for the LR model to examine which variables were important for the models. For the LR model, sensitivity,specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 0.83, 0.95,0.88, and 0.96, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.97, 0.95, 0.96, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.
참고문헌 (24)
- World Health Organization, "World health statistics 2010", pp.62~70 (2010), World Health Organization Press
- C.J. Murray, "Alternative projections of mortality and disability by cause 1990-2020: global burden of disease study", Lancet, 349(9064), pp.1498~1504 (1997)
- C.D. Deakin, "AB or ABC: pre-hospital fluid management in major trauma", J Accid Emerg Med, 11(3), pp.154~157 (1994)
- V.J. Markovchick, "Emergency medicine secrets,4th edition", pp.28~32 (2006), Mosby
- M. Wilson, "Diagnosis and monitoring of hemorrhagic shock during the initial resuscitation of multiple trauma patients: a review", J Emerg Med, 24(4), pp.413~422 (2003)
- H.R. Guly, "Vital signs and estimated blood loss in patients with major trauma: testing the validity of the ATLS classification of hypovolaemic shock", Resuscitation, 82(5), pp.861~867 (2010)
- R.P. Dutton, "Current concepts in hemorrhagic shock", Anesthesiology clinics, 25(1), pp.23~34 (2007)
- G.J. Pestel, "Hemodynamic parameters change earlier than tissue oxygen tension in hemorrhage", Journal of Surgical Research, 160(2), pp.288~293 (2010)
- D.W. Kim, "Survival prediction in rats with fixed-volume hemorrhage using a logistic regression equation", Shock, 33(1), pp.14~ (2010)
- 장경환, "지원벡터기계를 이용한 출혈을 일으킨 흰쥐에서의 생존 예측", 의공학회지, 33(1), pp.1~7 (2012), 대한의용생체공학회
- L. Breiman, "Random forests", Machine learning, 45(1), pp.5~32 (2001)
- C.H. Hsieh, "Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks", Surgery, 149(1), pp.87~93 (2010)
- R. Diaz-Uriarte, "Gene selection and classification of microarray data using random forest", BMC Bioinformatics, 7(3), pp.1~13 (2006)
- 김덕원, "젖산 농도와 관류 비를 이용한 흰쥐에서의 출혈성 쇼크의 사망 예측 지표 개발", 대한응급의학회지, 23(1), pp.41~49 (2012), 대한응급의학회
- M.J. Leahy, "Principles and practice of the laser-Doppler perfusion technique", Technol Health Care, 7(2), pp.145~162 (1999)
- D.A. Roberts, "The use of polynomial neural networks for mortality prediction in uncontrolled venous and arterial hemorrhage", J Trauma, 52(1), pp.130~135 (2002)
- L.G. Not, "Glucosamine administration improves survival rate after severe hemorrhagic shock combined with trauma in rats", Shock, 28(3), pp.345~352
- A. Takasu, "Effect of induction rate for mild hypothermia on survival time during uncontrolled hemorrhagic shock in rats", J Trauma, 61(6), pp.1330~1335 (2006)
- A.M. Prasad, "Newer classification and regression tree techniques: bagging and random forests for ecological prediction", Ecosystems, 9(2), pp.181~199 (2006)
- X.W. Chen, "Prediction of protein-protein interactions using random decision forest framework", Bioinformatics, 588(3), pp.424~432 (2008)
- K.J. Archer, "Empirical characterization of random forest variable importance measures", Computational Statistics & Data Analysis, 52(4), pp.2249~2260 (2008)
- J. Albert, "Implementation of the random forest method for the imaging atmospheric cherenkov telescope MAGIC", Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 588(3), pp.424~432 (2008)
- M.L. Kaiser, "Laser Doppler imaging for early detection of hemorrhage", J Trauma, 71(2), pp.401~406 (2011)
- W.J. Meijerink, "Mammalian opiate alkaloid synthesis: lessons derived from plant biochemistry", Shock, 12(3), pp.165~173 (1999)