Prediction of Severe Sepsis Using SVM Model
- 9 August 2010
- book chapter
- Published by Springer Science and Business Media LLC in Advances in experimental medicine and biology
- Vol. 680, 75-81
- https://doi.org/10.1007/978-1-4419-5913-3_9
Abstract
Sepsis is an infectious condition that results in damage to organs. This paper proposes a severe sepsis model based on Support Vector Machine (SVM) for predicting whether a septic patient will become severe sepsis. We chose several clinical physiology of sepsis for identifying the features used for SVM. Based on the model, a medical decision support system is proposed for clinical diagnosis. The results show that the prognosis of a septic patient can be more precisely predicted than ever. We conduct several experiments, whose results demonstrate that the proposed model provides high accuracy and high sensitivity and can be used as a reminding system to provide in-time treatment in ICU.Keywords
This publication has 5 references indexed in Scilit:
- Machine Learning Can Improve Prediction of Severity in Acute Pancreatitis Using Admission Values of APACHE II Score and C-Reactive ProteinPancreatology, 2006
- Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency roomCritical Care, 2005
- The enigma of sepsisJCI Insight, 2003
- Survival-Time Classification of Breast Cancer PatientsComputational Optimization and Applications, 2003
- Bedside prediction of mortality from bacteremic sepsis. A dynamic analysis of ICU patients.American Journal of Respiratory and Critical Care Medicine, 1996