Author/Authors :
Guo, Wenping Institute of Intelligent Information Processing - Taizhou University, China , Xu, Zhuoming College of Computer and Information - Hohai University, China , Ye, Xijian Polytechnic Institute - Zhejiang University, China , Zhang,Shiqing Institute of Intelligent Information Processing - Taizhou University, China , Zhao,Xiaoming Institute of Intelligent Information Processing - Taizhou University, China , Li4,Xue Neusoft Institute of Information - Dalian Neusoft University of Information, China
Abstract :
Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions of dollars annually worldwide. Predicting survival time for sepsis patients is a time-critical prediction problem. Considering the useful sequential information for sepsis development, this paper proposes a time-critical topic model (TiCTM) inspired by the latent Dirichlet allocation (LDA) model. The proposed TiCTM approach takes into account the time dependency structure between notes, measurement, and survival time of a sepsis patient. Experimental results on the public MIMIC-III database show that, overall, our method outperforms the conventional LDA and linear regression model in terms of recall, precision, accuracy, and F1-measure. It is also found that our method achieves the best performance by using 5 topics when predicting the probability for 30-day survival time.
