TY - JOUR
T1 - Probabilistic modeling approach for interpretable inference and prediction with data for sepsis diagnosis
AU - Yao, Shuaiyu
AU - Yang, Jian-Bo
AU - Xu, Dong-Ling
AU - Dark, Paul
N1 - Funding Information:
The authors express their sincere thanks for the support from European Union's Horizon 2020 Research and Innovation Programme RISE under grant agreement no. 823759 (REMESH), the Alliance Strategic Research Fund of the University of Manchester, and Natural Science Foundation of China under the grant No. U1709215, No. 71971139, No. 72071056, and No. 71601060.
Funding Information:
The authors express their sincere thanks for the support from European Union’s Horizon 2020 Research and Innovation Programme RISE under grant agreement no. 823759 (REMESH), the Alliance Strategic Research Fund of the University of Manchester, and Natural Science Foundation of China under the grant No. U1709215, No. 71971139, No. 72071056, and No. 71601060.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/11/30
Y1 - 2021/11/30
N2 - Sepsis is a serious disease that can cause death. It is important to predict sepsis within the early stages after the presence of sepsis symptoms. In this paper, a new probabilistic modeling approach is used to establish classifiers for sepsis diagnosis. This approach is characterized by unique strong interpretability, which is reflected in three aspects: (1) evidence acquisition based on likelihood analysis, (2) probabilistic rule-based inference, and (3) parameters optimization using machine learning algorithms. Four-fold cross-validation is used to train and validate classifiers established by the new approach and alternative ones. Results show that in terms of classification capability, the classifier established by the new approach generally performs better than the majority of alternative classifiers for sepsis diagnosis, and close to the best one. As the classifier also features an inherent interpretability, it can be used as a tool for supporting diagnostic decision-making in sepsis diagnosis.
AB - Sepsis is a serious disease that can cause death. It is important to predict sepsis within the early stages after the presence of sepsis symptoms. In this paper, a new probabilistic modeling approach is used to establish classifiers for sepsis diagnosis. This approach is characterized by unique strong interpretability, which is reflected in three aspects: (1) evidence acquisition based on likelihood analysis, (2) probabilistic rule-based inference, and (3) parameters optimization using machine learning algorithms. Four-fold cross-validation is used to train and validate classifiers established by the new approach and alternative ones. Results show that in terms of classification capability, the classifier established by the new approach generally performs better than the majority of alternative classifiers for sepsis diagnosis, and close to the best one. As the classifier also features an inherent interpretability, it can be used as a tool for supporting diagnostic decision-making in sepsis diagnosis.
KW - Interpretability
KW - Maximum likelihood evidential reasoning framework
KW - Probabilistic modeling
KW - Rule-based inference
KW - Sepsis diagnosis
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=pure_starter&SrcAuth=WosAPI&KeyUT=WOS:000694989100001&DestLinkType=FullRecord&DestApp=WOS_CPL
U2 - 10.1016/j.eswa.2021.115333
DO - 10.1016/j.eswa.2021.115333
M3 - Article
SN - 0957-4174
VL - 183
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 115333
ER -