Learning representations for the early detection of sepsis with deep neural networks

BACKGROUND Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. OBJECTIVE This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. METHOD Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. RESULTS With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. CONCLUSIONS The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns.

[1]  G. Clermont,et al.  Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care , 2001, Critical care medicine.

[2]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[3]  Ronald G. Tompkins,et al.  Spontaneous Neutrophil Migration Patterns during Sepsis after Major Burns , 2014, PloS one.

[4]  K. Fairchild,et al.  Predictive monitoring for early detection of sepsis in neonatal ICU patients , 2013, Current opinion in pediatrics.

[5]  Xiaohui Xie,et al.  Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks , 2016, AAAI.

[6]  André Longtin,et al.  Monitoring and Identification of Sepsis Development through a Composite Measure of Heart Rate Variability , 2012, PloS one.

[7]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[8]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Masafumi Hagiwara,et al.  Theoretical derivation of momentum term in back-propagation , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[10]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  P. Charles,et al.  Predicting outcome in patients with sepsis: new biomarkers for old expectations , 2014, Critical Care.

[12]  Hien Nguyen,et al.  From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system , 2014, J. Am. Medical Informatics Assoc..

[13]  Cheng H. Lee,et al.  Imputation-Enhanced Prediction of Septic Shock in ICU Patients , 2012 .

[14]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[15]  Thomas Brox,et al.  Synthesizing the preferred inputs for neurons in neural networks via deep generator networks , 2016, NIPS.

[16]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[17]  Dewang Shavdia,et al.  Septic shock : providing early warnings through multivariate logistic regression models , 2007 .

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  Elif Derya Übeyli,et al.  Recurrent neural networks employing Lyapunov exponents for EEG signals classification , 2005, Expert Syst. Appl..

[21]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[22]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[23]  A. Simpson,et al.  A Severe Sepsis Mortality Prediction Model and Score for Use With Administrative Data , 2016, Critical care medicine.

[24]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[25]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Seppo J. Ovaska,et al.  A modified Elman neural network model with application to dynamical systems identification , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[27]  Mitchell M. Levy,et al.  2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference , 2003, Intensive Care Medicine.

[28]  Klaus-Robert Müller,et al.  Interpretable deep neural networks for single-trial EEG classification , 2016, Journal of Neuroscience Methods.

[29]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[30]  W. Knaus,et al.  Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP/SCCM Consensus Conference Committee. American College of Chest Physicians/Society of Critical Care Medicine. , 1992, Chest.

[31]  R. Bellomo,et al.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). , 2016, JAMA.

[32]  Alexander Binder,et al.  Explaining nonlinear classification decisions with deep Taylor decomposition , 2015, Pattern Recognit..

[33]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[34]  Yoshua Bengio,et al.  Big Neural Networks Waste Capacity , 2013, ICLR.

[35]  R. Schiffer,et al.  Recurrent neural network-based approach for early recognition of Alzheimer's disease in EEG , 2001, Clinical Neurophysiology.

[36]  Herbert Jaeger,et al.  Echo state network , 2007, Scholarpedia.

[37]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[38]  P. Pronovost,et al.  A targeted real-time early warning score (TREWScore) for septic shock , 2015, Science Translational Medicine.

[39]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[40]  M. J. Pearce,et al.  Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients , 2008, Clinical and Vaccine Immunology.

[41]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[42]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[43]  Joshua A. Doherty,et al.  Early prediction of septic shock in hospitalized patients. , 2010, Journal of hospital medicine.

[44]  Christopher W. Barton,et al.  A computational approach to early sepsis detection , 2016, Comput. Biol. Medicine.

[45]  Fabrice Vallée,et al.  Lactate clearance for death prediction in severe sepsis or septic shock patients during the first 24 hours in Intensive Care Unit: an observational study , 2013, Annals of Intensive Care.