A Comparative Analysis of HMM and CRF for Early Prediction of Sepsis

This study aims to detect and predict sepsis precisely in ICU patients according to the data published for Physionet challenge 2019. Sepsis prediction can help in early intervention and therefore less mortality rate. Hidden Markov Model (HMM) is applied with the independence assumption of features; however, to tackle this problem, Linear-chain conditional random field (CRF) is implemented and the results are compared to HMM. The results show that CRF outperforms HMM in the early prediction of sepsis. The team of the authors, named IMSAT, ranked 50 in the mentioned challenge by gaining a utility score of 0.19.

[1]  Ikechukwu I. Ayogu,et al.  A comparative study of hidden Markov model and conditional random fields on a Yorùba part-of-speech tagging task , 2017, 2017 International Conference on Computing Networking and Informatics (ICCNI).

[2]  Shamim Nemati,et al.  Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019 , 2019, 2019 Computing in Cardiology (CinC).

[3]  Alfredo Vellido,et al.  Machine Learning for Critical Care: An Overview and a Sepsis Case Study , 2017, IWBBIO.

[4]  Guillaume Bouchard,et al.  The Tradeoff Between Generative and Discriminative Classifiers , 2004 .

[5]  Diego A. Alvarez,et al.  Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room , 2005, Critical care.

[6]  D. Angus,et al.  Assessment of Global Incidence and Mortality of Hospital-treated Sepsis. Current Estimates and Limitations. , 2016, American journal of respiratory and critical care medicine.

[7]  James M. Blum,et al.  Temporal Features and Kernel Methods for Predicting Sepsis in Postoperative Patients , 2010 .

[8]  Natalie McLymont,et al.  Scoring systems for the characterization of sepsis and associated outcomes. , 2016, Annals of translational medicine.

[9]  Khalid Ashraf,et al.  Sepsis Prediction and Vital Signs Ranking in Intensive Care Unit Patients , 2018, ArXiv.

[10]  Uzay Kaymak,et al.  Mortality prediction of septic shock patients using probabilistic fuzzy systems , 2016, Appl. Soft Comput..

[11]  Lionel Tarassenko,et al.  Logistic Regression-HSMM-Based Heart Sound Segmentation , 2016, IEEE Transactions on Biomedical Engineering.

[12]  Alfredo Vellido,et al.  Severe sepsis mortality prediction with logistic regression over latent factors , 2012, Expert Syst. Appl..

[13]  William Fleischman,et al.  Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach. , 2016, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[14]  Andrew McCallum,et al.  An Introduction to Conditional Random Fields , 2010, Found. Trends Mach. Learn..

[15]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[16]  Chieh-Chen Wu,et al.  Prediction of sepsis patients using machine learning approach: A meta-analysis , 2019, Comput. Methods Programs Biomed..

[17]  Fan Wu,et al.  The Prediction of Severe Sepsis Using SVM Model , 2009, BIOCOMP.

[18]  Ashish Sharma,et al.  Early Prediction of Sepsis from Clinical Data: the PhysioNet/Computing in Cardiology Challenge 2019 , 2019, 2019 Computing in Cardiology (CinC).