research-article

Machine Learning Methods for Septic Shock Prediction

Authors:

Aiman Darwiche,

Sumitra MukherjeeAuthors Info & Claims

AIVR 2018: Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality

Pages 104 - 110

https://doi.org/10.1145/3293663.3293673

Published: 23 November 2018 Publication History

Abstract

Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. This paper develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model is built by obtaining a risk score from fitting the Cox Hazard model on multiple input features. The score is added to the list of features and the Random Forest ensemble classifier is trained to produce the model. The Cox Enhanced Random Forest (CERF) proposed method is evaluated by comparing its predictive accuracy to those of extant methods.

References

[1]

Deepak, C., and Bhat, S. 2014. Prediction of outcome in patients with sepsis using C-reactive protein & APACHE II scoring system. IOSR Journal of Dental and Medical Sciences.13, 3 (Mar. 2014), 17--20.

[2]

Henry, K., Hager, D., Pronovost, P., and Saria, S., 2015. A targeted real-time early warning score (TREWScore) for septic shock. Science Translational Medicine. 7, 299.

[3]

Marty, P., et al. 2013. Lactate clearance for death prediction in severe sepsis or septic shock patients during the first 24 hours in Intensive Care Unit: an observational study. Annals of intensive care, 3, 3 (Feb. 2013), 1--7.

[4]

Prucha, M., Bellingan, G., and Zazula, R. Sepsis biomarkers. Clinica Chimica Acta. 440 (Feb. 2015), 97--103.

[5]

Lausevic, Z., and Lausevic, M. 2012. Early Detection of Sepsis, MOF and Outcome Prediction in Severely Traumatized Patients. In Sepsis - An Ongoing and Significant Challenge, 1st ed, L. Azevedo, Ed. InTech, Rijeka, Croatia, 159--170.

[6]

Lukaszewski, R., et al. 2008. Presymptomatic prediction of sepsis in intensive care unit patients. Clinical and Vaccine Immunology. 15, 7 Jul 2008). 1089--1094.

[7]

Nguyen, S. et al., 2014. Automated electronic medical record sepsis detection in the emergency department. PeerJ, 2, e343 (Apr. 2014), 1--10.

[8]

Mohan, A., et al. 2015. Development of a mortality prediction formula due to sepsis/severe sepsis in a medical intensive care unit. Lung India. 32, 4 (Aug. 2015), 313--319.

[9]

Sawyer, A., et al. 2011. Implementation of a real-time computerized sepsis alert in nonintensive care unit patients. Critical care medicine. 39, 3 (Dec. 2011), 469--473.

[10]

Cohen, J., and McConnell, J. 1988. Limulus assay in prediction of septic shock. The Lancet. 331, 8595 (May 1988), 1165.

[11]

Matsusue, Kashihara, and S. Koizumi, S. 1988. Prediction of mortality from septic shock in gastrointestinal surgery by probit analysis. Japanese journal of surgery. 18, 1 (Jan. 1988), 18--22.

[12]

Blomkalns, A. 2006. Lactate-a marker for sepsis and trauma. Emergency Medicine Cardiac Research and Education Group. 2, 43--49.

[13]

Wang, S., Wu, F., and Wang, B. 2010. Prediction of Severe Sepsis Using SVM Model. In Advances in Computational Biology, vol. 680, H. R. Arabnia, Ed. Springer, New York, NY, 75--81.

[14]

Thiel, S., et al. 2010. Early prediction of septic shock in hospitalized patients. Journal of Hospital Medicine. 5, 1 (Jan. 2010), 19--25.

[15]

Ho, J., Lee, C., and Ghosh, J. 2012. Imputation-enhanced prediction of septic shock in ICU patients. In Proceedings of the ACM SIGKDD workshop on health informatics (Beijing, China, Aug. 2012) ACM, New York, NY.

[16]

Ribas Ripoll, V., et al. 2014. Sepsis mortality prediction with the Quotient Basis Kernel. Artificial Intelligence in Medicine. 61, 1 (Mar. 2014), 45--52.

[17]

Mao, Q., et. al. 2018. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ open. 8, 1 (Jan. 2018), 1--10.

[18]

Phua, L., Koay, E., and Lee, K. 2008. Lactate, procalcitonin, and amino-terminal pro-B-type natriuretic peptide versus cytokine measurements and clinical severity scores for prognostication in septic shock. Shock. 29, 3 (Mar. 2008), 328--333.

[19]

Mikkelsen, M., et al. 2009. Serum lactate is associated with mortality in severe sepsis independent of organ failure and shock. Critical care medicine. 37, 5 (May 2009), 1--10, May 2009.

[20]

Nguyen, H., et al. (2010). Early lactate clearance is associated with biomarkers of inflammation, coagulation, apoptosis, organ dysfunction and mortality in severe sepsis and septic shock. Journal of Inflammation. 7, 6, 1--11.

[21]

Malmir, J., Bolvardi, E., and Afzal Aghaee, M. 2014. Serum lactate is a useful predictor of death in severe sepsis and septic shock. Reviews in Clinical Medicine. 1, 3 (Feb. 2014), 97--104.

[22]

Lee, S., and An, W. 2016. New clinical criteria for septic shock: serum lactate level as new emerging vital sign. Journal of Thoracic Disease. 8, 7, 1388--1390.

[23]

Azevedo, J. 2012. Procalcitonin as a prognostic biomarker of severe sepsis and septic shock. Revista do Colégio Brasileiro de Cirurgiões. 39, 6 (Dec.2012), 456--461.

[24]

Becker, K., Snider, R., and E. Nylen, E. 2010. Procalcitonin in sepsis and systemic inflammation: a harmful biomarker and a therapeutic target. British Journal of Pharmacology. 159, 2 (Jan. 2010), 253--264.

[25]

Kibe, S., Adams, K., and Barlow, G. 2011. Diagnostic and prognostic biomarkers of sepsis in critical care. Journal of Antimicrobial Chemotherapy., 66, 2 Apr. 2011), ii33-ii40.

[26]

McLean, A., Tang, B., and Huang, S. 2015. Investigating sepsis with biomarkers. BMJ. 350, h781 (Feb. 2015).

[27]

Riedel, S. 2012. Procalcitonin and the role of biomarkers in the diagnosis and management of sepsis. Diagnostic Microbiology and Infectious Disease. 73, 3 (Jul. 2012), 221--227.

[28]

Shapiro, N., et al. 2009. A prospective, multicenter derivation of a biomarker panel to assess risk of organ dysfunction, shock, and death in emergency department patients with suspected sepsis. Critical care medicine. 37, 1 (Jan. 2009), 96--104.

[29]

Lorente, L. et al. 2009. Matrix metalloproteinase-9, -10, and tissue inhibitor of matrix metalloproteinases-1 blood levels as biomarkers of severity and mortality in sepsis. Critical Care. 13, 5 (Oct. 2009). 1--9.

[30]

Hattori, N., et al. 2009. YKL-40 identified by proteomic analysis as a biomarker of sepsis. Shock. 32, 4 (Oct. 2009), 393--400.

[31]

Sturgess, D., et al. 2010. Prediction of hospital outcome in septic shock: a prospective comparison of tissue Doppler and cardiac biomarkers. Critical Care. 14, 2 (Mar. 2010).

[32]

Ricciuto, D., et al. 2011. Angiopoietin-1 and angiopoietin-2 as clinically informative prognostic biomarkers of morbidity and mortality in severe sepsis. Critical care medicine. 39, 4 Apr. 2011), 702--710.

[33]

Gibot, S., et al. 2012. Combination Biomarkers to Diagnose Sepsis in the Critically Ill Patient. American Journal of Respiratory and Critical Care Medicine. 186, 1 (Jul. 2012), 65--71.

[34]

K. Reinhart, K., et al. 2012. New approaches to sepsis: molecular diagnostics and biomarkers. Clinical microbiology reviews, 25, 4, 609--634.

[35]

Rivers, E., et. al. 2013. Early Biomarker Activity in Severe Sepsis and Septic Shock and a Contemporary Review of Immunotherapy Trials: Not a Time to Give Up, But to Give It Earlier. Shock. 39, 2, 127--137.

[36]

Berger, T., et al. 2013. Shock Index and Early Recognition of Sepsis in the Emergency Department: Pilot Study. Western Journal of Emergency Medicine. 14, 2, 168--174.

[37]

Gultepe, E., et al. 2014. From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system. Journal of the American Medical Informatics Association. 21, 2, 315--325.

[38]

Carrara, M., Baselli, G., and Ferrario, M. 2015. Mortality Prediction Model of Septic Shock Patients Based on Routinely Recorded Data. Computational and Mathematical Methods in Medicine. 2015 (Sep. 2015).

[39]

Desautels, T., et al. 2016. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Medical Informatics. 4, 3 (Sep. 2016).

[40]

Kelly, B., et al. 2016. Combined biomarkers discriminate a low likelihood of bacterial infection among surgical intensive care unit patients with suspected sepsis. Diagnostic Microbiology and Infectious Disease. 85, 1, 109--115.

[41]

Holder, A., et al. 2016. Predictors of early progression to severe sepsis or shock among emergency department patients with nonsevere sepsis. International Journal of Emergency Medicine. 9, 1 (Feb. 2016).

[42]

Sundén-Cullberg, J., et al. 2017. Fever in the emergency department predicts survival of patients with severe sepsis and septic shock admitted to the ICU. Critical care medicine. 45, 4.

[43]

Goldberger, A., et al. 2000. Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation. 101, 23, e215-e220.

[44]

Verburg, I., et al. 2018. Is patient length of stay associated with intensive care unit characteristics?. Journal of Critical Care. 43 (Feb. 2018), 114--121.

[45]

Ho, J., Lee, C., and Ghosh, J. 2014. Septic shock prediction for patients with missing data. ACM Transactions on Management Information Systems. 5, 1, 1--15.

Digital Library

[46]

Singer, M., et al. 2016. The third international consensus definitions for sepsis and septic shock (sepsis-3). JAMA. 315, 8, 801--810.

[47]

Therneau, T., Crowson, C., and Atkinson, E. 2018. Using time dependent covariates and time dependent coefficients in the Cox Model. (Jul. 2018). Retrieved Sept. 12, 2018 from https://cran.r-project.org/web/packages/survival/vignettes/timedep.pdf.

[48]

Kim, S., Park, T., and Kon, M. 2013. Computational methods for cancer survival classification using intermediate information. In Proceedings of the International Work-Conference on Bioinformatics and Biomedical Engineering (Granada, Spain, Mar. 2013). Copicentro Granada D.L, Granada, Spain.

[49]

Li, Z., Zhou, S., Choubey, S., and Sievenpiper, C. 2007. Failure event prediction using the Cox proportional hazard model driven by frequent failure signatures. IIE transactions. 39, 3, 303--315.

[50]

Fox, J., and Weisberg, S. 2011. Cox Proportional-Hazards Regression for Survival Data in R. (Feb. 2011). Retrieved Sept. 12, 2018 from http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.459.4496&rep=rep1&type=pdf.

[51]

Staley, J., et al. 2017. A comparison of Cox and logistic regression for use in genome-wide association studies of cohort and case-cohort design. European Journal of Human Genetics. 25, 854--862.

[52]

Liaw, L. 2018. Breiman and Cutlers random forests for classification and regression. cran.r-project.org, Mar. 25, 2018. {Online}. Available: https://cran.r-project.org/web/packages/randomForest/randomForest.pdf. {Accessed: Sept. 12, 2018}.

[53]

Kourou, K. 2015. Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal. 13, 8--17.

[54]

Srimani, P., and Koti, M. 2013. Medical diagnosis using ensemble classifiers-a novel machine-learning approach. Journal of Advanced Computing. 1, 9--27.

[55]

Lavanya, D., and Rani, K. 2012. Ensemble decision tree classifier for breast cancer data. International Journal of Information Technology Convergence and Services. 2, 1, 17--24.

[56]

Kelarev, A., et al. 2012. Improving classifications for cardiac autonomic neuropathy using multi-level ensemble classifiers and feature selection based on random forest. In Proceedings of the Tenth Australasian Data Mining Conference. (Sydney, Australia, Dec. 5-7 2012). Y. Zhao, J. Li, P. Kennedy, P. Christen, Eds. Australian Computer Society, Sydney, Australia, 93--102.

Digital Library

[57]

Williams, J., et al. 2013. Machine learning techniques for diagnostic differentiation of mild cognitive impairment and dementia. In the Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence (Bellevue, WA, Jul 4--18, 2013). AAAI, Bellevue, WA.

[58]

Ali, S., Majid, A., and Khan, A. 2014. IDM-PhyChm-Ens: intelligent decision-making ensemble methodology for classification of human breast cancer using physicochemical properties of amino acids. Amino acids. 46, 4, 977--993.

[59]

Gupta, S., et al. 2014. Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry. BMJ open. 4, 3.

[60]

Yao, Y., Guo, H., and Yang, X. 2015. PPCM: Combing Multiple Classifiers to Improve Protein-Protein Interaction Prediction. International Journal of Genomics. 2015.

[61]

Morino, K. et al. 2015. Predicting disease progression from short biomarker series using expert advice algorithm. Scientific Reports. 5, 8953.

[62]

Beleites, C., et al. 2013. Sample size planning for classification models. Analytica Chimica Acta. 760, 25--33.

[63]

Refaeilzadeh, P., Tang, L., and Liu, H. 2009. Cross-validation. In Encyclopedia of Database Systems, 2009 ed., Springer, Boston, MA, 2009, 532--538.

[64]

Strobl, C., Malley, J., and Tutz, G. 2009. An Introduction to Recursive Partitioning: Rationale, Application and Characteristics of Classification and Regression Trees, Bagging and Random Forests. Psychological methods. 14, 4, 323--348.

Cited By

Ilhan Taskin ZYildirak KAladag C(2023)An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection applicationJournal of Big Data10.1186/s40537-023-00720-910:1Online publication date: 30-Mar-2023
https://doi.org/10.1186/s40537-023-00720-9
A. SB. S(2023)Analysis of machine learning and deep learning prediction models for sepsis and neonatal sepsis: A systematic reviewICT Express10.1016/j.icte.2023.07.0079:6(1215-1225)Online publication date: Dec-2023
https://doi.org/10.1016/j.icte.2023.07.007
Darwiche AEL-Geneidy AMukherjee S(2021)Improving Septic Shock Prediction with AdaBoost and Cox Regression Model2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)10.1109/ICCECE51280.2021.9342457(522-527)Online publication date: 15-Jan-2021
https://doi.org/10.1109/ICCECE51280.2021.9342457
Show More Cited By

Index Terms

Machine Learning Methods for Septic Shock Prediction
1. Computing methodologies
  1. Machine learning
    1. Machine learning algorithms
      1. Ensemble methods

Recommendations

Septic Shock Prediction for Patients with Missing Data

Sepsis and septic shock are common and potentially fatal conditions that often occur in intensive care unit (ICU) patients. Early prediction of patients at risk for septic shock is therefore crucial to minimizing the effects of these complications. ...
Mortality prediction of septic shock patients using probabilistic fuzzy systems

Graphical abstractDisplay Omitted HighlightsProbabilistic fuzzy systems (PFS) are used to predict mortality of septic shock patients.PFS models are compared with Takagi-Sugeno fuzzy models and logistic regression models.The methods are tested using ICU ...
Septic shock prediction and knowledge discovery through temporal pattern mining
Abstract
Sepsis is the body's adverse response to infection which can lead to septic shock and eventually death if not treated in a timely manner. Analyzing patterns in sepsis patients' health status over time can help predict septic shock before its ...
Highlights
- A framework to identify relevant temporal patterns in data is proposed.
- Recent temporal pattern mining is combined with three feature selection techniques.
- Septic shock prediction models are trained using temporal patterns.
- ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

AIVR 2018: Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality

November 2018

144 pages

ISBN:9781450366410

DOI:10.1145/3293663

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

University of Tsukuba: University of Tsukuba

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 23 November 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

AIVR 2018

AIVR 2018: 2018 International Conference on Artificial Intelligence and Virtual Reality

November 23 - 25, 2018

Nagoya, Japan

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
169
Total Downloads

Downloads (Last 12 months)21
Downloads (Last 6 weeks)1

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ilhan Taskin ZYildirak KAladag C(2023)An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection applicationJournal of Big Data10.1186/s40537-023-00720-910:1Online publication date: 30-Mar-2023
https://doi.org/10.1186/s40537-023-00720-9
A. SB. S(2023)Analysis of machine learning and deep learning prediction models for sepsis and neonatal sepsis: A systematic reviewICT Express10.1016/j.icte.2023.07.0079:6(1215-1225)Online publication date: Dec-2023
https://doi.org/10.1016/j.icte.2023.07.007
Darwiche AEL-Geneidy AMukherjee S(2021)Improving Septic Shock Prediction with AdaBoost and Cox Regression Model2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)10.1109/ICCECE51280.2021.9342457(522-527)Online publication date: 15-Jan-2021
https://doi.org/10.1109/ICCECE51280.2021.9342457
El-Geneidy AMukherjee SDarwiche A(2021)Prediction of Sudden Cardiac Death Using Ensemble ClassifiersAdvances in Information and Communication10.1007/978-3-030-73103-8_48(677-692)Online publication date: 16-Apr-2021
https://doi.org/10.1007/978-3-030-73103-8_48
Mollura MRomano SMantoan GLehman LBarbieri R(2020) Prediction of Septic Shock Onset in ICU by Instantaneous Monitoring of Vital Signs * 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)10.1109/EMBC44109.2020.9176276(2768-2771)Online publication date: Jul-2020
https://doi.org/10.1109/EMBC44109.2020.9176276

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents