AN EARLY PREDICTION AND DIAGNOSIS OF SEPSIS IN INTENSIVE CARE UNITS: AN UNSUPERVİSED MACHINE LEARNING MODEL

Abstract

Sepsis infection, which is one of the most important causes of death in intensive care units, is seen as a severe global health crisis. If an early diagnosis of sepsis infection cannot be made, and treatment is not started rapidly, septic shock may result in multiple organ failure and death is almost inevitable. Therefore, it is vital to establish an early diagnosis and start the treatment at once. This study aims to accomplish a new model of unsupervised machine learning using lactate and Ph laboratory test values, which are considered to be important parameters to diagnose sepsis infection. The data used in the study have been obtained from MIMIC-III international clinical database. Unsupervised machine learning has been performed via the Fuzzy-C algorithm along with validity indexes like Xie Beni on patients’ data diagnosed sepsis and non-sepsis. The machine-generated ten labels at the end of the training session considering-designed validity indexes. The labelled cluster representatives have been reduced to two dimensions by Principal Component Analysis method in order to monitor the learning in a two-dimensional space. The study contributes to the literature by conducting unsupervised learning through two parameters (Lactate and Ph) and leading to multi-parameter studies. In addition, the study reports that there are five types of sepsis patterns in terms of Lactate and PH laboratory tests. 

Keywords

• Unsupervised Learning,Septic Infection,Intensive Care Unit,Fuzzy-C Means Clustering

References

1. [1] “The Global Competitiveness Report 2017-2018 | World Economic Forum.” [Online]. Available: https://www.weforum.org/reports/the-global-competitiveness-report-2017-2018. [Accessed: 25-Oct-2019].
2. [2] G. Silahtaroğlu and N. Yılmaztürk, “Data analysis in health and big data: A machine learning medical diagnosis model based on patients’ complaints,” Commun. Stat. - Theory Methods, 2019.
3. [3] “Sepsis — Global Sepsis Alliance.” [Online]. Available: https://www.global-sepsis-alliance.org/sepsis. [Accessed: 02-Nov-2019].
4. [4] W. Bone, R. C., Balk, R. A., Cerra, F. B., Dellinger, R. P., Fein, A. M., Knaus, W. A., ... & Sibbald, “Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis,” Chest, vol. 101, no. 6, pp. 1644–1655, 1992.
5. [5] World Health Statistics, 2018, https://apps.who.int/iris/bitstream/handle/10665/272596/9789241565585-eng.pdf,[ Accessed: 02-Nov-2019]
6. [6] T. Szakmany et al., “Sepsis prevalence and outcome on the general wards and emergency departments in Wales: Results of a multi-centre, observational, point prevalence study,” PLoS One, 2016.
7. [7] C. A. Lovejoy, V. Buch, and M. Maruthappu, “Artificial intelligence in the intensive care unit,” Critical Care. 2019.
8. [8] S. Nemati, A. Holder, F. Razmi, M. D. Stanley, G. D. Clifford, and T. G. Buchman, “An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU,” Crit. Care Med., 2018.

9. [9] G. Broder, M. W.- Science, and undefined 1964, “Excess lactate: an index of reversibility of shock in human patients,” science.sciencemag.org.
10. [10] D. W. Callaway, N. I. Shapiro, M. W. Donnino, C. Baker, and C. L. Rosen, “Serum lactate and base deficit as predictors of mortality in normotensive elderly blunt trauma patients,” J. Trauma - Inj. Infect. Crit. Care, vol. 66, no. 4, pp. 1040–1044, Apr. 2009.
11. [11] M. J. Vandromme, R. L. Griffin, J. A. Weinberg, L. W. Rue, and J. D. Kerby, “Lactate is a better predictor than systolic blood pressure for determining blood requirement and mortality: could prehospital measures improve trauma triage?,” J. Am. Coll. Surg., vol. 210, no. 5, pp. 861–7, 867–9, May 2010.
12. [12] G. Dede, L. Şahan, B. Dede, and S. Demirbilek, “Araştırma Makalesi Kan Laktat Seviyesi Yoğun Bakım Hastalarında Mortaliteyi Tahmin Etmede Ne Kadar Etkilidir? Blood Lactate Levels Intensive Care Patients Mortality Estimating, How much?”
13. [13] “Ağır Sepsiste Santral Venöz, Arteriyel ve Periferik Venöz Kan Gazı Değerlerinin Karşılaştırılması | Makale | Türkiye Klinikleri.” [Online]. Available: https://www.turkiyeklinikleri.com/article/tr-agir-sepsiste-santral-venoz-arteriyel-ve-periferik-venoz-kan-gazi-degerlerinin-karsilastirilmasi-56310.html. [Accessed: 03-Nov-2019].
14. [14] H. B. Nguyen et al., “Early lactate clearance is associated with improved outcome in severe sepsis and septic shock,” Crit. Care Med., 2004.
15. [15] C. D. Bouch and J. P. Thompson, “Severity scoring systems in the critically ill,” Contin. Educ. Anaesthesia, Crit. Care Pain, vol. 8, no. 5, pp. 181–185, 2008.
16. [16] R. J. Delahanty, J. A. Alvarez, L. M. Flynn, R. L. Sherwin, and S. S. Jones, “Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis,” Ann. Emerg. Med., vol. 73, no. 4, pp. 334–344, Apr. 2019.
17. [17] A. E. W. Johnson et al., “MIMIC-III, a freely accessible critical care database,” Sci. Data, vol. 3, May 2016.
18. [18] J. C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters,” J. Cybern., 1973.
19. [19] J. C. Bezdek, R. Ehrlich, and W. Full, “FCM: The fuzzy c-means clustering algorithm,” Comput. Geosci., 1984.
20. [20] A. Flores-Sintas, J. Cadenas, F. M.-F. S. and Systems, and undefined 1999, “Membership functions in the fuzzy C-means algorithm,” Elsevier.
21. [21] X. L. Xie and G. Beni, “A validity measure for fuzzy clustering,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 13, no. 8, pp. 841–847, Aug. 1991.