Artificial intelligence in critical care: prediction of sepsis in patients in intensive care from first initial laboratory parameters

Samrat Mitra; H. Sangwan

doi:10.18203/2320-6012.ijrms20201351

Authors

Samrat Mitra Department of Medicine, Military Hospital Jalandhar Cantt, Punjab, India
H. Sangwan Department of Medicine, Military Hospital Jalandhar Cantt, Punjab, India

DOI:

https://doi.org/10.18203/2320-6012.ijrms20201351

Keywords:

Artificial intelligence, Coagulation study, D-dimer, Fibrinogen, Machine learning, Sepsis, Sonocolot

Abstract

Background: Sepsis is a leading cause of morbidity and mortality in the critical care setting. The analysis of hemostatic parameters at admission have been proven to be a predictive marker for development of sepsis in the ICU. The present study aims to develop a machine learning model which can predict the development of sepsis after 72 hours of ICU admission, from initial assessment of hemostatic parameters.

Methods: A total of 170 ICU admissions over six months (May 2018 - Dec 2018) period were included in the study. Hemostatic parameters including platelet counts, prothrombin time and Sonoclot assay were assayed at time of admission. The patients were followed up for development of sepsis. The data was split in two sets: training (100) and test (70). A machine learning model was developed using the linear discriminant analysis (LDA) model, in the R programming environment. The statistical parameters employed were sensitivity, specificity, positive and negative predictive value.

Results: A comparison of incidence of development of clinical sepsis and predicted sepsis by the model showed 74.19% sensitivity and 84.61% specificity over the testing set. 06 false positives and 08 false negative predictions were encountered.

Conclusions: The model shows potential to be used as a predictive tool for development of sepsis in the critical care ward. Moderate sensitivity and good specificity were achieved by the model, highlighting the role of hematologic assessment at admission in prediction of development of sepsis. However, further studies with larger datasets are required before implementation in clinical practice.

Metrics

Metrics Loading ...

References

Smith SA. The cell-based model of coagulation. J Emerg Crit Care. 2009;19:3-10.

Hayem G. Du Sang et de Ses Alterations Aanatomique [Blood and its Anatomical Alterations]. Paris, France: G. Masson; 1889;323.

Hartert H, Schaeder J. The physical and biological constants of thromboelastography. Biorheol. 1962; 1:31-9.

Kaibara M. Dynamic viscoelastic study of the formation of fibrin networks in fibrinogen-thrombin systems and plasma. Biorheol. 1973;10:61-73.

Ferraris VA, Ferraris SP, Saha SP, Hessel II EA, Haan CK, Royston BD, et al. Perioperative blood transfusion and blood conservation in cardiac surgery: the Society of Thoracic Surgeons and The Society of Cardiovascular Anesthesiologists clinical practice guideline. Ann Thorac Surg. 2007 May 1;83(5):S27-86.

Kozek-Langenecker S. Management of massive operative blood loss. Minerva Anesthesiol 2007;73:401-15.

Luddington RJ. Thrombelastography /thromboelastometry. Clini Lab Haematol. 2005 Apr;27(2):81-90.

Ding R, Wang Z, Lin Y, Liu B, Zhang Z, Ma X. Comparison of a new criteria for sepsis-induced coagulopathy and International Society on Thrombosis and Haemostasis disseminated intravascular coagulation score in critically ill patients with sepsis 3.0 a retrospective study. Blood Coagul Fibrinolysis. 2018;29(6):551-8

Shillan D, Sterne JA, Champneys A, Gibbiso n B. Use of machine learning to analyse routinely collected intensive care unit data: a systematic review. Crit Care. 2019 Dec 1;23(1):284.

Lovejoy CA, Buch V, Maruthappu M. Artificial intelligence in the intensive care unit. Crit Care. 2019;23(1):7.

Vellido A, Ribas V, Morales C, Sanmartín AR, Rodríguez JC. Machine learning in critical care: state-of-the-art and a sepsis case study. Biomed engineering online. 2018 Nov 1;17(1):135.

Pirracchio R, Cohen MJ, Malenica I, Cohen J, Chambaz A, Cannesson M, et al. Big data and targeted machine learning in action to assist medical decision in the ICU. Anaesthes Crit Care Pain Med. 2019 Aug 1;38(4):377-84.

Lever A, Mackenzie I. Sepsis: definition, epidemiology, and diagnosis. BMJ. 2007 Oct 25;335(7625):879-83.

R: What is R? Available at: https://www.r-project.org/about.html. Accessed 29 June 2019.

Nemati S, Holder A, Razmi F, Stanley MD, Clifford GD, Buchman TG, et al. An interpretable machine learning model for accurate prediction of sepsis in the ICU. Crit Care Med. 2018;46:547-53.

Meyer A, Zverinski D, Pfahringer B, Kempfert J, Kuehne T, Sündermann SH, et al. Machine learning for real-time prediction of complications in critical care: a retrospective study. Lancet Respir Med. 2018 Dec 1;6(12):905-14.