Predictive Value of Red Blood Cell Distribution Width in Septic Shock Patients with Thrombocytopenia: A Retrospective Study Using Machine Learning

Overview

Journal J Clin Lab Anal

Publisher Wiley

Specialties Biomedical Engineering
Biotechnology
Pathology

Date 2021 Oct 21

PMID 34674393

Citations 6

Authors

Jianmin Ling

Tongzhou Liao

Yanqing Wu

Zhaohua Wang

Hai Jin

Feng Lu

Minghao Fang

Affiliations

Soon will be listed here.

Abstract

Background: Sepsis-associated thrombocytopenia (SAT) is common in critical patients and results in the elevation of mortality. Red cell distribution width (RDW) can reflect body response to inflammation and oxidative stress. We try to investigate the relationship between the RDW and the prognosis of patients with SAT through machine learning.

Methods: 809 patients were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) were used to analyze the impact of each feature. Logistic regression analysis, propensity score matching (PSM), receiver-operating characteristics (ROC) curve analysis, and the Kaplan-Meier method were used for data processing.

Results: The patients with thrombocytopenia had higher 28-day mortality (48.2%). Machine learning indicated that RDW was the second most important in predicting 28-day mortality. The RDW was significantly increased in non-survivors by logistic regression and PSM. ROC curve shows that RDW has moderate predictive power for 28-day mortality. The patients with RDW>16.05 exhibited higher mortality through Kaplan-Meier analysis.

Conclusions: Interpretable machine learning can be applied in clinical research. Elevated RDW is not only common in patients with SAT but is also associated with a poor prognosis.

Citing Articles

Association Between the Red Blood Cell Distribution Width and 30-Day Mortality in Intensive Care Patients Undergoing Cardiac Surgery: A Retrospective Observational Study Based on the Medical Information Mart for Intensive Care-IV Database.

Chen W, Yu P, Chen C, Cai S, Chen J, Zheng C Ann Lab Med. 2024; 44(5):401-409.

PMID: 38469636 PMC: 11169773. DOI: 10.3343/alm.2023.0345.

Interpretable machine learning model for early prediction of 28-day mortality in ICU patients with sepsis-induced coagulopathy: development and validation.

Zhou S, Lu Z, Liu Y, Wang M, Zhou W, Cui X Eur J Med Res. 2024; 29(1):14.

PMID: 38172962 PMC: 10763177. DOI: 10.1186/s40001-023-01593-7.

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records.

Baik S, Hong K, Park D BMC Bioinformatics. 2023; 24(1):190.

PMID: 37161395 PMC: 10169101. DOI: 10.1186/s12859-023-05321-0.

Applications of Artificial Intelligence in Thrombocytopenia.

Elshoeibi A, Ferih K, Elsabagh A, Elsayed B, Elhadary M, Marashi M Diagnostics (Basel). 2023; 13(6).

PMID: 36980370 PMC: 10047875. DOI: 10.3390/diagnostics13061060.

Diagnostic value of RDW for the prediction of mortality in adult sepsis patients: A systematic review and meta-analysis.

Wu H, Liao B, Cao T, Ji T, Huang J, Ma K Front Immunol. 2022; 13:997853.

PMID: 36325342 PMC: 9618606. DOI: 10.3389/fimmu.2022.997853.

References

Perlstein T, Weuve J, Pfeffer M, Beckman J . Red blood cell distribution width and mortality risk in a community-based prospective cohort. Arch Intern Med. 2009; 169(6):588-94. PMC: 3387573. DOI: 10.1001/archinternmed.2009.55. View

Parsa A, Movahedi A, Taghipour H, Derrible S, Mohammadian A . Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accid Anal Prev. 2019; 136:105405. DOI: 10.1016/j.aap.2019.105405. View

Menard C, Kumar A, Houston D, Turgeon A, Rimmer E, Houston B . Evolution and Impact of Thrombocytopenia in Septic Shock: A Retrospective Cohort Study. Crit Care Med. 2019; 47(4):558-565. DOI: 10.1097/CCM.0000000000003644. View

Aktas G, Sit M, Karagoz I, Erkus E, Ozer B, Kocak M . Could Red Cell Distribution Width be a Marker of Thyroid Cancer?. J Coll Physicians Surg Pak. 2017; 27(9):556-558. DOI: 2699. View

Lippi G, Targher G, Montagnana M, Salvagno G, Zoppini G, Guidi G . Relation between red blood cell distribution width and inflammatory biomarkers in a large cohort of unselected outpatients. Arch Pathol Lab Med. 2009; 133(4):628-32. DOI: 10.5858/133.4.628. View

Nemati S, Holder A, Razmi F, Stanley M, Clifford G, Buchman T . An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU. Crit Care Med. 2017; 46(4):547-553. PMC: 5851825. DOI: 10.1097/CCM.0000000000002936. View

Grommes J, Alard J, Drechsler M, Wantha S, Morgelin M, Kuebler W . Disruption of platelet-derived chemokine heteromers prevents neutrophil extravasation in acute lung injury. Am J Respir Crit Care Med. 2012; 185(6):628-36. PMC: 3326286. DOI: 10.1164/rccm.201108-1533OC. View

Islam M, Nasrin T, Walther B, Wu C, Yang H, Li Y . Prediction of sepsis patients using machine learning approach: A meta-analysis. Comput Methods Programs Biomed. 2019; 170:1-9. DOI: 10.1016/j.cmpb.2018.12.027. View

Vincent J, Moreno R, Takala J, Willatts S, de Mendonca A, Bruining H . The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine. Intensive Care Med. 1996; 22(7):707-10. DOI: 10.1007/BF01709751. View

10.

Sincer I, Mansiroglu A, Aktas G, Gunes Y, Kocak M . Association between Hemogram Parameters and Coronary Collateral Development in Subjects with Non-ST-Elevation Myocardial Infarction. Rev Assoc Med Bras (1992). 2020; 66(2):160-165. DOI: 10.1590/1806-9282.66.2.160. View

11.

Halacli B, Unver N, Oskay Halacli S, Canpinar H, Ortac Ersoy E, Ocal S . Investigation of hemophagocytic lymphohistiocytosis in severe sepsis patients. J Crit Care. 2016; 35:185-90. DOI: 10.1016/j.jcrc.2016.04.034. View

12.

Kim C, Kim S, Lee M, Kwon Y, Kim Y, Park K . An increase in mean platelet volume from baseline is associated with mortality in patients with severe sepsis or septic shock. PLoS One. 2015; 10(3):e0119437. PMC: 4350997. DOI: 10.1371/journal.pone.0119437. View

13.

Strauss R, Wehler M, Mehler K, Kreutzer D, Koebnick C, Hahn E . Thrombocytopenia in patients in the medical intensive care unit: bleeding prevalence, transfusion requirements, and outcome. Crit Care Med. 2002; 30(8):1765-71. DOI: 10.1097/00003246-200208000-00015. View

14.

Aktas G . Hematological predictors of novel Coronavirus infection. Rev Assoc Med Bras (1992). 2021; 67Suppl 1(Suppl 1):1-2. DOI: 10.1590/1806-9282.67.Suppl1.20200678. View

15.

Zakynthinos S, Papanikolaou S, Theodoridis T, Zakynthinos E, Christopoulou-Kokkinou V, Katsaris G . Sepsis severity is the major determinant of circulating thrombopoietin levels in septic patients. Crit Care Med. 2004; 32(4):1004-10. DOI: 10.1097/01.ccm.0000121433.61546.a0. View

16.

Ghali J . Anemia and heart failure. Curr Opin Cardiol. 2009; 24(2):172-8. DOI: 10.1097/HCO.0b013e328324ecec. View

17.

Lundberg S, Erion G, Chen H, DeGrave A, Prutkin J, Nair B . From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell. 2020; 2(1):56-67. PMC: 7326367. DOI: 10.1038/s42256-019-0138-9. View

18.

Nguyen T, Cruz M, Carcillo J . Thrombocytopenia-Associated Multiple Organ Failure and Acute Kidney Injury. Crit Care Clin. 2015; 31(4):661-74. PMC: 5281060. DOI: 10.1016/j.ccc.2015.06.004. View

19.

Ma A, Kubes P . Platelets, neutrophils, and neutrophil extracellular traps (NETs) in sepsis. J Thromb Haemost. 2007; 6(3):415-20. DOI: 10.1111/j.1538-7836.2007.02865.x. View

20.

Kakihana Y, Ito T, Nakahara M, Yamaguchi K, Yasuda T . Sepsis-induced myocardial dysfunction: pathophysiology and management. J Intensive Care. 2016; 4:22. PMC: 4804632. DOI: 10.1186/s40560-016-0148-1. View