Predicting Mortality of Patients with Acute Kidney Injury in the ICU Using XGBoost Model

Overview

Journal PLoS One

Specialties General Medicine
Science

Date 2021 Feb 4

PMID 33539390

Citations 46

Authors

Jialin Liu

Jinfa Wu

Siru Liu

Mengdie Li

Kunchang Hu

Ke Li

Affiliations

Soon will be listed here.

Abstract

Purpose: The goal of this study is to construct a mortality prediction model using the XGBoot (eXtreme Gradient Boosting) decision tree model for AKI (acute kidney injury) patients in the ICU (intensive care unit), and to compare its performance with that of three other machine learning models.

Methods: We used the eICU Collaborative Research Database (eICU-CRD) for model development and performance comparison. The prediction performance of the XGBoot model was compared with the other three machine learning models. These models included LR (logistic regression), SVM (support vector machines), and RF (random forest). In the model comparison, the AUROC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model.

Results: A total of 7548 AKI patients were analyzed in this study. The overall in-hospital mortality of AKI patients was 16.35%. The best performing algorithm in this study was XGBoost with the highest AUROC (0.796, p < 0.01), F1(0.922, p < 0.01) and accuracy (0.860). The precision (0.860) and recall (0.994) of the XGBoost model rank second among the four models.

Conclusion: XGBoot model had obvious advantages of performance compared to the other machine learning models. This will be helpful for risk identification and early intervention for AKI patients at risk of death.

Citing Articles

Predicting the risk of heart failure after acute myocardial infarction using an interpretable machine learning model.

Lin Q, Zhao W, Zhang H, Chen W, Lian S, Ruan Q Front Cardiovasc Med. 2025; 12:1444323.

PMID: 39925976 PMC: 11802525. DOI: 10.3389/fcvm.2025.1444323.

A machine learning model to predict neurological deterioration after mild traumatic brain injury in older adults.

Abe D, Inaji M, Hase T, Suehiro E, Shiomi N, Yatsushige H Front Neurol. 2025; 15():1502153.

PMID: 39830200 PMC: 11739101. DOI: 10.3389/fneur.2024.1502153.

Acute Kidney Injury Prognosis Prediction Using Machine Learning Methods: A Systematic Review.

Lin Y, Shi T, Kong G Kidney Med. 2025; 7(1):100936.

PMID: 39758155 PMC: 11699606. DOI: 10.1016/j.xkme.2024.100936.

Predicting student self-efficacy in Muslim societies using machine learning algorithms.

Ba-Aoum M, Alrezq M, Datta J, Triantis K Front Big Data. 2024; 7:1449572.

PMID: 39735162 PMC: 11672345. DOI: 10.3389/fdata.2024.1449572.

Exploring the role of Artificial Intelligence in Acute Kidney Injury management: a comprehensive review and future research agenda.

Al-Absi D, Simsekler M, Omar M, Anwar S BMC Med Inform Decis Mak. 2024; 24(1):337.

PMID: 39543611 PMC: 11566964. DOI: 10.1186/s12911-024-02758-y.

References

Kothiwale V, Patil P, Gaur S . Correlation of Thyroid Hormone Profile with the Acute Physiology and Chronic Health Evaluation II Score as a Prognostic Marker in Patients with Sepsis in the Intensive Care Unit. J Assoc Physicians India. 2019; 66(7):59-62. View

Essay P, Shahin T, Balkan B, Mosier J, Subbian V . The Connected Intensive Care Unit Patient: Exploratory Analyses and Cohort Discovery From a Critical Care Telemedicine Database. JMIR Med Inform. 2019; 7(1):e13006. PMC: 6365875. DOI: 10.2196/13006. View

Mayampurath A, Sanchez-Pinto L, Carey K, Venable L, Churpek M . Combining patient visual timelines with deep learning to predict mortality. PLoS One. 2019; 14(7):e0220640. PMC: 6668841. DOI: 10.1371/journal.pone.0220640. View

Lin K, Hu Y, Kong G . Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. Int J Med Inform. 2019; 125:55-61. DOI: 10.1016/j.ijmedinf.2019.02.002. View

Caicedo-Torres W, Gutierrez J . ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU. J Biomed Inform. 2019; 98:103269. DOI: 10.1016/j.jbi.2019.103269. View

Hoste E, Kellum J, Selby N, Zarbock A, Palevsky P, Bagshaw S . Global epidemiology and outcomes of acute kidney injury. Nat Rev Nephrol. 2018; 14(10):607-625. DOI: 10.1038/s41581-018-0052-0. View

Parreco J, Soe-Lin H, Parks J, Byerly S, Chatoor M, Buicko J . Comparing Machine Learning Algorithms for Predicting Acute Kidney Injury. Am Surg. 2019; 85(7):725-729. View

Kane-Gill S, Sileanu F, Murugan R, Trietley G, Handler S, Kellum J . Risk factors for acute kidney injury in older adults with critical illness: a retrospective cohort study. Am J Kidney Dis. 2014; 65(6):860-9. PMC: 4442750. DOI: 10.1053/j.ajkd.2014.10.018. View

Kwon J, Jeon K, Kim H, Kim M, Lim S, Kim K . Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction. PLoS One. 2019; 14(10):e0224502. PMC: 6822714. DOI: 10.1371/journal.pone.0224502. View

10.

Ottenbacher K, Smith P, Illig S, Linn R, Fiedler R, Granger C . Comparison of logistic regression and neural networks to predict rehospitalization in patients with stroke. J Clin Epidemiol. 2001; 54(11):1159-65. DOI: 10.1016/s0895-4356(01)00395-x. View

11.

Grams M, Sang Y, Ballew S, Gansevoort R, Kimm H, Kovesdy C . A Meta-analysis of the Association of Estimated GFR, Albuminuria, Age, Race, and Sex With Acute Kidney Injury. Am J Kidney Dis. 2015; 66(4):591-601. PMC: 4584180. DOI: 10.1053/j.ajkd.2015.02.337. View

12.

Holmes J, Roberts G, Meran S, Williams J, Phillips A . Understanding Electronic AKI Alerts: Characterization by Definitional Rules. Kidney Int Rep. 2017; 2(3):342-349. PMC: 5678680. DOI: 10.1016/j.ekir.2016.12.001. View

13.

Safari S, Hashemi B, Forouzanfar M, Shahhoseini M, Heidari M . Epidemiology and Outcome of Patients with Acute Kidney Injury in Emergency Department; a Cross-Sectional Study. Emerg (Tehran). 2018; 6(1):e30. PMC: 6036528. View

14.

Chen X, Wang Z, Pan X . HIV-1 tropism prediction by the XGboost and HMM methods. Sci Rep. 2019; 9(1):9997. PMC: 6620319. DOI: 10.1038/s41598-019-46420-4. View

15.

Pollard T, Johnson A, Raffa J, Celi L, Mark R, Badawi O . The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data. 2018; 5:180178. PMC: 6132188. DOI: 10.1038/sdata.2018.178. View

16.

Demirjian S, Chertow G, Zhang J, OConnor T, Vitale J, Paganini E . Model to predict mortality in critically ill adults with acute kidney injury. Clin J Am Soc Nephrol. 2011; 6(9):2114-20. PMC: 3359007. DOI: 10.2215/CJN.02900311. View

17.

Shipe M, Deppen S, Farjah F, Grogan E . Developing prediction models for clinical use using logistic regression: an overview. J Thorac Dis. 2019; 11(Suppl 4):S574-S584. PMC: 6465431. DOI: 10.21037/jtd.2019.01.25. View

18.

Lee H, Yoon S, Yang S, Kim W, Ryu H, Jung C . Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model. J Clin Med. 2018; 7(11). PMC: 6262324. DOI: 10.3390/jcm7110428. View

19.

Hsu C, Lin C . A comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw. 2008; 13(2):415-25. DOI: 10.1109/72.991427. View

20.

Hsu C, Liu C, Tain Y, Kuo C, Lin Y . Machine Learning Model for Risk Prediction of Community-Acquired Acute Kidney Injury Hospitalization From Electronic Health Records: Development and Validation Study. J Med Internet Res. 2020; 22(8):e16903. PMC: 7435690. DOI: 10.2196/16903. View