Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep 6:16:2625-2640.
doi: 10.2147/JMDH.S416943. eCollection 2023.

A Retrospective Cohort Study: Predicting 90-Day Mortality for ICU Trauma Patients with a Machine Learning Algorithm Using XGBoost Using MIMIC-III Database

Affiliations

A Retrospective Cohort Study: Predicting 90-Day Mortality for ICU Trauma Patients with a Machine Learning Algorithm Using XGBoost Using MIMIC-III Database

Shan Yang et al. J Multidiscip Healthc. .

Abstract

Objective: The aim of this study was to develop and validate a machine learning-based predictive model that predicts 90-day mortality in ICU trauma patients.

Methods: Data of patients with severe trauma were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The performances of mortality prediction models generated using nine machine learning extreme gradient boosting (XGBoost), logistic regression, random forest, AdaBoost, multilayer perceptron (MLP) neural networks, support vector machine (SVM), light gradient boosting machine (GBM), k nearest neighbors (KNN) and gaussian naive bayes (GNB). The performance of the model was evaluated in terms of discrimination, calibration and clinical application.

Results: We found that the accuracy, sensitivity, specificity, PPV, NPV and F1 score of our proposed XGBoost model were 82.8%, 79.7%, 77.6%, 51.2%, 91.5% and 0.624, respectively. Among the nine models, the XGBoost model performed best. Compared with traditional logistic regression, the calibration curves of the XGBoost model and decision curve analysis (DCA) performed well.

Conclusion: Our study shows that the XGBoost model outperforms other machine learning models in predicting 90-day mortality in trauma patients. It can be used to assist clinicians in the early identification of mortality risk factors and early intervention to reduce mortality.

Keywords: MIMIC-III; XGBoost; intensive care unit; mortality; prediction model; severe trauma patient.

PubMed Disclaimer

Conflict of interest statement

All authors have no competing interests in this work.

Figures

Figure 1
Figure 1
The flow chart of data extraction.
Figure 2
Figure 2
Receiver operating characteristic curves (ROCs) of the XGBoost, logistic regression, random forest, AdaBoost, MLP, GNB, SVM, KNN and LightGBM models. (a) Training sets. (b) Validation sets.
Figure 3
Figure 3
(a) Calibration plots and (b) decision curve analysis (DCA) of the XGBoost model and conventional logistic regression prediction models. The XGBoost calibration curves performed well, and the XGBoost model had a greater net benefit in DCA than the logistic regression model.
Figure 4
Figure 4
Model evaluation and validation in the training and validation sets. Receiver operating characteristic curves (ROCs) of XGBoost. (a) Training sets. (b) Test sets. (c) Learning curve.
Figure 5
Figure 5
Feature importance estimated using the Shapley Additive explanations (SHAP) values. The plot sorts features by the sum of SHAP value magnitudes over all samples. The color represents the feature value (red high, blue low). The x-axis measures the impact on the model output (right positive, left negative). Taking the feature SAPS II as an example, red points are on the right, whereas blue points are on the left. This means prediction scores will be smaller when patients have a lower SAPS II score.
Figure 6
Figure 6
The predicted results for three specific instances. The red and blue bars represent risk factors and protective factors, respectively. Longer lines indicate that the eigenvalues are more important. This figure shows the explanation for a low-risk instance (a), a medium-risk instance (b) and a high-risk instance (c).

Similar articles

Cited by

References

    1. Collaborators GBDCo D. Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet. 2018;392(10159):1736–1788. - PMC - PubMed
    1. Rhee P, Joseph B, Pandit V, et al. Increasing trauma deaths in the United States. Ann Surg. 2014;260(1):13–21. doi:10.1097/SLA.0000000000000600 - DOI - PubMed
    1. Azami-Aghdash S, Sadeghi-Bazargani H, Shabaninejad H, Abolghasem Gorji H. Injury epidemiology in Iran: a systematic review. J Inj Violence Res. 2017;9(1):27–40. doi:10.5249/jivr.v9i1.852 - DOI - PMC - PubMed
    1. Yousefzadeh Chabok S, Ranjbar Taklimie F, Malekpouri R, Razzaghi A. Predicting mortality, hospital length of stay and need for surgery in pediatric trauma patients. Chin J Traumatol. 2017;20(6):339–342. doi:10.1016/j.cjtee.2017.04.011 - DOI - PMC - PubMed
    1. Butcher N, Balogh ZJ. The definition of polytrauma: the need for international consensus. Injury. 2009;40 Suppl 4:S12–22. doi:10.1016/j.injury.2009.10.032 - DOI - PubMed