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
. 2022 Mar 18;20(1):136.
doi: 10.1186/s12967-022-03340-8.

A machine learning-based risk stratification tool for in-hospital mortality of intensive care unit patients with heart failure

Cida Luo  1   2 , Yi Zhu  3 , Zhou Zhu  1   2 , Ranxi Li  1   2 , Guoqin Chen  4 , Zhang Wang  5   6
Affiliations

A machine learning-based risk stratification tool for in-hospital mortality of intensive care unit patients with heart failure

Cida Luo et al. J Transl Med. .

Abstract

Background: Predicting hospital mortality risk is essential for the care of heart failure patients, especially for those in intensive care units.

Methods: Using a novel machine learning algorithm, we constructed a risk stratification tool that correlated patients' clinical features and in-hospital mortality. We used the extreme gradient boosting algorithm to generate a model predicting the mortality risk of heart failure patients in the intensive care unit in the derivation dataset of 5676 patients from the Medical Information Mart for Intensive Care III database. The logistic regression model and a common risk score for mortality were used for comparison. The eICU Collaborative Research Database dataset was used for external validation.

Results: The performance of the machine learning model was superior to that of conventional risk predictive methods, with the area under curve 0.831 (95% CI 0.820-0.843) and acceptable calibration. In external validation, the model had an area under the curve of 0.809 (95% CI 0.805-0.814). Risk stratification through the model was specific when the hospital mortality was very low, low, moderate, high, and very high (2.0%, 10.2%, 11.5%, 21.2% and 56.2%, respectively). The decision curve analysis verified that the machine learning model is the best clinically valuable in predicting mortality risk.

Conclusion: Using readily available clinical data in the intensive care unit, we built a machine learning-based mortality risk tool with prediction accuracy superior to that of linear regression model and common risk scores. The risk tool may support clinicians in assessing individual patients and making individualized treatment.

Keywords: Extreme gradient boosting; Heart failure; Machine learning models; Medical information mart for intensive care; Risk stratification.

PubMed Disclaimer

Conflict of interest statement

The authors declare that have no competing interests.

Figures

Fig. 1
Fig. 1
Feature importance derived from the XGBoost model
Fig. 2
Fig. 2
The receiver operating characteristic curves of the XGBoost model, elastic net model, SAPS-II score, and GWTG-HF score
Fig. 3
Fig. 3
Calibration plot for the XGBoost model. The model had good calibration with in-hospital mortality risk
Fig. 4
Fig. 4
Decision curve analysis of models. The X axis indicates the threshold probability for in-hospital mortality, and the Y axis indicates the net benefit
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Gianluigi S, Lund LH. global public health burden of heart failure. Card Fail Rev. 2017;3. 10.15420/cfr.2016:25:2. - PMC - PubMed
    1. Seferović PM. ESC/HFA guidelines for the diagnosis and treatment of acute and chronic heart failure 2016. J Card Fail. 2017 doi: 10.1016/j.cardfail.2017.08.005. - DOI
    1. Komanduri S, Jadhao Y, Guduru SS, Cheriyath P, Wert Y. Prevalence and risk factors of heart failure in the USA: NHANES 2013–2014 epidemiological follow-up study. J Commun Hosp Intern Med Perspect. 2017;7(1):15–20. doi: 10.1080/20009666.2016.1264696. - DOI - PMC - PubMed
    1. Amina G, Amer I, Admir R, Ira T, Selma J, Anes A, Adis K. Predictive value of SAPS II and APACHE II scoring systems for patient outcome in a medical intensive care unit. Acta Med Acad. 2016;45(2):97–103. - PubMed
    1. Izabela K, Rafał Ś, Karolina B, Paweł T, Wojciech S. Validation of APACHE II and SAPS II scales at the intensive care unit along with assessment of SOFA scale at the admission as an isolated risk of death predictor. Anaesthesiol Intensive Therapy. 2019;51(2):107–11. doi: 10.5114/ait.2019.86275. - DOI - PubMed