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
. 2024 Sep 9;24(1):249.
doi: 10.1186/s12911-024-02655-4.

Machine learning-based prognostic model for 30-day mortality prediction in Sepsis-3

Md Sohanur Rahman  1 , Khandaker Reajul Islam  2 , Johayra Prithula  1 , Jaya Kumar  3 , Mufti Mahmud  4 , Mohammed Fasihul Alam  5 , Mamun Bin Ibne Reaz  6 , Abdulrahman Alqahtani  7   8 , Muhammad E H Chowdhury  9
Affiliations

Machine learning-based prognostic model for 30-day mortality prediction in Sepsis-3

Md Sohanur Rahman et al. BMC Med Inform Decis Mak. .

Erratum in

Abstract

Background: Sepsis poses a critical threat to hospitalized patients, particularly those in the Intensive Care Unit (ICU). Rapid identification of Sepsis is crucial for improving survival rates. Machine learning techniques offer advantages over traditional methods for predicting outcomes. This study aimed to develop a prognostic model using a Stacking-based Meta-Classifier to predict 30-day mortality risks in Sepsis-3 patients from the MIMIC-III database.

Methods: A cohort of 4,240 Sepsis-3 patients was analyzed, with 783 experiencing 30-day mortality and 3,457 surviving. Fifteen biomarkers were selected using feature ranking methods, including Extreme Gradient Boosting (XGBoost), Random Forest, and Extra Tree, and the Logistic Regression (LR) model was used to assess their individual predictability with a fivefold cross-validation approach for the validation of the prediction. The dataset was balanced using the SMOTE-TOMEK LINK technique, and a stacking-based meta-classifier was used for 30-day mortality prediction. The SHapley Additive explanations analysis was performed to explain the model's prediction.

Results: Using the LR classifier, the model achieved an area under the curve or AUC score of 0.99. A nomogram provided clinical insights into the biomarkers' significance. The stacked meta-learner, LR classifier exhibited the best performance with 95.52% accuracy, 95.79% precision, 95.52% recall, 93.65% specificity, and a 95.60% F1-score.

Conclusions: In conjunction with the nomogram, the proposed stacking classifier model effectively predicted 30-day mortality in Sepsis patients. This approach holds promise for early intervention and improved outcomes in treating Sepsis cases.

Keywords: 30-day mortality prediction; Machine learning; Prognostic model; Sepsis; Stacking-based meta-classifier.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Step-by-step overview of the methodology for 30-Day Mortality Prediction in Sepsis-3
Fig. 2
Fig. 2
Bar plots presenting Feature Ranking using XGBoost, RF, and ET techniques
Fig. 3
Fig. 3
Comparison of receiver operating characteristics (ROC) curves for different classical machine learning models (a) and stacking machine learning models (b)
Fig. 4
Fig. 4
Confusion matrix showing the classification outcomes for predicting patient survival and death
Fig. 5
Fig. 5
SHAP analysis plot detailing the impact of each biomarker in classification outcome for the base models and stacked model
Fig. 6
Fig. 6
Calibration curve illustrating classification for survival and death class
Fig. 7
Fig. 7
Decision curves analysis showing comparison among different biomarkers to predict the death probability of patients with Sepsis
Fig. 8
Fig. 8
A nomogram utilizing multivariate LR model is employed to estimate the probable outcome for deceased persons developed to estimate mortality using a set of eight biomarkers
See this image and copyright information in PMC

References

    1. C. Fleischmann et al., "Assessment of Global Incidence and Mortality of Hospital-treated Sepsis. Current Estimates and Limitations," American Journal of Respiratory and Critical Care Medicine, 2016. [Online]. Available: https://www.atsjournals.org/doi/full/10.1164/rccm.201504-0781OC. - PubMed
    1. Liu V, Escobar GJ, Greene JD, Soule J, Whippy A, Angus DC, Iwashyna TJ. “Hospital deaths in patients with sepsis from 2 independent cohorts,” (in English). JAMA. 2014;312(1):90–2. 10.1001/jama.2014.5804. - PubMed
    1. Singer M, et al. “The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3),” (in English). JAMA. 2016;315(8):801. 10.1001/jama.2016.0287. - PMC - PubMed
    1. Sinha RK, et al. “Thrombosis and Hemostasis: PAR1 biased signaling is required for activated protein C in vivo benefits in sepsis and stroke,” (in English). Blood. 2018;131(11):1163. 10.1182/blood-2017-10-810895. - PMC - PubMed
    1. Kell DB, Pretorius E. “Editorial Compilation V: To What Extent Are the Terminal Stages of Sepsis, Septic Shock, Systemic Inflammatory Response Syndrome, and Multiple Organ Dysfunction Syndrome Actually Driven by a Prion/Amyloid Form of Fibrin?,” (in English). Semin Thromb Hemost. 2018;44(3):224. 10.1055/s-0037-1604108. - PMC - PubMed

LinkOut - more resources