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 Dec 18;24(1):394.
doi: 10.1186/s12911-024-02807-6.

Early prediction of mortality upon intensive care unit admission

Yu-Chang Yeh #  1 , Yu-Ting Kuo  2 , Kuang-Cheng Kuo  2 , Yi-Wei Cheng  3 , Ding-Shan Liu  4 , Feipei Lai  5 , Lu-Cheng Kuo  6 , Tai-Ju Lee  6 , Wing-Sum Chan  7 , Ching-Tang Chiu  2 , Ming-Tao Tsai  6 , Anne Chao  2 , Nai-Kuan Chou  8 , Chong-Jen Yu  9 , Shih-Chi Ku #  10
Affiliations

Early prediction of mortality upon intensive care unit admission

Yu-Chang Yeh et al. BMC Med Inform Decis Mak. .

Abstract

Background: We aimed to develop and validate models for predicting intensive care unit (ICU) mortality of critically ill adult patients as early as upon ICU admission.

Methods: Combined data of 79,657 admissions from two teaching hospitals' ICU databases were used to train and validate the machine learning models to predict ICU mortality upon ICU admission and at 24 h after ICU admission by using logistic regression, gradient boosted trees (GBT), and deep learning algorithms.

Results: In the testing dataset for the admission models, the ICU mortality rate was 7%, and 38.4% of patients were discharged alive or dead within 1 day of ICU admission. The area under the receiver operating characteristic curve (0.856, 95% CI 0.845-0.867) and area under the precision-recall curve (0.331, 95% CI 0.323-0.339) were the highest for the admission GBT model. The ICU mortality rate was 17.4% in the 24-hour testing dataset, and the performance was the highest for the 24-hour GBT model.

Conclusion: The ADM models can provide crucial information on ICU mortality as early as upon ICU admission. 24 H models can be used to improve the prediction of ICU mortality for patients discharged more than 1 day after ICU admission.

Keywords: Critically ill; Intensive care; Mortality; Prediction.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: MIMIC-IV database usage was approved by the Institutional Review Boards of Massachusetts Institute of Technology (no. 0403000206) and Beth Israel Deaconess Medical Center (2001-P-001699/14). CORE database used in our study was approved by the Research Ethics Committee (REC) of the National Taiwan University Hospital (REC no. 202004016RINB). Because this study was a secondary analysis of fully anonymized data, individual patient consent was not required. All investigations were performed in accordance with the Declaration of Helsinki. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Flowchart of patient inclusion criteria and allocation to training and testing data sets. ADM admission, CORE Center of Outcome and Resource Evaluation critical care database, DL deep learning, GBT gradient boosting trees, ICU intensive care unit, LR logistic regression, MIMIC Medical Information Mart for Intensive Care database
Fig. 2
Fig. 2
Performance of the ADM and 24 H models in the testing data sets. Performance measures are presented as values with corresponding 95% confidence intervals. The cutoff value for sensitivity, precision, and specificity was 0.04 for all models. ADM admission, APS acute physiology score of the acute physiologic assessment and chronic health evaluation (APACHE) III, AUPRC area under the precision-recall curve, AUROC area under the receiver operating characteristic curve, DL deep learning, GBT gradient boosting trees, LR logistic regression, SOFA sequential organ failure assessment
Fig. 3
Fig. 3
Calibration plots of the ADM models. ADM admission, DL deep learning, GBT gradient boosting trees, LR logistic regression
Fig. 4
Fig. 4
Feature importance of gradient boosting trees models. ADM admission, bmi body mass index, BUN blood urine nitrogen, cad coronary artery diseases, chf congestive heart failure, DBP diastolic blood pressure, ED emergency department, ESRD end stage renal disease, GBT gradient boosting trees, gcs Glasgow coma scale, hr heart rate, ICU intensive care unit, inv invasive ventilation, LOS length of stay, MAP mean arterial pressure, ph power of hydrogen, plat platelet, rr respiratory rate, SBP systolic blood pressure, wcc white cell counts
See this image and copyright information in PMC

References

    1. Cardona M, Dobler CC, Koreshe E, et al. A catalogue of tools and variables from crisis and routine care to support decision-making about allocation of intensive care beds and ventilator treatment during pandemics: scoping review. J Crit Care. 2021;66:33–43. - PubMed
    1. Shillan D, Sterne JAC, Champneys A, Gibbison B. Use of machine learning to analyse routinely collected intensive care unit data: a systematic review. Crit Care. 2019;23:284. - PMC - PubMed
    1. Escher M, Ricou B, Nendaz M, et al. Icu physicians’ and internists’ survival predictions for patients evaluated for admission to the intensive care unit. Ann Intensive Care. 2018;8:108. - PMC - PubMed
    1. Lim SC, Fok AC, Ong YY. Patient outcome and intensive care resource allocation using apache ii. Singap Med J. 1996;37:488–91. - PubMed
    1. Paxton C, Niculescu-Mizil A, Saria S. Developing predictive models using electronic medical records: challenges and pitfalls. AMIA Annu Symp Proc. 2013;1109–15. - PMC - PubMed

LinkOut - more resources