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
. 2021 Aug 31;11(9):1582.
doi: 10.3390/diagnostics11091582.

Mortality Prediction Utilizing Blood Biomarkers to Predict the Severity of COVID-19 Using Machine Learning Technique

Tawsifur Rahman  1 , Fajer A Al-Ishaq  2 , Fatima S Al-Mohannadi  2 , Reem S Mubarak  2 , Maryam H Al-Hitmi  2 , Khandaker Reajul Islam  1 , Amith Khandakar  1 , Ali Ait Hssain  3 , Somaya Al-Madeed  4 , Susu M Zughaier  2 , Muhammad E H Chowdhury  1
Affiliations

Mortality Prediction Utilizing Blood Biomarkers to Predict the Severity of COVID-19 Using Machine Learning Technique

Tawsifur Rahman et al. Diagnostics (Basel). .

Abstract

Healthcare researchers have been working on mortality prediction for COVID-19 patients with differing levels of severity. A rapid and reliable clinical evaluation of disease intensity will assist in the allocation and prioritization of mortality mitigation resources. The novelty of the work proposed in this paper is an early prediction model of high mortality risk for both COVID-19 and non-COVID-19 patients, which provides state-of-the-art performance, in an external validation cohort from a different population. Retrospective research was performed on two separate hospital datasets from two different countries for model development and validation. In the first dataset, COVID-19 and non-COVID-19 patients were admitted to the emergency department in Boston (24 March 2020 to 30 April 2020), and in the second dataset, 375 COVID-19 patients were admitted to Tongji Hospital in China (10 January 2020 to 18 February 2020). The key parameters to predict the risk of mortality for COVID-19 and non-COVID-19 patients were identified and a nomogram-based scoring technique was developed using the top-ranked five parameters. Age, Lymphocyte count, D-dimer, CRP, and Creatinine (ALDCC), information acquired at hospital admission, were identified by the logistic regression model as the primary predictors of hospital death. For the development cohort, and internal and external validation cohorts, the area under the curves (AUCs) were 0.987, 0.999, and 0.992, respectively. All the patients are categorized into three groups using ALDCC score and death probability: Low (probability < 5%), Moderate (5% < probability < 50%), and High (probability > 50%) risk groups. The prognostic model, nomogram, and ALDCC score will be able to assist in the early identification of both COVID-19 and non-COVID-19 patients with high mortality risk, helping physicians to improve patient management.

Keywords: COVID-19; D-dimer; biomarkers; coagulopathy; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Methodology of the study.
Figure 2
Figure 2
Outcome tree for the patients of Dataset-1 and Dataset-2.
Figure 3
Figure 3
Comparison of the receive operating characteristic (ROC) plots for (A) individual feature (Imputation-Mice, Classifier-Logistic regression), (B) top-ranked 1 up to 10 features (Imputation-Mice, Classifier-Logistic regression).
Figure 4
Figure 4
Internal Validation Curve (A,B) and the External validation (C).
Figure 5
Figure 5
Developed Nomogram.
Figure 6
Figure 6
ALDCC score from nomogram and corresponding death probability of COVID-19 and non-COVID-19 patients where ALDCC score ≤ 16.6 and death probability ≤ 5% are shown for low risk group and ALDCC score > 19.8 and death probability > 50% are shown for high risk group.
Figure 7
Figure 7
Prediction of internal and external validation with Dataset-1 and Dataset-2 using ALDCC score.
Figure 8
Figure 8
An example of nomogram-based ALDCC score to predict the probability of death of a patient from the test set (3 weeks before the actual outcome).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Vaidyanathan G. Coronavirus variants are spreading in India—What scientists know so far. Nature. 2021;593:321–322. doi: 10.1038/d41586-021-01274-7. - DOI - PubMed
    1. Black M., Lee A., Ford J. Vaccination against COVID-19 and inequalities–avoiding making a bad situation worse. Public Health Pract. 2021;2:100101. doi: 10.1016/j.puhip.2021.100101. - DOI - PMC - PubMed
    1. Kluge H., McKee M. COVID-19 vaccines for the European region: An unprecedented challenge. Lancet. 2021;397:1689–1691. doi: 10.1016/S0140-6736(21)00709-1. - DOI - PMC - PubMed
    1. COVID-19 Coronavirus Pandemic. [(accessed on 19 April 2020)]. Available online: https://www.worldometers.info/coronavirus/
    1. Huang D., Wang T., Chen Z., Yang H., Yao R., Liang Z. A novel risk score to predict diagnosis with coronavirus disease 2019 (COVID-19) in suspected patients: A retrospective, multicenter, and observational study. J. Med. Virol. 2020;92:2709–2717. doi: 10.1002/jmv.26143. - DOI - PMC - PubMed