Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score

Abstract

An early-warning model to predict in-hospital mortality on admission of COVID-19 patients at an emergency department (ED) was developed and validate using a Machine-Learning model. In total, 2782 patients were enrolled between March 2020 and December 2020, including 2106 patients (first wave) and 676 patients (second wave) in the COVID-19 outbreak in Italy. The first-wave patients were divided into two groups with 1474 patients used to train the model, and 632 to validate it. The 676 patients in the second wave were used to test the model. Age, 17 blood analytes and Brescia chest X-ray score were the variables processed using a Random Forests classification algorithm to build and validate the model. ROC analysis was used to assess the model performances. A web-based death-risk calculator was implemented and integrated within the Laboratory Information System of the hospital. The final score was constructed by age (the most powerful predictor), blood analytes (the strongest predictors were lactate dehydrogenase, D-dimer, Neutrophil/Lymphocyte ratio, C-reactive protein, Lymphocyte %, Ferritin std and Monocyte %), and Brescia chest X-ray score. The areas under the receiver operating characteristic curve obtained for the three groups (training, validating and testing) were 0.98, 0.83 and 0.78, respectively. The model predicts in-hospital mortality on the basis of data that can be obtained in a short time, directly at the ED on admission. It functions as a web-based calculator, providing a risk score which is easy to interpret. It can be used in the triage process to support the decision on patient allocation.

Data availability

We are unable to share the dataset as it contains sensitive personal data collected during the pandemic at Spedali Civili di Brescia. We cannot share the full data since are data from patients. Interested researchers should contact the authors for any query related to data sharing and submit a project proposal Once defined the goal of the study, and the data needed authors will submit the potential project of collaboration to the IRB of Spedali Civili di Brescia to receive approval to access a deidentified dataset. Please note that other informations related to patients can be acquired, always following approoval of IRB of Spedali Civili di Brescia, not only the ones studied in the paper.Anyway, following request to the authors, it will be possible to share processed version of the dataset ( e.g. an Excel sheet with numbers used to plot the graphs and charts of the manuscript).All code used to analyse the data can be found on GitHub at https://github.com/biostatUniBS/BS_EWS

Article and author information

Author details

  1. Emirena Garrafa

    University of Brescia, Brescia, Italy
    For correspondence
    emirena.garrafa@unibs.it
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-4761-6892
  2. Marika Vezzoli

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.
  3. Marco Ravanelli

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.
  4. Davide Farina

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.
  5. Andrea Borghesi

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.
  6. Stefano Calza

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.
  7. Roberto Maroldi

    University of Brescia, Brescia, Italy
    Competing interests
    The authors declare that no competing interests exist.

Funding

Stefano Calza (PRIN 20178S4EK9)

  • Stefano Calza

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Reviewing Editor

  1. Evangelos J Giamarellos-Bourboulis, National and Kapodistrian University of Athens, Medical School, Greece

Ethics

Human subjects: The Institutional review board aprpoved the study with the entry code NP4000.

Version history

  1. Received: May 24, 2021
  2. Preprint posted: June 13, 2021 (view preprint)
  3. Accepted: October 17, 2021
  4. Accepted Manuscript published: October 18, 2021 (version 1)
  5. Accepted Manuscript updated: October 22, 2021 (version 2)
  6. Version of Record published: October 27, 2021 (version 3)

Copyright

© 2021, Garrafa et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 977
    Page views
  • 129
    Downloads
  • 20
    Citations

Article citation count generated by polling the highest count across the following sources: Crossref, PubMed Central, Scopus.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Emirena Garrafa
  2. Marika Vezzoli
  3. Marco Ravanelli
  4. Davide Farina
  5. Andrea Borghesi
  6. Stefano Calza
  7. Roberto Maroldi
(2021)
Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score
eLife 10:e70640.
https://doi.org/10.7554/eLife.70640

Share this article

https://doi.org/10.7554/eLife.70640

Further reading

    1. Biochemistry and Chemical Biology
    2. Structural Biology and Molecular Biophysics
    Karolina Honzejkova, Dalibor Kosek ... Tomas Obsil
    Research Article

    Apoptosis signal-regulating kinase 1 (ASK1) is a crucial stress sensor, directing cells toward apoptosis, differentiation, and senescence via the p38 and JNK signaling pathways. ASK1 dysregulation has been associated with cancer and inflammatory, cardiovascular, and neurodegenerative diseases, among others. However, our limited knowledge of the underlying structural mechanism of ASK1 regulation hampers our ability to target this member of the MAP3K protein family towards developing therapeutic interventions for these disorders. Nevertheless, as a multidomain Ser/Thr protein kinase, ASK1 is regulated by a complex mechanism involving dimerization and interactions with several other proteins, including thioredoxin 1 (TRX1). Thus, the present study aims at structurally characterizing ASK1 and its complex with TRX1 using several biophysical techniques. As shown by cryo-EM analysis, in a state close to its active form, ASK1 is a compact and asymmetric dimer, which enables extensive interdomain and interchain interactions. These interactions stabilize the active conformation of the ASK1 kinase domain. In turn, TRX1 functions as a negative allosteric effector of ASK1, modifying the structure of the TRX1-binding domain and changing its interaction with the tetratricopeptide repeats domain. Consequently, TRX1 reduces access to the activation segment of the kinase domain. Overall, our findings not only clarify the role of ASK1 dimerization and inter-domain contacts but also provide key mechanistic insights into its regulation, thereby highlighting the potential of ASK1 protein-protein interactions as targets for anti-inflammatory therapy.

    1. Biochemistry and Chemical Biology
    Jake W Anderson, David Vaisar ... Natalie G Ahn
    Research Article

    Activation of the extracellular signal-regulated kinase-2 (ERK2) by phosphorylation has been shown to involve changes in protein dynamics, as determined by hydrogen-deuterium exchange mass spectrometry (HDX-MS) and NMR relaxation dispersion measurements. These can be described by a global exchange between two conformational states of the active kinase, named ‘L’ and ‘R,’ where R is associated with a catalytically productive ATP-binding mode. An ATP-competitive ERK1/2 inhibitor, Vertex-11e, has properties of conformation selection for the R-state, revealing movements of the activation loop that are allosterically coupled to the kinase active site. However, the features of inhibitors important for R-state selection are unknown. Here, we survey a panel of ATP-competitive ERK inhibitors using HDX-MS and NMR and identify 14 new molecules with properties of R-state selection. They reveal effects propagated to distal regions in the P+1 and helix αF segments surrounding the activation loop, as well as helix αL16. Crystal structures of inhibitor complexes with ERK2 reveal systematic shifts in the Gly loop and helix αC, mediated by a Tyr-Tyr ring stacking interaction and the conserved Lys-Glu salt bridge. The findings suggest a model for the R-state involving small movements in the N-lobe that promote compactness within the kinase active site and alter mobility surrounding the activation loop. Such properties of conformation selection might be exploited to modulate the protein docking interface used by ERK substrates and effectors.