Stratification of hospitalized COVID-19 patients into clinical severity progression groups by immuno-phenotyping and machine learning

  1. Yvonne M. Mueller
  2. Thijs J. Schrama
  3. Rik Ruijten
  4. Marco W. J. Schreurs
  5. Dwin G. B. Grashof
  6. Harmen J. G. van de Werken
  7. Giovanna Jona Lasinio
  8. Daniel Álvarez-Sierra
  9. Caoimhe H. Kiernan
  10. Melisa D. Castro Eiro
  11. Marjan van Meurs
  12. Inge Brouwers-Haspels
  13. Manzhi Zhao
  14. Ling Li
  15. Harm de Wit
  16. Christos A. Ouzounis
  17. Merel E. P. Wilmsen
  18. Tessa M. Alofs
  19. Danique A. Laport
  20. Tamara van Wees
  21. Geoffrey Kraker
  22. Maria C. Jaimes
  23. Sebastiaan Van Bockstael
  24. Manuel Hernández-González
  25. Casper Rokx
  26. Bart J. A. Rijnders
  27. Ricardo Pujol-Borrell
  28. Peter D. Katsikis

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Quantitative or qualitative differences in immunity may drive clinical severity in COVID-19. Although longitudinal studies to record the course of immunological changes are ample, they do not necessarily predict clinical progression at the time of hospital admission. Here we show, by a machine learning approach using serum pro-inflammatory, anti-inflammatory and anti-viral cytokine and anti-SARS-CoV-2 antibody measurements as input data, that COVID-19 patients cluster into three distinct immune phenotype groups. These immune-types, determined by unsupervised hierarchical clustering that is agnostic to severity, predict clinical course. The identified immune-types do not associate with disease duration at hospital admittance, but rather reflect variations in the nature and kinetics of individual patient’s immune response. Thus, our work provides an immune-type based scheme to stratify COVID-19 patients at hospital admittance into high and low risk clinical categories with distinct cytokine and antibody profiles that may guide personalized therapy.

Article activity feed

  1. Version published to 10.1038/s41467-022-28621-0
  2. ScreenIT

    SciScore for 10.1101/2021.05.07.21256531: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    EthicsIRB: The study was reviewed and approved by the institutional review board of the Erasmus University Medical Center.
    Consent: Written informed consent was obtained from every patient or legal representative.
    IACUC: Barcelona cohort samples and data from patients included in this study were provided by the HUVH Biobank (PT17/0015/0047), integrated in the Spanish National Biobanks Network and they were processed following standard operating procedures with the appropriate approval of the Ethics and Scientific Committees.
    Sex as a biological variablenot detected.
    RandomizationPatients: Rotterdam cohort samples were collected from patients (n=50) participating in the ConCOVID nationwide multicenter open-label randomized clinical trial in the Netherlands.
    Blindingnot detected.
    Power Analysisnot detected.

    Table 2: Resources

    Antibodies
    SentencesResources
    Anti-SARS-CoV-2 antibody measurements: Anti-SARS-CoV-2 IgM, IgG and IgA antibodies against nucleocapsid protein (N-protein) were measured in serum by ELISA using COVID-19 IgG ELISA (Tecan, 30177447), COVID-19 IgA ELISA (Tecan, 30177446) and COVID-19 IgM ELISA (Tecan, 30177448) according to the manufacturer’s instructions.
    Anti-SARS-CoV-2
    suggested: None
    IgA antibodies against nucleocapsid protein (N-protein
    suggested: None
    COVID-19 IgG
    suggested: None
    COVID-19 IgA ELISA (Tecan, 30177446
    suggested: None
    COVID-19 IgM ELISA (Tecan, 30177448
    suggested: None
    Network analysis: Network analysis was performed between immunotypes and select pro-inflammatory cytokines (IL-6, TNFα, IL-8, CCL2) interferons (IFNγ and IFNα) and anti-SARS-CoV-2 IgM, IgG and IgA antibodies.
    IL-6, TNFα
    suggested: None
    IL-8
    suggested: None
    CCL2
    suggested: None
    IFNα
    suggested: (Leinco Technologies Cat# T701, RRID:AB_2832118)
    anti-SARS-CoV-2 IgM, IgG
    suggested: None
    IgA
    suggested: None
    Software and Algorithms
    SentencesResources
    The workflow included running flowCut to check for changes in channels over acquisition time, UMAP for dimensionality reduction, flowSOM for clustering, and edgeR for statistical inference.
    edgeR
    suggested: (edgeR, RRID:SCR_012802)
    The optimal number of clusters for both cohorts was assigned with the NbClust (v1.0.12) package in R (44).
    NbClust
    suggested: None
    Subsequently, heatmaps were plotted using the R package pheatmap (v1.0.12).
    pheatmap
    suggested: (pheatmap, RRID:SCR_016418)

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    Results from scite Reference Check: We found no unreliable references.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  3. Version published to 10.1101/2021.05.07.21256531v1 on medRxiv