Clinical Decision Support Tool and Rapid Point-of-Care Platform for Determining Disease Severity in Patients with COVID-19

  1. Michael P. McRae
  2. Glennon W. Simmons
  3. Nicolaos J. Christodoulides
  4. Zhibing Lu
  5. Stella K. Kang
  6. David Fenyo
  7. Timothy Alcorn
  8. Isaac P. Dapkins
  9. Iman Sharif
  10. Deniz Vurmaz
  11. Sayli S. Modak
  12. Kritika Srinivasan
  13. Shruti Warhadpande
  14. Ravi Shrivastav
  15. John T. McDevitt

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

SARS-CoV-2 is the virus that causes coronavirus disease (COVID-19) which has reached pandemic levels resulting in significant morbidity and mortality affecting every inhabited continent. The large number of patients requiring intensive care threatens to overwhelm healthcare systems globally. Likewise, there is a compelling need for a COVID-19 disease severity test to prioritize care and resources for patients at elevated risk of mortality. Here, an integrated point-of-care COVID-19 Severity Score and clinical decision support system is presented using biomarker measurements of C-reactive protein (CRP), N-terminus pro B type natriuretic peptide (NT-proBNP), myoglobin (MYO), D-dimer, procalcitonin (PCT), creatine kinase–myocardial band (CK-MB), and cardiac troponin I (cTnI). The COVID-19 Severity Score combines multiplex biomarker measurements and risk factors in a statistical learning algorithm to predict mortality. The COVID-19 Severity Score was trained and evaluated using data from 160 hospitalized COVID-19 patients from Wuhan, China. Our analysis finds that COVID-19 Severity Scores were significantly higher for the group that died versus the group that was discharged with median (interquartile range) scores of 59 (40–83) and 9 (6–17), respectively, and area under the curve of 0.94 (95% CI 0.89– 0.99). These promising initial models pave the way for a point-of-care COVID-19 Severity Score system to impact patient care after further validation with externally collected clinical data. Clinical decision support tools for COVID-19 have strong potential to empower healthcare providers to save lives by prioritizing critical care in patients at high risk for adverse outcomes.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.04.16.20068411: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Antibodies
    SentencesResources
    CK-MB, CRP and Goat anti Mouse IgG (H + L) (R-PE) specific antibodies and standards and were acquired from Fitzgerald Industries International (Acton, Massachusetts).
    CK-MB , CRP
    suggested: None
    Mouse monoclonal anti-human antibodies for cTnI, (clone M18 and 560), CK-MB, MYO (clone 7C3),
    anti-human antibodies for cTnI ,
    suggested: None
    NT-proBNP (clone 15C4), CRP, and goat anti mouse IgG (H + L) (R-PE) antibodies were conjugated to beads sensors for target capture.
    anti mouse IgG
    suggested: None
    R-PE
    suggested: None
    , NT-proBNP (clone 13G12), and CRP antibodies using Alexa Fluor 488 protein labeling kit (Invitrogen, Eugene, Oregon) for target detection using manufacturer specified protocols.
    NT-proBNP
    suggested: None
    CRP
    suggested: None
    Software and Algorithms
    SentencesResources
    Control software and user interface was developed in MATLAB® 2014a (Natick, MA).
    MATLAB®
    suggested: (MATLAB, RRID:SCR_001622)
    Image analysis: Images were analyzed using a custom image analysis tool developed with MATLAB as described previously.
    MATLAB
    suggested: (MATLAB, RRID:SCR_001622)

    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: We detected the following sentences addressing limitations in the study:
    One limitation of this study was that all patients in the training dataset had hypertension and are, thus, at an elevated risk for cardiovascular events. Since the test panel contains several cardiac biomarkers, it’s possible that these training data could lead to overoptimistic results. However, in addition to cardiac biomarkers, the expanded biomarker panel represents diverse pathophysiology (i.e., indicators of infection, inflammation, mortality, thrombotic events, and rhabdomyolysis) which have the potential to significantly improve generalizability. Plans to evaluate and optimize the COVID-19 Severity Score model on external data are in place. Despite this limitation, the preliminary results demonstrate strong promise for the COVID-19 Severity Score. Reporting these preliminary findings now is critically important given the stage of the pandemic. Previously we have used the p-BNC platform to develop various wellness and disease severity scores for oral cancer18, 19, 32 and cardiac heart disease.22 Shown in Figure 5 is the initial rough scale for the COVID-19 Severity Score which was based on the CDC’s Interim Clinical Guidance for Management of Patients with Confirmed COVID-19.33 The continuous scale COVID-19 Severity Score has the potential to assist the identification of patients with severe/critical disease status. For example, most patients (∼80%) with a low COVID-19 Severity Score may be considered at Mild/Moderate risk for developing complications up to mild pneumo...

    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.

    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.

  2. Version published to 10.1101/2020.04.16.20068411 on medRxiv
  3. Version published to 10.1039/d0lc00373e