COVID-HEART: Development and Validation of a Multi-Variable Model for Real-Time Prediction of Cardiovascular Complications in Hospitalized Patients with COVID-19

This article has been Reviewed by the following groups

Read the full article See related articles

Abstract

Cardiovascular (CV) manifestations of COVID-19 infection carry significant morbidity and mortality. Current risk prediction for CV complications in COVID-19 is limited and existing approaches fail to account for the dynamic course of the disease. Here, we develop and validate the COVID-HEART predictor, a novel continuously-updating risk prediction technology to forecast CV complications in hospitalized patients with COVID-19. The risk predictor is trained and tested with retrospective registry data from 2178 patients to predict two outcomes: cardiac arrest and imaging-confirmed thromboembolic events. In repeating model validation many times, we show that it predicts cardiac arrest with an average median early warning time of 18 hours (IQR: 13-20 hours) and an AUROC of 0.92 (95% CI: 0.91-0.92), and thromboembolic events with a median early warning time of 72 hours (IQR: 12-204 hours) and an AUROC of 0.70 (95% CI: 0.67-0.73). The COVID-HEART predictor is anticipated to provide tangible clinical decision support in triaging patients and optimizing resource utilization, with its clinical utility potentially extending well beyond COVID-19.

Article activity feed

  1. SciScore for 10.1101/2021.01.03.21249182: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    RandomizationPatients were randomly assigned to development (80%) and testing (20%) data sets with stratification to ensure there were approximately the same proportion of patients with and without adverse CV events in each set.
    BlindingSince this was a retrospective study and did not include any data collected prospectively, there was no need of blind assessment of predictors for patients in the testing set.
    Power Analysisnot detected.
    Sex as a biological variableGender was defined as the patient’s legal gender (Male or Female) as listed in the electronic health record (EHR).

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    All pre-processing steps were performed using the Python Pandas data analysis library.
    Python
    suggested: (IPython, RRID:SCR_001658)

    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.

    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.