Using patient biomarker time series to determine mortality risk in hospitalised COVID-19 patients: A comparative analysis across two New York hospitals

  1. Ben Lambert
  2. Isaac J. Stopard
  3. Amir Momeni-Boroujeni
  4. Rachelle Mendoza
  5. Alejandro Zuretti

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

A large range of prognostic models for determining the risk of COVID-19 patient mortality exist, but these typically restrict the set of biomarkers considered to measurements available at patient admission. Additionally, many of these models are trained and tested on patient cohorts from a single hospital, raising questions about the generalisability of results. We used a Bayesian Markov model to analyse time series data of biomarker measurements taken throughout the duration of a COVID-19 patient’s hospitalisation for n = 1540 patients from two hospitals in New York: State University of New York (SUNY) Downstate Health Sciences University and Maimonides Medical Center. Our main focus was to quantify the mortality risk associated with both static (e.g. demographic and patient history variables) and dynamic factors (e.g. changes in biomarkers) throughout hospitalisation, by so doing, to explain the observed patterns of mortality. By using our model to make predictions across the hospitals, we assessed how predictive factors generalised between the two cohorts. The individual dynamics of the measurements and their associated mortality risk were remarkably consistent across the hospitals. The model accuracy in predicting patient outcome (death or discharge) was 72.3% (predicting SUNY; posterior median accuracy) and 71.3% (predicting Maimonides) respectively. Model sensitivity was higher for detecting patients who would go on to be discharged (78.7%) versus those who died (61.8%). Our results indicate the utility of including dynamic clinical measurements when assessing patient mortality risk but also highlight the difficulty of identifying high risk patients.

Article activity feed

  1. Version published to 10.1371/journal.pone.0272442
  2. Version published to 10.1101/2021.11.12.21266248v2 on medRxiv
  3. ScreenIT

    SciScore for 10.1101/2021.11.12.21266248: (What is this?)

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

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    No key resources detected.

    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:
    Our study suffered from a number of limitations. Data availability limited the prognostic factors tested, and future work is therefore required to quantify the mortality risk associated with dynamic changes in other prognostic factors that are known to be important at presentation. These include abnormal biomarkers of inflammation, myocardial injury, acute respiratory distress syndrome (ARDS) and coagulopathy [25, 27]. We also did not include time-dependent changes in certain chemokines and cytokines, which can also indicate disease progression [12, 28]. Additionally, we did not account for the potential impact of patient treatment on dynamic changes in biomarkers or on outcomes. Mechanical ventilation of patients with ARDS, for example, is used to maintain certain arterial pCO2 values, and both mechanical ventilation and certain COVID-19 pharmaceutical treatments can influence inflammatory markers [29, 30]. We considered patients solely hospitalised during early to mid-2020 within a single region (New York), but novel variants and existing immunity may alter survival [31]. Within certain settings, patient survival has improved throughout the course of the pandemic [32], and temporal recalibration of multivariate regression models, which aim to quantify the OR of survival for different prognostic factors, is therefore necessary to ensure survival is not under- or overestimated [33]. Whilst our model performed well across the two cohorts examined, we caution against its use as...

    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.

  4. Version published to 10.1101/2021.11.12.21266248v1 on medRxiv