Prediction of Mortality in hospitalized COVID-19 patients in a statewide health network

  1. Bharath Ambale-Venkatesh
  2. Thiago Quinaglia
  3. Mahsima Shabani
  4. Jaclyn Sesso
  5. Karan Kapoor
  6. Matthew B Matheson
  7. Colin O Wu
  8. Christopher Cox
  9. Joao A C Lima

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Importance

A predictive model to automatically identify the earliest determinants of both hospital discharge and mortality in hospitalized COVID-19 patients could be of great assistance to caregivers if the predictive information is generated and made available in the immediate hours following admission.

Objective

To identify the most important predictors of hospital discharge and mortality from measurements at admission for hospitalized COVID-19 patients.

Design

Observational cohort study.

Setting

Electronic records from hospitalized patients.

Participants

Patients admitted between March 3 rd and August 24 th with COVID-19 in Johns Hopkins Health System hospitals.

Exposures

216 phenotypic variables collected within 48 hours of admission.

Main Outcomes

We used age-stratified (<60 and >=60 years) random survival forests with competing risks to identify the most important predictors of death and discharge. Fine-Gray competing risk regression (FGR) models were then constructed based on the most important RSF-derived covariates.

Results

Of 2212 patients, 1913 were discharged (age 57±19, time-to-discharge 9±11 days) while 279 died (age 75±14, time to death 14±15 days). Patients >= 60 years were nearly 10 times as likely to die within 60 days of admission as those <60. As the pandemic evolved, the rate of hospital discharge increased in both older and younger patients. Incident death and hospital discharge were accurately predicted by measures of respiratory distress, inflammation, infection, renal function, red cell turn over and cardiac stress. FGR models for each of hospital discharge and mortality as outcomes based on these variables performed well in the older (AUC 0.80-0.85 at 60-days) and younger populations (AUC >0.90 at 60-days).

Conclusions and Relevance

We identified markers collected within 2 days of admission that predict hospital discharge and mortality in COVID-19 patients and provide prediction models that may be used to guide patient care. Our proposed model suggests that hospital discharge and mortality can be forecasted with high accuracy based on 8-10 variables at this stage of the COVID-19 pandemic. Our findings also point to several specific pathways that could be the focus of future investigations directed at reducing mortality and expediting hospital discharge among COVID-19 patients. Probability of hospital discharge increased over the course of the pandemic.

K ey P oints

Question

Can we predict the likelihood of hospital discharge as well as mortality from data obtained in the first 48 hours from admission in hospitalized COVID-19 patients?

Findings

Models based on extensive phenotyping mined directly from electronic medical records followed by variable selection, accounted for the competing events of hospital death versus discharge, predicted both death and discharge with area under the receiver operating characteristic curves of >0.80.

Meaning

Hospital discharge and mortality can be forecasted with high accuracy based on just 8-10 variables, and the probability of hospital discharge increased over the course of the pandemic.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2021.02.17.21251758: (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:
    The limitations of the predictive model for hospital mortality among patients younger than 60 have been emphasized. In that group, 1061 patients were discharged and only 30 died while in the hospital. Therefore, the model for mortality should be interpreted with caution. Another limitation of our study is that data are derived from a statewide health system and their generalizability is therefore affected by population demographic and other regional differences. Data on disease presentation and history of medical conditions from the electronic health record may be incomplete. Similarly, post-discharge outcomes were not included in this analysis and those occurring outside our health care system may have been missed. A strength of this study is the use of competing risk to assess outcomes after hospitalization for COVID-19. As observed in other studies as well as in our study population, the time to discharge is relatively short and the likelihood of discharge is high after hospitalization for COVID-19. Given this scenario, considering patients who were discharged at a given time point as right-censored when in-hospital death is the primary outcome, implicitly assumes that they have similar risk of dying from COVID-19, compared to those who are still at risk (i.e. still in the hospital) at that time point. In such a situation, assessment of competing risks provides a more accurate assessment of risks. The study of time to discharge also adds to our understanding of prolonged h...

    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 10.1101/2021.02.17.21251758v1 on medRxiv