Development of a multivariable prediction model for severe COVID-19 disease: a population-based study from Hong Kong

  1. Jiandong Zhou
  2. Sharen Lee
  3. Xiansong Wang
  4. Yi Li
  5. William Ka Kei Wu
  6. Tong Liu
  7. Zhidong Cao
  8. Daniel Dajun Zeng
  9. Keith Sai Kit Leung
  10. Abraham Ka Chung Wai
  11. Ian Chi Kei Wong
  12. Bernard Man Yung Cheung
  13. Qingpeng Zhang
  14. Gary Tse

Reviewed by

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

Log in to save this article

Abstract

Recent studies have reported numerous predictors for adverse outcomes in COVID-19 disease. However, there have been few simple clinical risk scores available for prompt risk stratification. The objective is to develop a simple risk score for predicting severe COVID-19 disease using territory-wide data based on simple clinical and laboratory variables. Consecutive patients admitted to Hong Kong’s public hospitals between 1 January and 22 August 2020 and diagnosed with COVID-19, as confirmed by RT-PCR, were included. The primary outcome was composite intensive care unit admission, need for intubation or death with follow-up until 8 September 2020. An external independent cohort from Wuhan was used for model validation. COVID-19 testing was performed in 237,493 patients and 4442 patients (median age 44.8 years old, 95% confidence interval (CI): [28.9, 60.8]); 50% males) were tested positive. Of these, 209 patients (4.8%) met the primary outcome. A risk score including the following components was derived from Cox regression: gender, age, diabetes mellitus, hypertension, atrial fibrillation, heart failure, ischemic heart disease, peripheral vascular disease, stroke, dementia, liver diseases, gastrointestinal bleeding, cancer, increases in neutrophil count, potassium, urea, creatinine, aspartate transaminase, alanine transaminase, bilirubin, D-dimer, high sensitive troponin-I, lactate dehydrogenase, activated partial thromboplastin time, prothrombin time, and C-reactive protein, as well as decreases in lymphocyte count, platelet, hematocrit, albumin, sodium, low-density lipoprotein, high-density lipoprotein, cholesterol, glucose, and base excess. The model based on test results taken on the day of admission demonstrated an excellent predictive value. Incorporation of test results on successive time points did not further improve risk prediction. The derived score system was evaluated with out-of-sample five-cross-validation (AUC: 0.86, 95% CI: 0.82–0.91) and external validation ( N  = 202, AUC: 0.89, 95% CI: 0.85–0.93). A simple clinical score accurately predicted severe COVID-19 disease, even without including symptoms, blood pressure or oxygen status on presentation, or chest radiograph results.

Article activity feed

  1. Version published to 10.1038/s41746-021-00433-4
  2. ScreenIT

    SciScore for 10.1101/2020.10.21.20217380: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board StatementIRB: Study design and population: This study was approved by the Institutional Review Board of the University of Hong Kong/Hospital Authority Hong Kong West Cluster.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    They were performed using RStudio software (Version: 1.1.456) and Python (Version: 3.6).
    RStudio
    suggested: (RStudio, RRID:SCR_000432)
    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: We detected the following sentences addressing limitations in the study:
    Limitations: The major limitation of this study is that it is based on a single territory-wide cohort. The model should be externally validated using patient data from other different regions.

    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.

  3. Version published to 10.1101/2020.10.21.20217380 on medRxiv