A novel artificial intelligence-assisted triage tool to aid in the diagnosis of suspected COVID-19 pneumonia cases in fever clinics

  1. Cong Feng
  2. Lili Wang
  3. Xin Chen
  4. Yongzhi Zhai
  5. Feng Zhu
  6. Hua Chen
  7. Yingchan Wang
  8. Xiangzheng Su
  9. Sai Huang
  10. Lin Tian
  11. Weixiu Zhu
  12. Wenzheng Sun
  13. Liping Zhang
  14. Qingru Han
  15. Juan Zhang
  16. Fei Pan
  17. Li Chen
  18. Zhihong Zhu
  19. Hongju Xiao
  20. Yu Liu
  21. Gang Liu
  22. Wei Chen
  23. Tanshi Li

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

No abstract available

Article activity feed

  1. Version published to 10.21037/atm-20-3073
  2. Version published to 10.1101/2020.03.19.20039099v2 on medRxiv
  3. ScreenIT

    SciScore for 10.1101/2020.03.19.20039099: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board StatementIRB: The study was approved by institutional ethics committee of the General Hospital of the PLA (NO.: 2020-094 the registration number of ethics board).
    Consent: Studies performed on de-identified data constitute non-human subject research, thus no informed consent was required for this study.
    RandomizationDuring the model training, we randomly held out 20% of the cohort data as a testing set and then used 10-fold cross-validation to yield the optimal of the LASSO regularization parameter in the training and validation sets.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    All computations were achieved by scikit-learn (version: 0.22.1) in python.
    scikit-learn
    suggested: (scikit-learn, RRID:SCR_002577)
    The model validation was also performed in python.
    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:
    Although the diagnosis results are highly reliable according to the recall score, inevitable limitations may still exist in this study. First, we only evaluated lymphopenia, elevated CRP, and elevated IL-6, while other biomarkers might be more discriminant. Second, the data size was relatively small based on only a single-center fever clinic, which calls for ‘big data’ analysis depend on multiple-center fever clinics. Third, the model was developed and validated in mildly ill patients and with fewer comorbidities; therefore, more well-performing models would be welcomed for a specifical subpopulation. Fourth, since the model was developed and validated in a single-center fever clinic, the performance might vary when evaluated in other fever clinics, particularly if they differ in patient characteristics and COVID-19 prevalence. Therefore, the diagnosis aid model of this study requires further external validation based on different background populations. Fifth, there is a potential risk for misuse of the online calculator. To make the right choice and decision, more consideration should be taken in suited patients and classification threshold (27). Last but not the least, the “Suspected COVID-19 pneumonia Diagnosis Aid System” would only be used as one of the auxiliary references for making clinical and management decisions.

    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.

  4. Version published to 10.1101/2020.03.19.20039099v1 on medRxiv