Deep learning for predicting COVID-19 malignant progression

  1. Cong Fang
  2. Song Bai
  3. Qianlan Chen
  4. Yu Zhou
  5. Liming Xia
  6. Lixin Qin
  7. Shi Gong
  8. Xudong Xie
  9. Chunhua Zhou
  10. Dandan Tu
  11. Changzheng Zhang
  12. Xiaowu Liu
  13. Weiwei Chen
  14. Xiang Bai
  15. Philip H.S. Torr

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

No abstract available

Article activity feed

  1. Version published to 10.1016/j.media.2021.102096
  2. ScreenIT

    SciScore for 10.1101/2020.03.20.20037325: (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

    Software and Algorithms
    SentencesResources
    Implementation details: The proposed network is implemented using Python (Version 3.6 with scipy, scikit-learn, and PyTorch).
    Python
    suggested: (IPython, RRID:SCR_001658)
    scipy
    suggested: (SciPy, RRID:SCR_008058)
    scikit-learn
    suggested: (scikit-learn, RRID:SCR_002577)

    Results from OddPub: Thank you for sharing your code.

    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    However, our study still has several limitations. First, samples available for malignant progression prediction are limited. The diverse data in the large-scale dataset will allow deep learning-based methods to gain a more comprehensive understanding of what causes the malignant progression. Second, the data source of our study is limited to three hospital branches of two hospitals in Wuhan. More data needs to be collected from multiple centers, especially from foreign hospitals, to further enhance our model. Third, this study only conducts an interpretable analysis of the relationship between prognostic factors and patients who are easy to deteriorate from the perspective of relevance. Future studies can combine evidence-based medicine to identify the cause and effect of malignant progression.

    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 10.1101/2020.03.20.20037325v3 on medRxiv
  4. ScreenIT

    SciScore for 10.1101/2020.03.20.20037325: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board StatementThis study was approved by the Institutional Review Board of Wuhan Pulmonary Hospital on February 6, 2020.Randomizationnot detected.BlindingAll serial CT images were reviewed by three radiologists (QC, CC, DN, 2 years’ experience in radiology) independently blinded to the clinical information, and the discrepancy was resolved by consulting another radiologist (WC, 15 years’ experience in radiology).Power Analysisnot detected.Sex as a biological variable* * B A * C * D * Figure 4: Representative cases without malignant progres progression(C, D) A 32-year-old male with symptoms of fever, cough, and dyspnoea lesion (yellow stars) in the left upper lobe and some fibrosis (red a image of 3 days follow-up (B) shows the prior lesions shrunk in size male with symptoms of fever, dyspnoea. CT1 (C) shows ground bilateral upper lobes.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    Statistical Analysis All the statistical analysis was performed using SPSS (Version 26) with statistical significance set at 0.05.
    SPSS
    suggested: (SPSS, SCR_002865)
    Statistical optimization of the deep learning model was done through iterative training using Python (Version 3.6 with scipy, scikit-learn, and pytorch packages).
    Python
    suggested: (IPython, SCR_001658)
          <div style="margin-bottom:8px">
        <div><b>scipy</b></div>
        <div>suggested: (SciPy, <a href="https://scicrunch.org/resources/Any/search?q=SCR_008058">SCR_008058</a>)</div>
      </div>
    
      <div style="margin-bottom:8px">
        <div><b>scikit-learn</b></div>
        <div>suggested: (scikit-learn, <a href="https://scicrunch.org/resources/Any/search?q=SCR_002577">SCR_002577</a>)</div>
      </div>
    </td></tr><tr><td style="min-width:100px;vertical-align:top;border-bottom:1px solid lightgray">Admission Critical Severe Mild 0 5 10 15 20 Onset of symptoms 2 Days Mild patients without severe/cri Mild patients with severe/critica Mild patients with severe/critica igure 5: The plots of clinical courses for all included patients OC curves of different methods on COVID-19 dataset er operating characteristic.</td><td style="min-width:100px;border-bottom:1px solid lightgray">
      <div style="margin-bottom:8px">
        <div><b>Mild</b></div>
        <div>suggested: (MILD, <a href="https://scicrunch.org/resources/Any/search?q=SCR_003335">SCR_003335</a>)</div>
      </div>
    </td></tr></table>

    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).

    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 is not a substitute for expert review. SciScore checks for the presence and correctness of RRIDs (research resource identifiers) in the manuscript, and detects sentences that appear to be missing RRIDs. SciScore also checks to make sure that rigor criteria are addressed by authors. It does this by detecting sentences that discuss criteria such as blinding or power analysis. SciScore does not guarantee that the rigor criteria that it detects are appropriate for the particular study. Instead it assists authors, editors, and reviewers by drawing attention to sections of the manuscript that contain or should contain various rigor criteria and key resources. For details on the results shown here, including references cited, please follow this link.

  5. Version published to 10.1101/2020.03.20.20037325v2 on medRxiv
  6. Version published to 10.1101/2020.03.20.20037325v1 on medRxiv