Distinguishing COVID-19 From Influenza Pneumonia in the Early Stage Through CT Imaging and Clinical Features

  1. Zhiqi Yang
  2. Daiying Lin
  3. Xiaofeng Chen
  4. Jinming Qiu
  5. Shengkai Li
  6. Ruibin Huang
  7. Zhijian Yang
  8. Hongfu Sun
  9. Yuting Liao
  10. Jianning Xiao
  11. Yanyan Tang
  12. Xiangguang Chen
  13. Sheng Zhang
  14. Zhuozhi Dai

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Both coronavirus disease 2019 (COVID-19) and influenza pneumonia are highly contagious and present with similar symptoms. We aimed to identify differences in CT imaging and clinical features between COVID-19 and influenza pneumonia in the early stage and to identify the most valuable features in the differential diagnosis.

Methods

Seventy-three patients with COVID-19 confirmed by real-time reverse transcription-polymerase chain reaction (RT-PCR) and 48 patients with influenza pneumonia confirmed by direct/indirect immunofluorescence antibody staining or RT-PCR were retrospectively reviewed. Clinical data including course of disease, age, sex, body temperature, clinical symptoms, total white blood cell (WBC) count, lymphocyte count, lymphocyte ratio, neutrophil count, neutrophil ratio, and C-reactive protein, as well as 22 qualitative and 25 numerical imaging features from non-contrast-enhanced chest CT images were obtained and compared between the COVID-19 and influenza pneumonia groups. Correlation tests between feature metrics and diagnosis outcomes were assessed. The diagnostic performance of each feature in differentiating COVID-19 from influenza pneumonia was also evaluated.

Results

Seventy-three COVID-19 patients including 41 male and 32 female with mean age of 41.9 ± 14.1 and 48 influenza pneumonia patients including 30 male and 18 female with mean age of 40.4 ± 27.3 were reviewed. Temperature, WBC count, crazy paving pattern, pure GGO in peripheral area, pure GGO, lesion sizes (1–3 cm), emphysema, and pleural traction were significantly independent associated with COVID-19. The AUC of clinical-based model on the combination of temperature and WBC count is 0.880 (95% CI: 0.819–0.940). The AUC of radiological-based model on the combination of crazy paving pattern, pure GGO in peripheral area, pure GGO, lesion sizes (1–3 cm), emphysema, and pleural traction is 0.957 (95% CI: 0.924–0.989). The AUC of combined model based on the combination of clinical and radiological is 0.991 (95% CI: 0.980–0.999).

Conclusion

COVID-19 can be distinguished from influenza pneumonia based on CT imaging and clinical features, with the highest AUC of 0.991, of which crazy-paving pattern and WBC count play most important role in the differential diagnosis.

Article activity feed

  1. Version published to 10.3389/fmicb.2022.847836
  2. ScreenIT

    SciScore for 10.1101/2020.04.17.20061242: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board StatementIRB: Patients: Ethical approval by the institutional review boards of Second affiliated Hospital of Shantou University Medical
    Consent: College (Approval number: SDYFE202029) was obtained for this retrospective analysis, with the requirement for informed consent waived.
    Randomizationnot detected.
    BlindingFor the extraction of CT qualitative and quantitative imaging features, two senior radiologists (Z.Y. and X.C., more than 15 years of experience) reached a consensus and were blinded to the clinical and laboratory findings.
    Power Analysisnot detected.
    Sex as a biological variableAmong them, 41 patients were men (mean age: 41.4 years; range: 16 - 69 years) and 32 were women (mean age: 42.6 years; range: 3 - 66 years).

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    All statistical analyses for this study were performed with R (version 3.6.4, http://www.r-project.org/).
    http://www.r-project.org/
    suggested: (R Project for Statistical Computing, RRID:SCR_001905)

    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:
    There are several limitations in this study. First, in order to evaluate the differential diagnosis in the early stage, we only compare the initial CT scanning both in COVID-19 and influenza pneumonia. Since the CT manifestations change with the course of the disease (34), our results may have a bias at different time windows. Second, there may be some inherent deviations in the multi-center retrospective design (35), since the scanning protocols are slightly diverse in different hospitals. Finally, although the preliminary results are promising, further validation on a larger and independent dataset is needed to determine the potential of these features for distinguishing COVID-19 from influenza pneumonia. After validation, further diagnostic models may be created based on these features. In conclusion, a total of 1537 lesions and 62 features were compared between COVID-19 and influenza pneumonia patients. Twenty-six features were significantly different between the two groups. In CT imaging, the crazy paving pattern was recognized as the most powerful feature in the differential diagnosis in the early stage, with AUC of 0.687 (95% CI: 0.611∼0.764). In clinical manifestations, white blood cell count had the highest AUC of 0.811 (95% CI: 0.731∼0.890). These findings help to distinguish COVID-19 from influenza pneumonia.

    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 10.1101/2020.04.17.20061242v1 on medRxiv