Network for subclinical prognostication of COVID 19 Patients from data of thoracic roentgenogram: A feasible alternative screening technology

  1. Akash Bararia
  2. Abhirup Ghosh
  3. Chiranjit Bose
  4. Debarati Bhar

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Background and Study Aim

COVID 19 is the terminology driving people’s life in the year 2020 without a supportive globally high mortality rate. Coronavirus lead pandemic is a new found disease with no gold standard diagnostic and therapeutic guideline across the globe. Amidst this scenario our aim is to develop a prediction model that makes mass screening easy on par with reducing strain on hospitals diagnostic facility and doctors alike. For this prediction model, a neural network based on Chest X-ray images has been developed. Alongside the aim is also to generate a case record form that would include prediction model result along with few other subclinical factors for generating disease identification. Once found positive then only it will proceed to RT-PCR for final validation. The objective was to provide a cheap alternative to RT-PCR for mass screening and to reduced burden on diagnostic facility by keeping RT-PCR only for final confirmation.

Methods

Datasets of chest X-ray images gathered from across the globe has been used to test and train the network after proper dataset curing and augmentation.

Results

The final neural network-based prediction model showed an accuracy of 81% with sensitivity of 82% and specificity of 90%. The AUC score obtained is 93.7%.

Discussion and Conclusion

The above results based on the existing datasets showcase our model capability to successfully distinguish patients based on Chest X-ray (a non-invasive tool) and along with the designed case record form it can significantly contribute in increasing hospitals monitoring and health care capability.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.09.07.20189852: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    All statistical analysis was performed using GraphPad Prism version 8.0.2.
    GraphPad Prism
    suggested: (GraphPad Prism, RRID:SCR_002798)

    Results from OddPub: Thank you for sharing your code and data.

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We found bar graphs of continuous data. We recommend replacing bar graphs with more informative graphics, as many different datasets can lead to the same bar graph. The actual data may suggest different conclusions from the summary statistics. For more information, please see Weissgerber et al (2015).

    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 10.1101/2020.09.07.20189852v1 on medRxiv