Automated chest radiograph diagnosis: A Twofer for Tuberculosis and Covid-19

  1. Mitushi Verma
  2. Deepak Patkar
  3. Madhura Ingalharikar
  4. Amit Kharat
  5. Pranav Ajmera
  6. Viraj Kulkarni
  7. Aniruddha Pant
  8. Vaishnavi Thakker
  9. Gunjan Naik

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Coronavirus disease (Covid 19) and Tuberculosis (TB) are two challenges the world is facing. TB is a pandemic which has challenged mankind for ages and Covid 19 is a recent onset fast spreading pandemic. We study these two conditions with focus on Artificial Intelligence (AI) based imaging, the role of digital chest x-ray and utility of end to end platform to improve turnaround times. Using artificial intelligence assisted technology for triage and creation of structured radiology reports using an end to end platform can ensure quick diagnosis. Changing dynamics of TB screening in the times of Covid 19 pandemic have resulted in bottlenecks for TB diagnosis. The paper tries to outline two types of use cases, one is COVID-19 screening in a hospital-based scenario and the other is TB screening project in mobile van setting and discusses the learning of these models which have both used AI for prescreening and generating structured radiology reports.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.10.13.20178483: (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

    No key resources detected.

    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:
    On the flip side there are limitations in the X-ray examination, COVID 19 carriers and asymptomatic may not be diagnosed. Also, there is risk of exposure to radiation although minimal. These can be subjected to surveillance testing by RT-PCR and serology through a decision support tool as the one provided by British Society of Thoracic Imaging [19]. This may also help bring down the burden of the tests to be performed using RT PCR [20]. Although, using RT-PCR has led to a few false-negative results they have been attributed to the quality of the kit, the collected sample, or performance of the test. RT-PCR has been widely deployed in diagnostic virology and has yielded few false-positive outcomes as well [21]. In conclusion, However the dynamics of diagnostics are changing on a day to day basis and are dependent on various factors and the foremost being access to healthcare. Performing clinical assessment, SPO2 monitoring, CBC and digital Xray of the chest in symptomatic to assist triage could be an option which can help tide the crisis of Covid-19 and can be decided on the available infrastructure and guidelines can be structured accordingly. Promoting mobile van diagnostic testing can help tackle especially in hot spot two conditions – Covid 19 and TB [22]. This could also be an opportunity in disguise to scale the TB screening process, if India want to meet the target of TB eradication by 2025 and WHO wants to adhere to the global target of TB elimination by 2030. Our expe...

    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.

  2. Version published to 10.1101/2020.10.13.20178483v1 on medRxiv