Publication:
Diagnostic Accuracy of Artificial Intelligence-Based Chest X-Ray reading for screening of Tuberculosis

Simple item page
creativeworkseries.issn1999-6217
dc.contributor.authorShrestha, Ruby Maka
dc.contributor.authorPaudel, Ram Chandra
dc.contributor.authorAdhikari, Puspanjali
dc.contributor.authorGhimire, Ram Hari
dc.contributor.authorGurung, Karma
dc.contributor.authorShrestha, Rajeev
dc.date.accessioned2025-07-20T06:21:32Z
dc.date.available2025-07-20T06:21:32Z
dc.date.issued2024
dc.descriptionRuby Maka Shrestha Dhulikhel Hospital, Kathmandu University Hospital, Dhulikhel, Kavre, Nepal Ram Chandra Paudel Dhulikhel Hospital, Kathmandu University Hospital, Dhulikhel, Kavre, Nepal Puspanjali Adhikari Dhulikhel Hospital, Kathmandu University Hospital, Dhulikhel, Kavre, Nepal Ram Hari Ghimire Nobel Medical College and Teaching Hospital, Biratnagar, Morang, Nepal Karma Gurung International Organisation for Migration, Baluwatar, Kathmandu, Nepal Rajeev Shrestha Dhulikhel Hospital, Kathmandu University Hospital, Dhulikhel, Kavre, Nepal
dc.description.abstractBackground: Tuberculosis remains a public health challenge in Nepal and ranks as the seventh leading cause of death in the country. The END Tuberculosis strategy stresses - the screening for symptoms alone may not suffice; additional screening tools such as a chest radiograph may facilitate referral for diagnosis of tuberculosis. The study aims to evaluate the diagnostic accuracy of artificial intelligence (AI) based Chest X-ray and compare it with the human reading (radiologist), using GeneXpert-MTB RIF Assay for tuberculosis case detection. Methods: Tuberculosis-suspected patients with a history of cough were screened using chest X-rays at two study sites (Dhulikhel Hospital and Nobel Medical College). The reading of AI qXR software was compared with radiologists reading who were blinded of the results generated by the software. Results: The sensitivity of the test by qXR-based AI reading was 100%, (95% CI: 40 – 100%) and specificity 80% (95% CI: 73 – 87%), whereas the sensitivity of the test by the radiologist was 100%, (95% CI: 40 – 100%); and specificity 62% (95% CI: 53 – 70%). Conclusions: Higher sensitivity and specificity were observed for both qXR-based AI and Radiographer readings for the diagnosis of TB. Keywords: Artificial Intelligence; chest X-ray; diagnostic accuracy; screening; tuberculosis.
dc.identifierhttps://doi.org/10.33314/jnhrc.v22i03.4637
dc.identifier.urihttps://hdl.handle.net/20.500.14572/391
dc.language.isoen_US
dc.publisherNepal Health Research Council
dc.titleDiagnostic Accuracy of Artificial Intelligence-Based Chest X-Ray reading for screening of Tuberculosis
dc.typeArticle
dspace.entity.typePublication
local.article.typeOriginal Article
oaire.citation.endPage483
oaire.citation.startPage477
relation.isJournalIssueOfPublicationbdc38a4e-8fed-4c8d-ae10-a4918d68512e
relation.isJournalIssueOfPublication.latestForDiscoverybdc38a4e-8fed-4c8d-ae10-a4918d68512e
relation.isJournalOfPublication40bd2739-8b19-447c-be60-723a1bdd1dcd

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
477-483.pdf
Size:
302.96 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.86 KB
Format:
Item-specific license agreed to upon submission
Description:
Download

Collections

Publications

Connect with us

Nepal Health Research Council © 2023
Ramshah Path, Kathmandu Nepal P.O.Box 7626