<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV

dc.contributor.authorPranav Rajpurkar
dc.contributor.authorChloe O’Connell
dc.contributor.authorAmit Schechter
dc.contributor.authorNishit Asnani
dc.contributor.authorJason Li
dc.contributor.authorAmirhossein Kiani
dc.contributor.authorRobyn L. Ball
dc.contributor.authorMarc Mendelson
dc.contributor.authorGary Maartens
dc.contributor.authorDaniël J. van Hoving
dc.contributor.authorRulan Griesel
dc.contributor.authorAndrew Y. Ng
dc.contributor.authorTom H. Boyles
dc.contributor.authorMatthew P. Lungren
dc.date.accessioned2026-11-18T07:10:27Z
dc.date.issued2020
dc.descriptionOfficial PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. Rights classification: FULL_TEXT_OK. Licence verified from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7481246/ (checked 2026-11-18). Source: grid.7836.a0000 0004 1937 1151Department of Medicine, University of Cape Town, Cape Town, South Africa ORCID: 0000-0002-8030-3727; 0000-0003-4471-477X; 0000-0002-7335-3339; 0000-0002-4300-0372 African relevance: Sector: Healthcare. CheXaid deep-learning tuberculosis diagnostic assistant trained on chest X-rays from two South African hospitals and evaluated with clinicians. Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution.
dc.description.abstractTuberculosis (TB) is the leading cause of preventable death in HIV-positive patients, and yet often remains undiagnosed and untreated. Chest x-ray is often used to assist in diagnosis, yet this presents additional challenges due to atypical radiographic presentation and radiologist shortages in regions where co-infection is most common. We developed a deep learning algorithm to diagnose TB using clinical information and chest x-ray images from 677 HIV-positive patients with suspected TB from two hospitals in South Africa. We then sought to determine whether the algorithm could assist clinicians in the diagnosis of TB in HIV-positive patients as a web-based diagnostic assistant. Use of the algorithm resulted in a modest but statistically significant improvement in clinician accuracy (p = 0.002), increasing the mean clinician accuracy from 0.60 (95% CI 0.57, 0.63) without assistance to 0.65 (95% CI 0.60, 0.70) with assistance. However, the accuracy of assisted clinicians was significantly lower (p < 0.001) than that of the stand-alone algorithm, which had an accuracy of 0.79 (95% CI 0.77, 0.82) on the same unseen test cases. These results suggest that deep learning assistance may improve clinician accuracy in TB diagnosis using chest x-rays, which would be valuable in settings with a high burden of HIV/TB co-infection. Moreover, the high accuracy of the stand-alone algorithm suggests a potential value particularly in settings with a scarcity of radiological expertise.
dc.format.mimetypeapplication/pdf
dc.identifier.doi10.1038/s41746-020-00322-2
dc.identifier.urihttps://doi.org/10.1038/s41746-020-00322-2
dc.identifier.urihttps://library.dare.co.zw/handle/123456789/5091
dc.language.isoen
dc.publisherNature Publishing Group
dc.rightsCC BY 4.0. Licence evidence: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7481246/
dc.rights.holderNamed authors
dc.rights.licenseCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourcegrid.7836.a0000 0004 1937 1151Department of Medicine, University of Cape Town, Cape Town, South Africa
dc.source.urihttps://doi.org/10.1038/s41746-020-00322-2
dc.subjectHealthcare
dc.subjectDiagnosis
dc.subjectMachine learning
dc.subjectNPJ Digital Medicine
dc.titleCheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV
dc.typejournal article

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
applied_healthcare_10_1038_s41746_020_00322_2.pdf
Size:
1.29 MB
Format:
Adobe Portable Document Format