CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV
Open Access
- 9 September 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in npj Digital Medicine
- Vol. 3 (1), 1-8
- https://doi.org/10.1038/s41746-020-00322-2
Abstract
Tuberculosis (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.Keywords
This publication has 36 references indexed in Scilit:
- Xpert (R) MTB/RIF assay for pulmonary tuberculosis and rifampicin resistance in adultsEmergencias, 2013
- Automatic Tuberculosis Screening Using Chest RadiographsIEEE Transactions on Medical Imaging, 2013
- Diagnostic accuracy of a urine lipoarabinomannan strip-test for TB detection in HIV-infected hospitalised patientsEuropean Respiratory Journal, 2012
- HIV-Tuberculosis: A Study of Chest X-Ray Patterns in Relation to CD4 CountNorth American Journal of Medical Sciences, 2012
- Xpert MTB/RIF: a New Pillar in Diagnosis of Extrapulmonary Tuberculosis?Journal of Clinical Microbiology, 2011
- Assessing Tuberculosis Case Fatality Ratio: A Meta-AnalysisPLOS ONE, 2011
- Manifestations of tuberculosis in HIV/AIDS patients and its relationship with CD4 countLung India, 2011
- HIV Infection–Associated Tuberculosis: The Epidemiology and the ResponseClinical Infectious Diseases, 2010
- Radiographic features of pulmonary tuberculosis in patients infected by HIV: is there an objective indicator of co-infection?Revista da Sociedade Brasileira de Medicina Tropical, 2001
- Pulmonary tuberculosis in HIV infection: Radiographic appearance is related to CD4+ T-lymphocyte countTubercle and Lung Disease, 1995