Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct 29;8(11):488.
doi: 10.3390/tropicalmed8110488.

Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam's District Health Facilities: An Implementation Study

Anh L Innes  1 , Andres Martinez  2 , Xiaoming Gao  2 , Nhi Dinh  2 , Gia Linh Hoang  3 , Thi Bich Phuong Nguyen  3 , Viet Hien Vu  3 , Tuan Ho Thanh Luu  3 , Thi Thu Trang Le  3 , Victoria Lebrun  3 , Van Chinh Trieu  3 , Nghi Do Bao Tran  3 , Zhi Zhen Qin  4 , Huy Minh Pham  5 , Van Luong Dinh  6 , Binh Hoa Nguyen  6 , Thi Thanh Huyen Truong  6 , Van Cu Nguyen  6 , Viet Nhung Nguyen  6   7 , Thu Hien Mai  3
Affiliations

Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam's District Health Facilities: An Implementation Study

Anh L Innes et al. Trop Med Infect Dis. .

Abstract

In Vietnam, chest radiography (CXR) is used to refer people for GeneXpert (Xpert) testing to diagnose tuberculosis (TB), demonstrating high yield for TB but a wide range of CXR abnormality rates. In a multi-center implementation study, computer-aided detection (CAD) was integrated into facility-based TB case finding to standardize CXR interpretation. CAD integration was guided by a programmatic framework developed for routine implementation. From April through December 2022, 24,945 CXRs from TB-vulnerable populations presenting to district health facilities were evaluated. Physicians interpreted all CXRs in parallel with CAD (qXR 3.0) software, for which the selected TB threshold score was ≥0.60. At three months, there was 47.3% concordance between physician and CAD TB-presumptive CXR results, 7.8% of individuals who received CXRs were referred for Xpert testing, and 858 people diagnosed with Xpert-confirmed TB per 100,000 CXRs. This increased at nine months to 76.1% concordant physician and CAD TB-presumptive CXRs, 9.6% referred for Xpert testing, and 2112 people with Xpert-confirmed TB per 100,000 CXRs. Our programmatic CAD-CXR framework effectively supported physicians in district facilities to improve the quality of referral for diagnostic testing and increase TB detection yield. Concordance between physician and CAD CXR results improved with training and was important to optimize Xpert testing.

Keywords: artificial intelligence; calibration; innovative diagnosis; radiography; tuberculosis.

PubMed Disclaimer

Conflict of interest statement

A.L.I., G.L.H., T.B.P.N., V.H.V., T.H.T.L., T.T.T.L., V.L., V.C.T., N.D.B.T. and T.H.M. received salary support from USAID Contract No. AID-440-C-16-00001 and Agreement No. 72044020CA00002; A.M., X.G. and N.D. were funded by the same USAID Contract and Agreement to conduct statistical analyses for this work. H.M.P. (USAID) participated in the conceptualization of the work and in the manuscript review; USAID as the funding organization was otherwise not involved in the design, conceptualization, analysis, or manuscript preparation. Z.Z.Q., V.L.D., B.H.N., T.T.H.T., V.C.N. and V.N.N. have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
Framework for programmatic computer-aided detection (CAD) artificial intelligence to interpret chest radiography (CXR) for tuberculosis (TB) abnormalities.
Figure 2
Figure 2
CAD integration into the Double X algorithm in district facilities. Data are from nine months (April–December 2022) of CAD-parallel implementation, in which both CAD and physicians interpreted all CXRs for TB vulnerable populations. 2X = Double X; MTB = mycobacterium tuberculosis; Xpert = GeneXpert; (+) = positive by Xpert test; (−) = negative by Xpert test.
See this image and copyright information in PMC

References

    1. World Health Organization (WHO) Global Tuberculosis Report 2022. WHO; Geneva, Switzerland: 2022.
    1. Miller C., Lonnroth K., Sotgiu G., Migliori G.B. The long and winding road of chest radiography for tuberculosis detection. Eur. Respir. J. 2017;49:1700364. doi: 10.1183/13993003.00364-2017. - DOI - PubMed
    1. Harris M., Qi A., Jeagal L., Torabi N., Menzies D., Korobitsyn A., Pai M., Nathavitharana R.R., Ahmad Khan F. A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis. PLoS ONE. 2019;14:e0221339. doi: 10.1371/journal.pone.0221339. - DOI - PMC - PubMed
    1. Singh R., Kalra M.K., Nitiwarangkul C., Patti J.A., Homayounieh F., Padole A., Rao P., Putha P., Muse V.V., Sharma A., et al. Deep learning in chest radiography: Detection of findings and presence of change. PLoS ONE. 2018;13:e0204155. doi: 10.1371/journal.pone.0204155. - DOI - PMC - PubMed
    1. Murphy K., Habib S.S., Zaidi S.M.A., Khowaja S., Khan A., Melendez J., Scholten E.T., Amad F., Schalekamp S., Verhagen M., et al. Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system. Sci. Rep. 2020;10:5492. doi: 10.1038/s41598-020-62148-y. - DOI - PMC - PubMed

LinkOut - more resources