Clinical validation of an artificial intelligence model for tuberculosis detection in microbiologically confirmed chest x-rays

• Maria C. B. da Silva HIAE
• Thiago F. O. de Camargo HIAE
• Joselisa P. Q. de Paiva HIAE
• Jaqueline D. C. Horvath HIAE
• Guilherme A. S. Ribeiro HIAE

DOI: https://doi.org/10.5753/sbcas_estendido.2025.7025

Abstract

This study presents an artificial intelligence (AI) algorithm based on a ResNet-50 architecture designed to identify chest X-rays with patterns suggestive of pulmonary tuberculosis (TB). The model was trained and internally validated on 13,023 images from public datasets and then clinically validated using a unique dataset of radiographs from patients with microbiologically confirmed TB, with assessments performed by a thoracic radiologist. On public data, the algorithm achieved an AUC of 0.89, sensitivity of 0.84, and specificity of 0.72, while clinical validation yielded an AUC and sensitivity of 1.00. These results underscore the critical importance of incorporating microbiological confirmation as the gold standard to ensure the accuracy and clinical reliability of AI models in TB detection.

References

Bustos, A., Pertusa, A., Salinas, J.-M., et al. (2020). Padchest: A large chest x-ray image dataset with multi-label annotated reports. Medical image analysis, 66:101797.

Cohen, J. P., Viviano, J. D., Bertin, P., et al. (2022). Torchxrayvision: A library of chest x-ray datasets and models. In International Conference on Medical Imaging with Deep Learning, pages 231–249. PMLR.

de Camargo, T. F. O., Ribeiro, G. A. S., da Silva, M. C. B., et al. (2025). Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs. Frontiers in Artificial Intelligence, 8:1512910.

Del Ciello, A., Franchi, P., Contegiacomo, A., et al. (2017). Missed lung cancer: when, where, and why? Diagnostic and interventional radiology, 23(2):118.

Harris, M., Qi, A., Jeagal, L., et al. (2019). A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis. PloS one, 14(9):e0221339.

Huy, V. T. Q. and Lin, C.-M. (2023). An improved densenet deep neural network model for tuberculosis detection using chest x-ray images. IEEE Access, 11:42839–42849.

Irvin, J., Rajpurkar, P., Ko, M., et al. (2019). Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 590–597.

Jaeger, S., Candemir, S., Antani, S., Wang, Y.-X. J., Lu, P.-X., and Thoma, G. (2014). Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quantitative imaging in medicine and surgery, 4(6):475.

Kim, D. W., Jang, H. Y., Kim, K. W., Shin, Y., and Park, S. H. (2019). Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers. Korean journal of radiology, 20(3):405–410.

Malik, H., Anees, T., Din, M., and Naeem, A. (2023). Cdc net: Multi-classification convolutional neural network model for detection of covid-19, pneumothorax, pneumonia, lung cancer, and tuberculosis using chest x-rays. Multimedia Tools and Applications, 82(9):13855–13880.

Ministério da Saúde (MS) (2024). Brasil avança na prevenção, diagnóstico e tratamento da tuberculose. Acesso em: 24 fev. 2025.

Mungai, B., Ong ‘angò, J., Ku, C. C., et al. (2022). Accuracy of computer-aided chest x-ray in community-based tuberculosis screening: Lessons from the 2016 kenya national tuberculosis prevalence survey. PLOS global public health, 2(11):e0001272.

Nguyen, H. Q., Lam, K., Le, L. T., Pham, H. H., et al. (2022). Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations. Scientific Data, 9(1):429.

Organização Mundial da Saúde (OMS) (2024). Global Tuberculosis Report 2024. WHO, Geneva. Acesso em: 24 fev. 2025.

Organização Pan-Americana da Saúde (OPAS) (2024). Opas pede que as américas adotem tecnologias e tratamentos inovadores para eliminar a tb. Acesso em: 24 fev. 2025.

Park, S. H. and Kressel, H. Y. (2018). Connecting technological innovation in artificial intelligence to real-world medical practice through rigorous clinical validation: what peer-reviewed medical journals could do. Journal of Korean Medical Science, 33(22):e152.

Qin, Z. Z., Ahmed, S., Sarker, M. S., Paul, K., et al. (2021). Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. The Lancet Digital Health, 3(9):e543–e554.

Reis, E. P., de Paiva, J. P. Q., da Silva, M. C. B., Ribeiro, G. A. S., et al. (2022). Brax, brazilian labeled chest x-ray dataset. Scientific Data, 9(1):487.

Rosenthal, A., Gabrielian, A., Engle, E., et al. (2017). The tb portals: an open-access, web-based platform for global drug-resistant-tuberculosis data sharing and analysis. Am Soc Microbiol, 55(11):3267–3282.

Tack, D. and Howarth, N. (2019). Missed lung lesions: side-by-side comparison of chest radiography with mdct. Diseases of the Chest, Breast, Heart and Vessels 2019-2022: Diagnostic and Interventional Imaging, pages 17–26.

Yang, Y., Xia, L., Liu, P., Yang, F., Wu, Y., Pan, H., Hou, D., Liu, N., and Lu, S. (2023). A prospective multicenter clinical research study validating the effectiveness and safety of a chest x-ray-based pulmonary tuberculosis screening software jf cxr-1 built on a convolutional neural network algorithm. Frontiers in Medicine, 10:1195451.