COMPARATIVE EVALUATION OF THE DIAGNOSTIC ACCURACY OF ARTIFICIAL INTELLIGENCE-ASSISTED TOOLS AND CONVENTIONAL TOOLS FOR PULMONARY TUBERCULOSIS SCREENING: A SYSTEMATIC REVIEW AND META-ANALYSIS
DOI:
https://doi.org/10.17501/26138417.2025.8110Keywords:
diagnostic accuracy, screening, meta-analysis, tuberculosisAbstract
Tuberculosis is a preventable and curable disease, however, it remains as the second leading cause of death worldwide. Systematic screening for TB is one of the key active approaches of the End TB Strategy. However, conventional tools for TB screening have some limitations. AI-based algorithms could be developed, which can help in improving the performance of conventional screening methods. This study intends to evaluate the diagnostic test accuracy of AI-assisted PTB screening tools by meta-analyzing existing literature, and comparison of sensitivity and specificity, as well as assessment of factors which may influence the diagnostic performance of AI-assisted TB screening tools. Literature search was done through electronic databases, reference tracking, and library search. The Preferred Reporting of Items for Systematic Reviews and Meta-Analysis (PRISMA) flow diagram was used to report the selection and screening of relevant studies between 2014 to 2024. A final count of 31 studies were included in this analysis. Quality assessment was done through the use of QUADAS-C tool. Meta analysis was done through RevMan 5.4.1 and STATA 17. Sensitivity and specificity were used in this analysis. A subgroup analysis was also conducted. The AI-assisted screening tools for pulmonary tuberculosis showed a pooled sensitivity of 93.84% (95% CI: 90.88-95.88) and 83.27% (95% CI: 73.41-89.97), and a diagnostic odds ratio (DOR) of 75.829 (95% CI: 33.19-173.23). Machine Learning (ML) algorithms yielded the highest sensitivity and specificity at 95.06% (95% CI:83.57-98.64) and 91.01% (95% CI: 76.76-96.88) respectively among the AI algorithm subgroup. The results of the meta-analysis done show that AI-assisted screening tools for pulmonary tuberculosis are viable options to improve screening for pulmonary tuberculosis. More robust, multi-center clinical studies regarding the diagnostic accuracy of these AI-assisted tools must be conducted in order to ensure a more valid and generalizable study.
Downloads
References
Breuninger, M., Van Ginneken, B., Philipsen, R. H. H. M., Mhimbira, F., Hella, J. J., Lwilla, F., et al. (2014). Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: A validation study from sub-Saharan Africa. PLOS ONE, 9(9), e106381.
Chauhan, A., Chauhan, D., & Rout, C. (2014). Role of GIST and PHOG features in computer-aided diagnosis of tuberculosis without segmentation. PLOS ONE, 9(11), e112980.
Muyoyeta, M., Maduskar, P., Moyo, M., Kasese, N., Milimo, D., Spooner, R., et al. (2014). The sensitivity and specificity of using a computer-aided diagnosis program for automatically scoring chest X-rays of presumptive TB patients compared with Xpert MTB/RIF in Lusaka, Zambia. PLOS ONE, 9(4), e93757.
Melendez, J., Van Ginneken, B., Maduskar, P., Philipsen, R. H. H. M., Reither, K., Breuninger, M., et al. (2015). A novel multiple-instance learning-based approach to computer-aided detection of tuberculosis on chest X-rays. IEEE Transactions on Medical Imaging, 34(1), 179–192.
Steiner, A., Mangu, C., Van Den Hombergh, J., Van Deutekom, H., Van Ginneken, B., Clowes, P., et al. (2015). Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays. Public Health Action, 5(4), 249–254.
Hooda, R., Sofat, S., Kaur, S., Mittal, A., & Meriaudeau, F. (2017). Deep learning: A potential method for tuberculosis detection using chest radiography. In 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) (pp. 497–502). IEEE. https://doi.org/10.1109/ICSIPA.2017.8120663
Zaidi, S. M. A., Habib, S. S., Van Ginneken, B., Ferrand, R. A., Creswell, J., Khowaja, S., et al. (2018). Evaluation of the diagnostic accuracy of computer-aided detection of tuberculosis on chest radiography among private sector patients in Pakistan. Scientific Reports, 8(1), 12339.
Philipsen, R. H. H. M., Sánchez, C. I., Melendez, J., Lew, W. J., & Van Ginneken, B. (2019). Automated chest X-ray reading for tuberculosis in the Philippines to improve case detection: A cohort study. International Journal of Tuberculosis and Lung Disease, 23(7), 805–810.
Habib, S. S., Rafiq, S., Zaidi, S. M. A., Ferrand, R. A., Creswell, J., Van Ginneken, B., et al. (2020). Evaluation of computer-aided detection of tuberculosis on chest radiography among people with diabetes in Karachi, Pakistan. Scientific Reports, 10(1), 6276.
Khan, F. A., Majidulla, A., Tavaziva, G., Nazish, A., Abidi, S. K., Benedetti, A., et al. (2020). Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: A prospective study of diagnostic accuracy for culture-confirmed disease. Lancet Digital Health, 2(11), e573–e581.
Natarajan, A., Beena, P. M., Devnikar, A. V., & Mali, S. (2020). A systemic review on tuberculosis. Indian Journal of Tuberculosis, 67(3), 295–311.
Alsdurf, H., Empringham, B., Miller, C., & Zwerling, A. (2021). Tuberculosis screening costs and cost-effectiveness in high-risk groups: A systematic review. BMC Infectious Diseases, 21(1), 935.
Murphy, K., Habib, S. S., Zaidi, S. M. A., Khowaja, S., Khan, A., Melendez, J., et al. (2020). Computer-aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system. Scientific Reports, 10(1), 5492.
Nash, M., Kadavigere, R., Andrade, J., Sukumar, C. A., Chawla, K., Shenoy, V. P., et al. (2020). Deep learning, computer-aided radiography reading for tuberculosis: A diagnostic accuracy study from a tertiary hospital in India. Scientific Reports, 10(1), 210.
Rahman, T., Khandakar, A., Kadir, M. A., Islam, K. R., Islam, K. F., Mazhar, R., et al. (2020). Reliable tuberculosis detection using chest X-ray with deep learning, segmentation, and visualization. IEEE Access, 8, 191586–191601.
Ullah, R., Khan, S., Chaudhary, I. I., Shahzad, S., Ali, H., & Bilal, M. (2020). Cost-effective and efficient screening of tuberculosis disease with Raman spectroscopy and machine learning algorithms. Photodiagnosis and Photodynamic Therapy, 32, 101963.
Ayaz, M., Shaukat, F., & Raja, G. (2021). Ensemble learning-based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors. Physiological Engineering and Science in Medicine, 44(1), 183–194.
Codlin, A. J., Dao, T. P., Vo, L. N. Q., Forse, R. J., Van Truong, V., Dang, H. M., et al. (2021). Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Scientific Reports, 11(1), 23895.
Das, D., Santosh, K. C., & Pal, U. (2021). Inception-based deep learning architecture for tuberculosis screening using chest X-rays. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 3612–3619). IEEE. https://doi.org/10.1109/ICPR48806.2021.9412748
Dasanayaka, C., & Dissanayake, M. B. (2021). Deep learning methods for screening pulmonary tuberculosis using chest X-rays. Computational Methods in Biomechanics and Biomedical Engineering Imaging and Visualization, 9(1), 39–49.
Govindarajan, S., & Swaminathan, R. (2021). Extreme learning machine-based differentiation of pulmonary tuberculosis in chest radiographs using integrated local feature descriptors. Computational Methods and Programs in Biomedicine, 204, 106058.
Qin, Z. Z., Ahmed, S., Sarker, M. S., Paul, K., Adel, A. S. S., Naheyan, T., et al. (2021). Tuberculosis detection from chest X-rays for triaging in a high tuberculosis-burden setting: An evaluation of five artificial intelligence algorithms. Lancet Digital Health, 3(9), e543–e554.
Sharma, A., Sharma, A., Malhotra, R., Singh, P., Chakrabortty, R. K., Mahajan, S., et al. (2021). An accurate artificial intelligence system for the detection of pulmonary and extrapulmonary tuberculosis. Tuberculosis, 131, 102143.
Acharya, V., Dhiman, G., Prakasha, K., Bahadur, P., Choraria, A., M. S., et al. (2022). AI-assisted tuberculosis detection and classification from chest X-rays using a deep learning normalization-free network model. Computational Intelligence and Neuroscience, 2022, 1–19.
Bhandari, M., Shahi, T. B., Siku, B., & Neupane, A. (2022). Explanatory classification of CXR images into COVID-19, pneumonia, and tuberculosis using deep learning and XAI. Computational Biology and Medicine, 150, 106156.
U.S. Agency for International Development. (2022). Philippines tuberculosis roadmap overview, fiscal year 2023 [Internet]. Available from: https://www.usaid.gov/global-health/health-areas/tuberculosis/resources/news-and-updates/global-accelerator-end-tb/tb-roadmaps/philippines-tuberculosis-roadmap-overview-fiscal-year-2022
Gelaw, S. M., Kik, S. V., Ruhwald, M., Ongarello, S., Egzertegegne, T. S., Gorbacheva, O., et al. (2023). Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: Analysis of an international, multicenter migrants screening study. PLOS Global Public Health, 3(7), e0000402.
Simi Margarat, G., Hemalatha, G., Mishra, A., Shaheen, H., Maheswari, K., Tamijeselvan, S., et al. (2022). Early diagnosis of tuberculosis using deep learning approach for IoT-based healthcare applications. Computational Intelligence and Neuroscience, 2022, 1–9.
Kagujje, M., Kerkhoff, A. D., Nteeni, M., Dunn, I., Mateyo, K., & Muyoyeta, M. (2023). The performance of computer-aided detection digital chest X-ray reading technologies for triage of active tuberculosis among persons with a history of previous tuberculosis. Clinical Infectious Diseases, 76(3), e894–e901.
Manivannan, K., & Sathiamoorthy, S. (2023). Automated tuberculosis classification using Egret swarm optimization with deep learning-based fusion model on chest X-ray images. Journal of Intelligent & Fuzzy Systems, 45(6), 10335–10347.
World Health Organization. (2023). Global tuberculosis report 2023 [Internet]. Available from: https://www.who.int/teams/global-tuberculosis-programme/tb-reports/global-tuberculosis-report-2023
Yellapu, G. D., Rudraraju, G., Sripada, N. R., Mamidgi, B., Jalukuru, C., Firmal, P., et al. (2023). Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB. Scientific Reports, 13(1), 4740.
Flores, G., Tamayo, R., Leong, R. N., Biglaen, C. S., Uy, K. N., Maglenete, R., et al. (2024). Diagnostic performance of a computer-aided system for tuberculosis screening in two Philippine cities. Acta Medica Philippina. https://doi.org/10.47895/amp.v58i1.8950
Okada, K., Yamada, N., Takayanagi, K., Hiasa, Y., Kitamura, Y., Hoshino, Y., et al. (2024). Applicability of artificial intelligence-based computer-aided detection (AI–CAD) for pulmonary tuberculosis to community-based active case finding. Tropical Medicine and Health, 52(1), 2.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Conrigo Boya Santos, Jejunee Rivera, Vladimir Alexis Sustento
This work is licensed under a Creative Commons Attribution 4.0 International License.
