The Role of Artificial Intelligence in Improving Diagnostic Accuracy for Paediatric Tuberculosis

Authors

  • Kanisheka Sharma
  • Arindam Adhikary
  • Inkashaf Alam
  • Shagun Sawhney

Keywords:

Artificial intelligence (AI), Tuberculosis (TB), Machine learning (ML), Computer aided detection (CAD), Nucleic acid amplification test (NAAT), Interferon-gamma release assays (IGRA), Chest radiograph

Abstract


Despite worldwide efforts focused on early diagnosis and treatments to reduce disease transmission, Tuberculosis (TB) remain the leading cause of death for children. Childhood tuberculosis diagnosis is complicated due to the fact that the disease is usually paucibacillary and that it is difficult to collect appropriate clinical samples, leading to the poor sensitivity of the existing tests based on pathogens. Over the last few years, significant technological changes in particular the creation of artificial intelligence (AI) and deep learning have started to transform the field of pediatric TB diagnosis and management. AI-enhance digital chest radiography has demonstrated diagnostic power and sensitivity similar to expert radiologists and at the same time eliminates workload, inter-reader reliability and delays in diagnostics. The CAD systems based on machine learning enhance finding radiographic abnormalities at an early stage and it can be particularly applicable to tuberculosis screening in low-resource or high-burden cases. The review defines the current diagnostic methods like Microscopy, Culture, NAAT like Xpert Mycobacterium tuberculosis/RIF, Interferon-gamma release assays (IGRA) and advanced imaging modalities that emphasize the necessity of having integrated, high-precise and cost-effective diagnostics. Although the potential of AI-based methods is obvious, the issue of data privacy and the absence of standardized validation research, which ensure equal access to AI-based methods, as well as effective systems of governance, are vital measures toward achieving the full potential of artificial intelligence in pediatric TB care.We also the primary challenges to applying AI for paediatric tuberculosis diagnosis and look at current AI application for TB screening in resource-constrained situations. Overall, this review highlights that AI is an effective supplement to current diagnostics, which have promising possibilities of earlier diagnosis, more accurate screening and better management of TB in children worldwide



Downloads

Download data is not yet available.

References

[1] J. Mallozi, “Tuberculosis: an airborne disease.,” UN Chron., vol. 5, no. 2, p. 73, 1998.

[2] S. Basu and S. Chakraborty, “A Comprehensive Review of the Diagnostics for Pediatric Tuberculosis Based on Assay Time, Ease of Operation, and Performance,” Microorganisms, vol. 13, no. 1, 2025, doi: 10.3390/microorganisms13010178.

[3] F. W. Basile, P. Nabeta, M. Ruhwald, and R. Song, “Pediatric Tuberculosis Diagnostics: Present and Future,” J. Pediatric Infect. Dis. Soc., vol. 11, no. Supplement_3, pp. S85–S93, Oct. 2022, doi: 10.1093/JPIDS/PIAC082.

[4] C. C. Boehme et al., “Rapid Molecular Detection of Tuberculosis and Rifampin Resistance,” N. Engl. J. Med., vol. 363, no. 11, pp. 1005–1015, Sep. 2010, doi: 10.1056/NEJMOA0907847;WGROUP:STRING:MMS.

[5] J. Naidoo, S. C. Shelmerdine, C. F. Ugas-Charcape, and A. S. Sodhi, “Artificial Intelligence in Paediatric Tuberculosis,” Pediatr. Radiol., vol. 53, no. 9, pp. 1733–1745, 2023, doi: 10.1007/s00247-023-05606-9.

[6] D. Tristram and E. H. Tobin, “Tuberculosis in Children,” Clin. Tuberc. A Pract. Handb., pp. 81–97, Nov. 2024, doi: 10.1201/b20755-9.

[7] Y. R. Choi, S. H. Yoon, J. Kim, J. Y. Yoo, H. Kim, and K. N. Jin, “Chest Radiography of Tuberculosis: Determination of Activity Using Deep Learning Algorithm,” Tuberc. Respir. Dis. (Seoul)., vol. 86, no. 3, pp. 226–233, 2023, doi: 10.4046/trd.2023.0020.

[8] C. C. Huang et al., “The Contribution of Chest Radiography to the Clinical Management of Children Exposed to Tuberculosis,” Am. J. Respir. Crit. Care Med., vol. 206, no. 7, pp. 892–900, 2022, doi: 10.1164/rccm.202202-0259OC.

[9] J. Onno, F. Ahmad Khan, A. Daftary, and P. M. David, “Artificial intelligence-based computer aided detection (AI-CAD) in the fight against tuberculosis: Effects of moving health technologies in global health,” Soc. Sci. Med., vol. 327, p. 115949, Jun. 2023, doi: 10.1016/j.socscimed.2023.115949.

[10] J. P. Smith et al., “Machine learning to predict bacteriologic confirmation of Mycobacterium tuberculosis in infants and very young children,” PLOS Digit. Heal., vol. 2, no. 5, pp. 1–18, 2023, doi: 10.1371/journal.pdig.0000249.

[11] G. Tavaziva et al., “Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy,” Clin. Infect. Dis., vol. 74, no. 8, pp. 1390–1400, Apr. 2022, doi: 10.1093/CID/CIAB639.

[12] W. C. Chen, C. C. Chang, and Y. E. Lin, “Pulmonary Tuberculosis Diagnosis Using an Intelligent Microscopy Scanner and Image Recognition Model for Improved Acid-Fast Bacilli Detection in Smears,” Microorg. 2024, Vol. 12, Page 1734, vol. 12, no. 8, p. 1734, Aug. 2024, doi: 10.3390/MICROORGANISMS12081734.

[13] Z. Tian, C. Zhu, N. Zhang, B. Yu, and N. Fu, “Computed tomography in the diagnosis of bilateral renal tuberculosis: diagnostic value, limitations, and future directions,” Front. Med. Technol., vol. 7, p. 1592592, Aug. 2025, doi: 10.3389/FMEDT.2025.1592592/BIBTEX.

[14] N. G. Etim, T. Y. Mirabeau, O. A. Olorode, M. U. Nwodo, and S. C. Izah, “Current Diagnostics Tools of Tuberculosis: Challenges And Opportunities,” ES Gen., 2023, doi: 10.30919/ESG1059.

[15] M. Harris et al., “A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis,” PLoS One, vol. 14, no. 9, p. e0221339, Sep. 2019, doi: 10.1371/JOURNAL.PONE.0221339.

[16] J. L. Cross, M. A. Choma, and J. A. Onofrey, “Bias in medical AI: Implications for clinical decision-making,” PLOS Digit. Heal., vol. 3, no. 11, p. e0000651, Nov. 2024, doi: 10.1371/JOURNAL.PDIG.0000651

Downloads

Published

2025-05-20

How to Cite

1.
Sharma K, Adhikary A, Alam I, Sawhney S. The Role of Artificial Intelligence in Improving Diagnostic Accuracy for Paediatric Tuberculosis. J Neonatal Surg [Internet]. 2025 May 20 [cited 2026 Apr. 1];14(20S):1019-23. Available from: https://jneonatalsurg.com/index.php/jns/article/view/9873

Issue

Vol. 14 No. 20S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.