Challenges and Gaps in Tuberculosis Diagnosis: Toward Robust Diagnostic Frameworks for Severity Assessment Using Microscopic Sputum Smears

DOI

10.2991/978-94-6463-978-0_48How to use a DOI?

Keywords

Tuberculosis; microscopy of sputum smears; severity; diagnostics; class imbalance; uncertainty; artificial intelligence

Abstract

Even with the major progress in diagnostics and treatment, tuberculosis (TB) is one of the major causes of mortality related to infections in the world. Despite a low sensitivity and inter-observer variability, microscopy of sputum smears remains the most frequently used diagnostic technique in resource-constrained environments, which can be explained by its cost-effectiveness and availability. Higher sensitivity is offered by molecular X. e.g., GeneXpert MTB/RIF, but is frequently costly enough to be prohibitive, and requires special infrastructure, thus it cannot be as readily available in high-burden, low-income areas. The current diagnostic technologies are mainly providing dichotomous results, i.e., the presence or absence of TB, and do not have effective ways of examining the severity of the disease. This weakness is also intensified by the difficulties of the fact that class balances in diagnostic data sets are not balanced, and predictive models do not handle uncertainty. The underreport seeks to implement a methodological review of TB diagnostics techniques, outline outstanding gaps, and express the necessity of superior computing schemes. Integration of severity quantification, class imbalance control and uncertainty modeling to sputum smear analysis is the way to go in order to come up with diagnostic systems that can give more reliable and clinically feasible information, especially in limited healthcare settings.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Amol Bajrang Chincholkar
AU  - Reema Ajmera
PY  - 2025
DA  - 2025/12/31
TI  - Challenges and Gaps in Tuberculosis Diagnosis: Toward Robust Diagnostic Frameworks for Severity Assessment Using Microscopic Sputum Smears
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 560
EP  - 577
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_48
DO  - 10.2991/978-94-6463-978-0_48
ID  - Chincholkar2025
ER  -