Machine Learning in Tuberculosis: Advancements in Diagnostics, Drug Resistance Prediction, and Prognosis
Disease Prevention and Epidemiology · 24.02.2026 · 1 (1) · 48-62
DOI: 10.64229/0x7z9373 ↗Kurz gefasst
Fachartikel in der Zeitschrift Disease Prevention and Epidemiology, online erschienen am 24.02.2026. Verfasst von Stalin Arulsamy und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Tuberculosis (TB) continues to challenge global health and has become much worse due to the complexities associated with diagnosis, the need to perform time-consuming culture-based drug susceptibility testing, and the emergence of drug-resistant strains. The integration of machine learning (ML) and Artificial Intelligence (AI) has transformed how we computationally approach TB control, providing approaches to use ML and AI as tools to assist with the entire scope of the disease, rapidly and accurately, without the need for invasive methods. This review highlights the recent developments in the application of ML models and highlights their potential use as diagnostic biomarkers (e.g., using host-gene-expression, metabolomics, and spectrographic data), predicting drug resistance from genomic sequencing (Whole-Genome Sequencing), and predicting patient prognosis and treatment outcome. Although there are many different algorithms that can produce predictive results, further work in developing capabilities for model interpretation and performing external validation using diverse cohorts from around the world is needed to enable the use of these novel tools to be incorporated into everyday clinical use; thereby supporting continued efforts to achieve global eradication of TB.
Zitieren
APA
Arulsamy, S., & Sharma, S. (2026). Machine Learning in Tuberculosis: Advancements in Diagnostics, Drug Resistance Prediction, and Prognosis. Disease Prevention and Epidemiology, 1(1), 48-62. https://doi.org/10.64229/0x7z9373
Vancouver
Arulsamy S, Sharma S. Machine Learning in Tuberculosis: Advancements in Diagnostics, Drug Resistance Prediction, and Prognosis. Disease Prevention and Epidemiology. 2026;1(1):48-62. doi:10.64229/0x7z9373
BibTeX
@article{Arulsamy2026,
author = {Arulsamy, Stalin and Sharma, Shivank},
title = {Machine Learning in Tuberculosis: Advancements in Diagnostics, Drug Resistance Prediction, and Prognosis},
journal = {Disease Prevention and Epidemiology},
year = {2026},
volume = {1},
number = {1},
pages = {48--62},
doi = {10.64229/0x7z9373}
}
EUVIMED