EUVIMEDEUVIMED entdecken
Open Access

Artificial intelligence for screening drug resistance in tuberculosis

Sucharitha Kannappan Mohanvel, Ramalingam Radhakrishnan, Prasaanth Balraj, Niket Singh, Sachin Danisetty, Harsh Vats, Aparna Chaudhury, Hansraj Choudhary, Priya Rajendran, Madhumathi Jayaprakasam, Senthil Devi Vadivel, Bershila Preysingh und 20 weitere

The Indian Journal of Medical Research · 2026

DOI: 10.25259/ijmr_1546_2025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Indian Journal of Medical Research, 2026. Verfasst von Sucharitha Kannappan Mohanvel und 31 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India. Hauptthemen laut MEDLINE: Artificial Intelligence, Mycobacterium tuberculosis, Tuberculosis, Tuberculosis, Multidrug-Resistant. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: World Health Organization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background & objectives Central TB division facilitated development of a line probe assay (LPA) artificial intelligence (AI) tool. The tool was developed, trained, and validated for performance by collecting more than 18,000 LPA strips across culture and drug susceptibility Testing (C&DST) laboratories. The Indian Council of Medical Research (ICMR)-National Institute for Research in Tuberculosis (NIRT) evaluated the LPAAI tool independently. The objective was to establish and verify an AI-driven system for automatically interpreting LPA strips, which are employed in tuberculosis drug resistance screening, to improve accuracy, consistency, and scalability across diverse laboratory settings.

Methods

The AI system integrates faster regions convolutional neural network (FR-CNN) for strip detection, detection transformer (DETR) for band localisation, and a hierarchical neural network (HNN) for classification of bands, loci, and drug labels. Independent validation was conducted by ICMR-NIRT using 2810 first-line (FL)-LPA and 241 reflex second-line (SL-LPA) across ten intermediate reference laboratories (IRLs).

Results

AI comparative models demonstrated an accuracy range of 92-100 per cent, with sensitivity between 80-100 per cent and specificity from 86-100 per cent for the tub, rpoB , katG , InhA , gyrA/gyrB , rrs , and eis genes. The overall F1 score varies from 0.81 to 1.00, indicating perfect precision and recall. Interpretation & conclusions This AI system offers a novel, modular architecture capable of expert-level interpretation of LPA strips. The AI tool performs at par with expert readers and offers a reliable, scalable solution for LPA interpretation.AI tool adoption can reduce interpretation time, enhance result uniformity, and improve treatment delivery across India’s TB programme, supporting national goals for TB elimination.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceMycobacterium tuberculosisTuberculosisTuberculosis, Multidrug-ResistantHumansMicrobial Sensitivity TestsConvolutional Neural NetworksAntitubercular AgentsNeural Networks, ComputerIntelligent Systems

Stichwörter der Autor:innen

Artificial intelligenceDRTBhierarchical neural networkline probe assay

Substanzen

Antitubercular Agents

Autor:innen und Institutionen

  • Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India.
  • Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India.
  • Division of Communicable Disease , Indian Council of Medical Research, New Delhi, India.
  • Department of Tuberculosis, Intermediate Reference Laboratory, Chennai, Tamil Nadu, India.
  • Department of Tuberculosis, Intermediate Reference Laboratory, Hyderabad, Telangana, India.
  • Intermediate Reference Laboratory, State TB Office, Bhopal, India.

Förderung

  • World Health Organization

Zitieren

APA

Mohanvel, S. K., Radhakrishnan, R., Balraj, P., Singh, N., Danisetty, S., Vats, H., Chaudhury, A., Choudhary, H., Rajendran, P., Jayaprakasam, M., Devi Vadivel, S., Preysingh, B., Thariyasha, S., Anjaiyan, S., Chittiboyina, S., Dhawan, S., Lichade, S., Kumari, R., Ratnam, R., …, & Shanmugam, S. K. (2026). Artificial intelligence for screening drug resistance in tuberculosis. The Indian Journal of Medical Research. https://doi.org/10.25259/ijmr_1546_2025

Vancouver

Mohanvel SK, Radhakrishnan R, Balraj P, Singh N, Danisetty S, Vats H, et al. Artificial intelligence for screening drug resistance in tuberculosis. The Indian Journal of Medical Research. 2026. doi:10.25259/ijmr_1546_2025

BibTeX
@article{Mohanvel2026,
  author = {Mohanvel, Sucharitha Kannappan and Radhakrishnan, Ramalingam and Balraj, Prasaanth and Singh, Niket and Danisetty, Sachin and Vats, Harsh and Chaudhury, Aparna and Choudhary, Hansraj and Rajendran, Priya and Jayaprakasam, Madhumathi and Devi Vadivel, Senthil and Preysingh, Bershila and Thariyasha, Shakinbanu and Anjaiyan, Sinduja and Chittiboyina, Sumalata and Dhawan, Sowmya and Lichade, Shailesh and Kumari, Rashmi and Ratnam, Rashmi and Chandrakar, Sachin and Nasir Khan, Mohammed and Srivastava, Ashutosh Kumar and Roy, Indranath and Kingsberry, Reena and Sridharan, Anand and Ramachandran, Ranjani and Kumar, Nishant and Singh, Manjula and Rao, Raghuram and Singh, Urvashi B and Padmapriyadarsini, Chandrasekaran and Shanmugam, Siva Kumar},
  title = {Artificial intelligence for screening drug resistance in tuberculosis},
  journal = {The Indian Journal of Medical Research},
  year = {2026},
  doi = {10.25259/ijmr_1546_2025}
}
Kostenlos starten →