{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T03:44:34Z","timestamp":1789789474491,"version":"4.0.1"},"reference-count":14,"publisher":"Scientific Scholar","content-domain":{"domain":["ijmr.org.in"],"crossmark-restriction":true},"short-container-title":["Indian J Med Res"],"abstract":"\n Background & objectives<\/jats:title>\n 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\u00a0(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.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n 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).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n 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,\n rpoB<\/jats:italic>\n ,\n katG<\/jats:italic>\n ,\n InhA<\/jats:italic>\n ,\n gyrA\/gyrB<\/jats:italic>\n ,\n rrs<\/jats:italic>\n , and\n eis<\/jats:italic>\n genes. The overall F1 score varies from 0.81 to 1.00, indicating perfect precision and recall.\n <\/jats:p>\n <\/jats:sec>\n \n Interpretation & conclusions<\/jats:title>\n \n 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\n across India\u2019s TB programme, supporting national goals for TB elimination.<\/jats:bold>\n <\/jats:p>\n <\/jats:sec>","DOI":"10.25259\/ijmr_1546_2025","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:34:30Z","timestamp":1769880870000},"page":"910-916","update-policy":"https:\/\/doi.org\/10.25259\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial intelligence for screening drug resistance in tuberculosis"],"prefix":"10.25259","volume":"162","author":[{"given":"Sucharitha Kannappan","family":"Mohanvel","sequence":"first","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramalingam","family":"Radhakrishnan","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasaanth","family":"Balraj","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niket","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachin","family":"Danisetty","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Vats","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aparna","family":"Chaudhury","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Wadhwani Institute for Artificial Intelligence, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hansraj","family":"Choudhary","sequence":"additional","affiliation":[{"name":"Division of Communicable Disease , Indian Council of Medical Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priya","family":"Rajendran","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhumathi","family":"Jayaprakasam","sequence":"additional","affiliation":[{"name":"Division of Communicable Disease , Indian Council of Medical Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senthil","family":"Devi Vadivel","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bershila","family":"Preysingh","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shakinbanu","family":"Thariyasha","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinduja","family":"Anjaiyan","sequence":"additional","affiliation":[{"name":"Department of Tuberculosis, Intermediate Reference Laboratory, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumalata","family":"Chittiboyina","sequence":"additional","affiliation":[{"name":"Department of Tuberculosis, Intermediate Reference Laboratory, Hyderabad, Telangana, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sowmya","family":"Dhawan","sequence":"additional","affiliation":[{"name":"Intermediate Reference Laboratory, State TB Office, Bhopal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shailesh","family":"Lichade","sequence":"additional","affiliation":[{"name":"State TB Training & Demonstration Centre & Intermediate Reference Laboratory, Nagpur, Maharashtra, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rashmi","family":"Kumari","sequence":"additional","affiliation":[{"name":"Health Department, Intermediate Reference Laboratory, Patna, Bihar, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rashmi","family":"Ratnam","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Intermediate Reference Laboratory, Lucknow, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sachin","family":"Chandrakar","sequence":"additional","affiliation":[{"name":"Intermediate Reference Laboratory, Raipur, Chhattisgarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Nasir Khan","sequence":"additional","affiliation":[{"name":"Department of TB Culture and DST Lab, Dr. Sampurnanand Medical College, KN Chest Hospital, Jodhpur, Rajasthan, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashutosh Kumar","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Department of Tuberculosis Culture & DST Lab, Intermediate Reference Laboratory, Indore, Madhya Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Indranath","family":"Roy","sequence":"additional","affiliation":[{"name":"Intermediate Reference Laboratory, Department of Health and Family Welfare, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reena","family":"Kingsberry","sequence":"additional","affiliation":[{"name":"National Tuberculosis Institute, Bengaluru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anand","family":"Sridharan","sequence":"additional","affiliation":[{"name":"Central TB Division, World Health Organization, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranjani","family":"Ramachandran","sequence":"additional","affiliation":[{"name":"Central TB Division, World Health Organization, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nishant","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Central TB Division, Ministry of Family and Health Welfare, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjula","family":"Singh","sequence":"additional","affiliation":[{"name":"Division of Communicable Disease , Indian Council of Medical Research, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raghuram","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Central TB Division, Ministry of Family and Health Welfare, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Urvashi B.","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Central TB Division, Ministry of Family and Health Welfare, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandrasekaran","family":"Padmapriyadarsini","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siva Kumar","family":"Shanmugam","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10894","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"10.25259\/IJMR_1546_2025\/ref-4","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.cca.2022.06.020","article-title":"Systematic evaluation of line probe assays for the diagnosis of tuberculosis and drug-resistant tuberculosis","volume":"533","author":"Lin","year":"2022","journal-title":"Clin Chim Acta"},{"key":"10.25259\/IJMR_1546_2025\/ref-5","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.1016\/j.ijtb.2023.01.006","article-title":"Drug resistance patterns and treatment outcomes in DR-TB patients at a tertiary care centre in Mumbai","volume":"71","author":"Mohan","year":"2024","journal-title":"Indian J Tuberc"},{"key":"10.25259\/IJMR_1546_2025\/ref-8","doi-asserted-by":"crossref","first-page":"e43154","DOI":"10.2196\/43154","article-title":"Machine and deep learning for tuberculosis detection on chest X-rays: Systematic literature review","volume":"25","author":"Hansun","year":"2023","journal-title":"J Med Internet Res"},{"key":"10.25259\/IJMR_1546_2025\/ref-9","doi-asserted-by":"crossref","first-page":"5487","DOI":"10.1038\/s41598-020-62368-2","article-title":"Artificial intelligence and Machine learning based prediction of resistant and susceptible mutations in Mycobacterium tuberculosis","volume":"10","author":"Jamal","year":"2020","journal-title":"Sci Rep"},{"key":"10.25259\/IJMR_1546_2025\/ref-10","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1093\/bioinformatics\/bty949","article-title":"Application of machine learning techniques to tuberculosis drug resistance analysis","volume":"35","author":"Kouchaki","year":"2019","journal-title":"Bioinformatics"},{"key":"10.25259\/IJMR_1546_2025\/ref-11","doi-asserted-by":"crossref","first-page":"21897","DOI":"10.1609\/aaai.v38i20.30191","article-title":"Automatic interpretation of line probe assay test for tuberculosis","volume":"38","author":"Agrawal","year":"2024","journal-title":"AAAI"},{"key":"10.25259\/IJMR_1546_2025\/ref-13","doi-asserted-by":"crossref","first-page":"7567","DOI":"10.1038\/s41598-021-87171-5","article-title":"Development of machine learning model for diagnostic disease prediction based on laboratory tests","volume":"11","author":"Park","year":"2021","journal-title":"Sci Rep"},{"key":"10.25259\/IJMR_1546_2025\/ref-14","doi-asserted-by":"crossref","first-page":"e437","DOI":"10.7717\/peerj-cs.437","article-title":"Classification model for accuracy and intrusion detection using\u00a0machine learning approach","volume":"7","author":"Agarwal","year":"2021","journal-title":"Peer J Comput Sci"},{"key":"10.25259\/IJMR_1546_2025\/ref-15","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13040-021-00244-z","article-title":"The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","volume":"14","author":"Chicco","year":"2021","journal-title":"BioData Min"},{"key":"10.25259\/IJMR_1546_2025\/ref-16","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s10278-020-00399-x","article-title":"An automated deep learning method for Tile AO\/OTA pelvic fracture severity grading from trauma whole-body CT","volume":"34","author":"Dreizin","year":"2021","journal-title":"J Digit Imaging"},{"key":"10.25259\/IJMR_1546_2025\/ref-17","doi-asserted-by":"crossref","first-page":"e693","DOI":"10.1016\/S2589-7500(21)00216-8","article-title":"Evaluation of artificial intelligence on a reference standard based on subjective interpretation","volume":"3","author":"Chen","year":"2021","journal-title":"Lancet Digit Health"},{"key":"10.25259\/IJMR_1546_2025\/ref-18","doi-asserted-by":"crossref","first-page":"874475","DOI":"10.3389\/fmolb.2022.874475","article-title":"Artificial intelligence assisting the early detection of active pulmonary tuberculosis from chest X-rays: a population-based study","volume":"9","author":"Nijiati","year":"2022","journal-title":"Front Mol Biosci"},{"key":"10.25259\/IJMR_1546_2025\/ref-19","doi-asserted-by":"crossref","first-page":"4740","DOI":"10.1038\/s41598-023-31772-9","article-title":"Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB","volume":"13","author":"Yellapu","year":"2023","journal-title":"Sci Rep"},{"key":"10.25259\/IJMR_1546_2025\/ref-20","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1038\/s41598-022-06449-4","article-title":"Accurate and rapid prediction of tuberculosis drug resistance from genome sequence data using traditional machine learning algorithms and CNN","volume":"12","author":"Kuang","year":"2022","journal-title":"Sci Rep"}],"container-title":["The Indian Journal of Medical Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/ijmr.org.in\/artificial-intelligence-for-screening-drug-resistance-in-tuberculosis\/","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/ijmr.org.in\/artificial-intelligence-for-screening-drug-resistance-in-tuberculosis\/","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:34:32Z","timestamp":1769880872000},"score":1,"resource":{"primary":{"URL":"http:\/\/ijmr.org.in\/artificial-intelligence-for-screening-drug-resistance-in-tuberculosis\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":14,"alternative-id":["10.25259\/IJMR_1546_2025"],"URL":"https:\/\/doi.org\/10.25259\/ijmr_1546_2025","relation":{},"ISSN":["0971-5916"],"issn-type":[{"value":"0971-5916","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1,31]]},"article-number":"910"}}