👤 Madhumathi Jayaprakasam

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 eisgenes. 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. Show less

Fatty acid elongases and desaturases play an important role in hepatic and whole body lipid composition. We examined the role that key transcription factors played in the control of hepatic elongase and desaturase expression. Studies with peroxisome proliferator-activated receptor alpha (PPARalpha)-deficient mice establish that PPARalpha was required for WY14643-mediated induction of fatty acid elongase-5 (Elovl-5), Elovl-6, and all three desaturases [Delta(5) desaturase (Delta(5)D), Delta(6)D, and Delta(9)D]. Increased nuclear sterol-regulatory element binding protein-1 (SREBP-1) correlated with enhanced expression of Elovl-6, Delta(5)D, Delta(6)D, and Delta(9)D. Only Delta(9)D was also regulated independently by liver X receptor (LXR) agonist. Glucose induction of l-type pyruvate kinase, Delta(9)D, and Elovl-6 expression required the carbohydrate-regulatory element binding protein/MAX-like factor X (ChREBP/MLX) heterodimer. Suppression of Elovl-6 and Delta(9)D expression in livers of streptozotocin-induced diabetic rats and high fat-fed glucose-intolerant mice correlated with low levels of nuclear SREBP-1. In leptin-deficient obese mice (Lep(ob/ob)), increased SREBP-1 and MLX nuclear content correlated with the induction of Elovl-5, Elovl-6, and Delta(9)D expression and the massive accumulation of monounsaturated fatty acids (18:1,n-7 and 18:1,n-9) in neutral lipids. Diabetes- and obesity-induced changes in hepatic lipid composition correlated with changes in elongase and desaturase expression. In conclusion, these studies establish a role for PPARalpha, LXR, SREBP-1, ChREBP, and MLX in the control of hepatic fatty acid elongase and desaturase expression and lipid composition. Show less