👤 C Padmapriyadarsini

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

Children exposed to antiretroviral therapy (ART) are at risk of developing metabolic complications. The association between gene polymorphisms and the development of dyslipidemia in children post ART initiation was studied. Children initiating first-line ART were followed for 2 years at the National Institute for Research in Tuberculosis (Chennai, India), and St. John's Medical College Hospital (Bangalore, India). Clinical examination and fasting serum lipid profiles were measured every 6 months. Participants were genotyped for the polymorphisms in the APOC3 gene (rs2854116; rs2854117, and rs5128). Changes in lipid levels from baseline to months 6, 12, and 24, and the difference between the various genotype variants were analyzed using a modified analysis of variance test. Study enrolled 393 ART-naive HIV-infected children (mean age: 7.6 ± 3 years, mean weight: 18 ± 6) of whom 289 (75%) were started on nevirapine (NVP)-based ART and the remaining 96 (25%) were started on efavirenz-based ART. Only children carrying the GG allele of rs5128 genotype showed a decrease in CD4% and serum triglycerides pre-ART. An increasing trend of total cholesterol, high-density lipoprotein cholesterol (HDL-c), and low-density lipoprotein cholesterol were seen at 6 months in both EFZ and NVP groups, which subsequently stabilized by 12 months irrespective of genotype variants. Genotype variants of APOC3 (rs2854116 and rs2854117 polymorphism) did not show significant changes in serum lipid levels after 24 months of ART, whereas rs5128 polymorphism with "G" allele showed an association with HDL-c levels when on NVP-based ART. Our results suggest that ART plays a major role in normalizing lipid levels in HIV-infected children and APOC3 polymorphisms may not play a significant role in ART-induced dyslipidemia. Show less

Cardiovascular disease (CVD) risk with low high-density lipoprotein cholesterol (HDL-C) and high triglycerides is common in the general population in India. As nevirapine (NVP)-based antiretroviral therapy (ART) tends to increase HDL-C, gene polymorphisms associated with HDL-C metabolism in HIV-infected adults on stable NVP-based ART were studied. A cross-sectional study was conducted between January 2013 and July 2014 among adults receiving NVP-based ART for 12-15 months. Blood lipids were estimated and gene polymorphisms in apolipoprotein C3 (APOC3), cholesteryl ester transfer protein (CETP) and lipoprotein lipase (LPL) genes were analyzed by real-time polymerase chain reaction. Framingham's 10-yr CVD risk score was estimated. Logistic regression was done to show factors related to low HDL-C levels. Of the 300 patients included (mean age: 38.6±8.7 yr; mean CD4 count 449±210 cell/μl), total cholesterol (TC) >200 mg/dl was observed in 116 (39%) patients. Thirty nine per cent males and 47 per cent females had HDL-C levels below normal while 32 per cent males and 37 per cent females had TC/HDL ratio of 4.5 and 4.0, respectively. Body mass index [adjusted odds ratio (aOR)=1.70, 95% confidence interval (CI) 1.01-2.84, P=0.04] and viral load (aOR=3.39, 95% CI: 1.52-7.52, P=0.003) were negatively associated with serum HDL-C levels. The 10-yr risk score of developing CVD was 11-20 per cent in 3 per cent patients. Allelic variants of APOC3 showed a trend towards low HDL-C. High-risk lipid profiles for atherosclerosis and cardiovascular disease were common among HIV-infected individuals, even after 12 months of NVP-based ART. Targeted interventions to address these factors should be recommended in the national ART programmes. Show less