Research Projects

Preeclampsia (PE) is a critical hypertensive disorder affecting maternal health, contributing to over 50,000 maternal causalities and more than 500,000 fetal causalities worldwide (Karrar et al, 2024). In India, the incidence of preeclampsia is estimated to be seven times higher than the developed countries. PE ranks among the leading causes of maternal mortality, alongside conditions such as hemorrhage and sepsis in India (Shandilya et al, 2023). PE is a complex condition affecting multiple organs during pregnancy, typically identified by elevated blood pressure and confirmed through the detection of particular proteins in the urine. Multiple demographic and health-related determinants contribute to the high prevalence of PE in India. Limited access to prenatal healthcare in rural and marginalized regions often leads to delayed detection and inadequate management of the condition. Traditional methods such as monitoring blood pressure and proteinuria for PE detection are rely on laboratory-based test and are time consuming. There is a crucial need for timely and affordable screening test for PE for early intervention and timely treatment. In PE, exosomes may carry biomolecules reflective of trophoblastic injury, including specific microRNAs, DNA fragments, and proteins. The profiling of these exosomal contents offers potential for early prediction of PE (Rao et al, 2023). Isolating and analyzing exosomes from maternal blood or urine is considered a more reliable approach for early PE diagnosis (Melo et al, 2015). Notably, exosomal concentrations have been found to be significantly elevated in cases of early-onset PE (before 34 weeks of gestation) compared to late-onset cases (after 34 weeks) (Pillay et al, 2019). In parallel, growing evidence supports the use of exosomes extracted from maternal blood and urine as promising tools that may enhance both the precision and early detection capabilities of PE diagnostics (Matsubara et al., 2021; Zou et al., 2022; Dutta et al, 2019; Chang et al, 2018). The application of machine learning (ML) can greatly improve the interpretation of this complex exosomal data. By analyzing miRNA signatures and other biomarkers, ML models can help identify individuals at high risk for PE early in pregnancy. Incorporating these models into point-of-care (POC) diagnostic platforms enables timely intervention, even in low-resource settings. Developing a ML-integrated, exosome-based POC system aligns with international efforts to enhance maternal healthcare. With rapid advancements in biosensors, microfluidics, and AI-powered diagnostics, such technologies offer a promising path forward for early detection and improved health equity in pregnancy care worldwide.