India has launched its largest pregnancy cohort study involving 12,000 women under the GARBH-INi (Interdisciplinary Group for Advanced Research on Birth Outcomes) initiative. Union Minister Dr Jitendra Singh announced the milestone, highlighting the programme’s focus on developing AI-driven solutions to predict preterm births.
Preterm birth remains a major global public health challenge, contributing significantly to neonatal mortality and long-term health complications. Since India accounts for a substantial share of these cases, experts stress the urgent need for context-specific, data-driven healthcare solutions.
GARBH-INi Programme Focuses on Indigenous Research
To address this challenge, the Department of Biotechnology (DBT) launched the GARBH-INi programme to develop research tailored specifically to Indian populations. The initiative integrates clinical epidemiology, multi-omics biomarkers, and artificial intelligence to create personalised predictive models for pregnancy outcomes.
Speaking at a recent event, Dr Jitendra Singh noted that the programme has already enrolled around 12,000 pregnant women, making it one of the largest pregnancy research cohorts in South Asia.
Massive Dataset to Drive AI-Based Maternal Health Research
As reported by digitalhealthnews, the initiative has already generated an extensive scientific database. Researchers have collected over 1.6 million biospecimens and more than one million ultrasound images as part of the study.
Scientists are using this large dataset to:
- Develop AI-based pregnancy dating models suited for Indian populations
- Identify microbiome-linked predictors of preterm birth
- Create rapid diagnostic tools and genetic markers for early risk detection
These innovations aim to improve early diagnosis and clinical decision-making in maternal healthcare.
National Biorepository and Data Platform Boost Global Collaboration
One of the key milestones of the programme is the creation of a national biorepository alongside the GARBH-INi-DRISHTI data-sharing platform.
This platform allows secure access to anonymised research data for scientists worldwide, thereby enabling broader research collaboration and accelerating scientific discoveries in maternal and neonatal health.
Partnerships Accelerate Real-World Implementation
To translate research findings into practical healthcare solutions, the programme has also formed strategic industry partnerships.
These collaborations include technology transfer initiatives for microbiome-based biotherapeutics and partnerships with technology companies such as Qure.ai. Through these partnerships, researchers aim to develop AI-enabled ultrasound reporting systems and advanced risk stratification tools for predicting pregnancy complications.
Supporting India’s Vision for Better Maternal and Child Health
Dr Jitendra Singh linked the GARBH-INi initiative to India’s long-term development vision for 2047, emphasising that improving maternal and child health is critical for building a healthier and more productive population.
He also highlighted the rapid expansion of India’s bioeconomy, which has grown significantly over the past decade due to advancements in biotechnology, biomedical research, and preventive healthcare innovation.
Experts Call for Scaling Predictive Healthcare Tools
Healthcare experts, including Dr V. K. Paul, Member of NITI Aayog, have stressed the need to move the programme into its next phase of implementation.
This next stage will involve:
- Scaling AI-based predictive tools for clinical use
- Expanding data analysis to uncover new health insights
- Strengthening collaborations between research institutions and industry
Transforming Maternal Healthcare Through Data and Technology
As the initiative progresses, GARBH-INi is expected to play a pivotal role in translating scientific research into accessible maternal healthcare solutions. By combining large-scale clinical data, artificial intelligence, and collaborative research, the programme aims to reduce preterm birth risks and improve maternal and neonatal outcomes across India.