GARBH-INi Initiative: India’s AI-Driven Push to Tackle Preterm Births

Why in News ?

The government has highlighted that India’s largest pregnancy cohort study under the GARBH-INi initiative, involving around 12,000 women, is aimed at developing indigenous, AI-driven solutions to predict and prevent preterm births.

Background and Context

India continues to face significant challenges in :

• Maternal health
• Infant mortality
• Adverse pregnancy outcomes

Among these, preterm birth is a leading cause of :

• Neonatal deaths
• Long-term health complications

Need for Intervention

• Limited early prediction tools
• High burden of maternal and neonatal morbidity
• Dependence on non-indigenous research data

This necessitated a large-scale, India-specific research initiative.

About GARBH-INi Initiative

The GARBH-INi Initiative (Group for Advanced Research in BirtH outcomes – DBT India Initiative) :

• Launched in May 2015
• Focuses on maternal and child health research
• Aims to develop predictive tools for adverse pregnancy outcomes

Institutional Framework :

• Implemented under the Department of Biotechnology (DBT)
• Led by Translational Health Science and Technology Institute
• Part of the Atal Jai Anusandhan Biotech Mission

Key Objectives

• Develop deep scientific understanding of :
  • Preterm birth (PTB)
  • Fetal growth restriction (FGR)
• Create :
  • Early prediction tools
  • Preventive strategies
• Reduce :
  • Maternal mortality
  • Neonatal morbidity

What is Preterm Birth ?

Preterm birth refers to babies born before 37 weeks of pregnancy.

Categories :

• Extremely preterm: < 28 weeks
• Very preterm: 28–32 weeks
• Moderate to late preterm: 32–37 weeks

Key Features of the Initiative

1. Large Cohort Study

• Involves 12,000 pregnant women
• Generates : 
  • Longitudinal health data
  • India-specific evidence

2. AI-Driven Predictive Models

• Uses :
  • Artificial Intelligence
  • Machine Learning
• Helps in :
  • Early detection of risks
  • Timely medical intervention

3. Interdisciplinary Approach

• Combines : 
  • Biotechnology
  • Clinical research
  • Data science

4. Indigenous Research Focus

• Reduces reliance on : 
  • Western datasets
• Builds : 
  • Context-specific solutions

Significance of the Initiative

1. Improving Maternal and Child Health

• Early prediction reduces : 
  • Complications
  • Mortality rates

2. Strengthening Public Health Systems

• Provides data for : 
  • Evidence-based policymaking

3. Technological Advancement

• Promotes : 
  • AI integration in healthcare

4. Reducing Healthcare Burden

• Preventive care reduces : 
  • Hospitalisation costs
  • Long-term treatment needs

5. Supporting National Health Goals

• Contributes to : 
  • SDGs on maternal and child health

Challenges

• Data privacy and ethical concerns
• Integration of AI tools into public health systems
• Accessibility in rural and low-resource settings
• Need for skilled healthcare workforce

Way Forward

• Scale up AI-based tools across healthcare systems
• Strengthen maternal healthcare infrastructure
• Ensure ethical use of health data
• Increase awareness among healthcare providers
• Integrate findings into national health programmes