IIT Madras Develops 1st India-Specific AI Model for Accurate Foetal Age Determination

Chennai: Researchers at the Indian Institute of Technology (IIT) Madras have unveiled a groundbreaking Artificial Intelligence (AI) model named ‘Garbhini-GA2’. This model, tailored specifically for the Indian population, accurately estimates the gestational age of foetuses during the second and third trimesters of pregnancy.

Traditional methods in India rely on formulas designed for Western populations, leading to increased margin of error. However, the Garbhini-GA2 model reduces this error significantly, as validated in a study published in Lancet Regional Health Southeast Asia.

Led by Dr. Himanshu Sinha from IIT Madras, the research team collaborated with the Translational Health Science and Technology Institute (THSTI), Faridabad, under the ‘Interdisciplinary Group for Advanced Research on Birth Outcomes — DBT India Initiative’ (GARBH-Ini) programme.

Dr. Rajesh Gokhale, Secretary of the Department of Biotechnology (DBT), praised the initiative, highlighting its potential to enhance maternal and infant healthcare in India.

The Garbhini-GA2 model utilizes ultrasound parameters from the GARBH-Ini cohort data, initially collected at Gurugram Civil Hospital, Haryana. It has been successfully validated in a South Indian cohort.

With further validation in pan-India cohorts, the Garbhini-GA2 model is poised to revolutionize obstetric and neonatal care across India, thereby reducing maternal and infant mortality rates.

Principal Investigator of the GARBH-Ini programme, Dr. Shinjini Bhatnagar, emphasized the model’s role in mitigating adverse pregnancy outcomes.