IIT Madras & THSTI Develop India-Specific AI Model for Fetal Age Estimation

The development of GARBH-Ini holds promise for transforming obstetric and neonatal care, contributing to improved maternal and infant outcomes.

Researchers at the Indian Institute of Technology Madras (IIT Madras) and the Translational Health Science and Technology Institute (THSTI) have collaborated to develop an India-specific artificial intelligence (AI) model to precisely determine the age of a fetus during the second and third trimesters of pregnancy.

This initiative is part of the 'Interdisciplinary Group for Advanced Research on Birth Outcomes – DBT India Initiative' (GARBH-Ini) program.

Significance of Accurate Gestational Age

Accurate gestational age (GA) is crucial for ensuring appropriate care for pregnant women and determining precise delivery dates.

The conventional method of determining fetal age relies on a formula developed for Western populations, posing challenges in the later stages of pregnancy due to variations in fetal growth among the Indian population.

The newly developed AI model, named 'Garbhini-GA2,' claims to address this issue specifically by providing precise gestational age estimates tailored to the Indian population.

The 'Garbhini-GA2' model has undergone validation using Indian population data and has demonstrated a substantial reduction in errors compared to existing models.

The researchers state that the precision of fetal age estimation has improved nearly threefold, marking a significant advancement in obstetric and neonatal care. The AI model holds the potential to enhance the quality of care provided by healthcare professionals, contributing to the reduction of maternal and infant mortality rates in India.

The research endeavor was led by Dr Himanshu Sinha, associate professor at the Bhupat and Jyoti Mehta School of Biosciences, Department of Biotechnology, IIT Madras. Dr Shinjini Bhatnagar, principal investigator of the GARBH-Ini program and professor at THSTI, played a pivotal role in the collaborative effort.

The findings of the research were published in the international peer-reviewed journal Lancet Regional Health Southeast Asia.

GARBH-Ini Program and DBT Support

The BRIC-THSTI operates as an institution under the Biotechnology Research and Innovation Council (BRIC), a part of the Department of Biotechnology (DBT) under the Ministry of Science and Technology, Government of India.

As a catalyst, the institute facilitates the translation of fundamental discoveries by establishing robust clinical research capabilities, ensuring the swift transition of breakthroughs from laboratory settings to practical applications in patient care.

GARBH-Ini is a flagship program of the DBT aimed at addressing birth outcome challenges. The development of population-specific models for estimating gestational age is a notable outcome of this program.

Dr Rajesh Gokhale, secretary, DBT, Government of India, commended the program's achievements, emphasizing the validation of these models across the country.

AI & Data Science for Healthcare Solutions

Dr Himanshu Sinha, who is also a coordinator at the Center for Integrative Biology and Systems Medicine, IIT Madras, and who led the data science work for this research, highlighted IIT Madras's commitment to leveraging advanced data science and AI/ML techniques to address healthcare challenges at the grassroots level.

"IIT Madras has been contributing towards solving healthcare problems at the grassroots and local level with the aim of enhancing public health in India. To this end, working with our clinical partner, THSTI, we are utilising advanced data science and AI/ML techniques to build tools to predict unfavourable birth outcomes. The first step towards this is to develop accurate GA models that perform significantly better than currently used models designed using Western populations," he said.

The development of GARBH-Ini holds promise for transforming obstetric and neonatal care, contributing to improved maternal and infant outcomes.

The research outcomes underscore the significance of tailoring healthcare solutions to the specific needs of diverse populations, showcasing the potential of AI and data science in addressing critical healthcare challenges.

In related developments, IIT Madras researchers initiated the #Right2Face project, providing 3D-printed face implants to Black Fungus patients. This severe condition, reported in COVID-19 patients and those with certain medical conditions, received aid through approximately 50 custom implants for economically weaker sections.

Additionally, IIT Madras researchers unveiled 'GBMDriver,' an ML-driven tool enhancing the identification of cancerous brain and spinal cord tumors.