• ENG

New Algorithm To Predict Neonatal And Infant Mortality In India Developed

New Algorithm To Predict Neonatal And Infant Mortality In India Developed
Researchers Predict Neonatal And Infant Mortality By Machine Learning Techniques

A team of researchers from the India and the US have identified significant neonatal and infant mortality predictors using multiple machine learning (ML) algorithms.

Written by Kinkini Gupta |Updated : May 30, 2022 8:01 PM IST

India accounts for almost one fifth of the world's annual child births. One of the many babies born dies each minute. Such is the mortality rate of infants in India. According to data reported by UNICEF, almost 46 per cent of all maternal deaths and 40 per cent of neonatal deaths happen during labor or the first 24 hours after birth.

Major Causes Of Infant Deaths

There are many causes for the high mortality rate of infants in India. But the main ones are

Pre-maturity (35 per cent)

Also Read

More News

Neonatal infections (33 per cent)

Birth asphyxia (20 per cent)

Congenital malformations (9 per cent)

Pre-mature Births Are The Leading Cause Of Infant Mortality

In some cases, babies are born earlier than the predicted birth date. Because of early birth, nearly 1.7 million infants are born with birth defects and almost one million new-borns are discharged each year from Special New-born Care Units (SNCUs). These new-borns are at high mortality risks and other risks of stunting, and developmental delay. The critical window of opportunity for preventing infant deaths is the first 28 days after the date of the child's birth.

Experts Say Infant Death Can Be Avoided. How?

A team of researchers from the Indian Institute of Technology, Jodhpur and Western Michigan University, US, has found a solution to the high rate of infant deaths taking place every day. They have identified significant neonatal and infant mortality predictors using multiple machine learning (ML) techniques. This study was published in the journal Applied Economics. It uses a range of machine learning algorithms to assess the relative importance of criteria's such as first-born children, being born in households that are poor or are below poverty level and weight of the new born baby. They have also identified some early warning indicators such as observable biological characteristics; demographic characteristics; and socio-economic factors of households, mothers and new-borns.

As part of India's Newborn Action Plan, their main goal is to enable researchers identify a 'high mortality risk' group of mothers and infants. This will become possible through the predictors from the interpretable ML algorithms. Early identification of any risk factors will allow women and new-borns to get timely medical care and reduce the child mortality rate in India.

Goal Of This Study

The team said that the future goal is to extend and develop more streamlined screening criteria with the availability of more granular data with a combination of clinical and socio-economic characteristics.

The research team stated, "Our analysis sheds light on policy relevance and suggests some new policy prescriptions such as close monitoring of at-risk babies including females and those with small birth-size."