RSV infects almost every child before they turn 2, and it is responsible for more than 100,000 infant deaths globally every year. Machine learning and statistical models are being used to identify those most at risk.
Asunción Mejías, a pediatric infectious diseases specialist, has seen firsthand the deadly unpredictability of RSV. “It’s a disease which can change very quickly,” she says. RSV infections are very common, but some children can develop severe lung disease. The problem is, aside from a few known risk factors, it’s hard to tell which children will be worst affected.
Different research groups are developing machine learning algorithms and statistical models to identify which children are most vulnerable to RSV. These tools aim to identify groups of risk factors that can help predict which children are more likely to be hospitalized with an infection.
Examples of New Tools
– A statistical model developed by Tina Hartert and her colleagues at Vanderbilt University identifies a set of 19 risk factors for RSV.
– The tool uses variables such as prenatal smoking and low birth weight to calculate an individual infant’s risk at birth.
– The tool can help healthcare providers prioritize the most at-risk children for vaccines and other preventative measures.
Preventative Measures
– A vaccine called Abrysvo has been approved to be given to mothers during weeks 32 to 36 of pregnancy to ensure that babies are born with protective antibodies against RSV.
– A drug called Beyfortus has been approved to provide protection ahead of the winter RSV season.