Birth month predicts severe RSV infection in infants

Infants born prior to or within the early weeks of a respiratory syncytial virus (RSV) epidemic must be prioritized to prevent the development of a clinical severe infection, suggests a study that used machine-learning algorithms. 

“Although RSV preventive measures are vital for all infants and specific recommendations exist for patients with high-risk comorbidities, in situations where prioritization becomes necessary, infants born just before or within the early weeks of the epidemic should be considered as a risk group,” the researchers said. 

This retrospective observational study conducted at the Hospices Civils de Lyon, France, involved infants born between 2014 and 2018, focusing on those hospitalized with severe and very severe acute lower respiratory tract infections associated with RSV (SARI-WI group). 

The research team collected data, which included perinatal information and clinical data. They used machine-learning algorithms to distinguish SARI-WI cases from nonhospitalized infants. 

A total of 42,069 infants were identified, of whom 555 developed SARI-WI. Those born in November had a high chance (>80 percent) of developing SARI-WI. Infants born in October were also more likely to acquire RSV-related severe acute lower respiratory infection, but not those who were born at term by vaginal delivery and without siblings. [Pediatr Infec Dis J 2024;43:819-824] 

On the other hand, infants had a low chance (<10 percent) of developing SARI-WI if they met all these conditions: born in other months, at term, by vaginal delivery, and without siblings. Other infants assessed in this study were predicted to develop SARI-WI either possibly (10 percent to 30 percent) or probably (30 percent to 80 percent). 

Birth month 

“Our findings highlighted birth month as the main driver influencing the likelihood of severe RSV disease in our setting,” said the researchers, adding that this data supports previous studies that assessed factors associated with RSV infection. [Vaccines 2022;10:729; Pediatrics 2011;127:35-41; Lancet Digit Health 2023;5:e821-e830] 

“This observation ... [also] highlights the notion that infants born during the initial weeks of the epidemic face a higher risk due to the absence of passive transplacental immunity naturally acquired by their mothers, as their mothers have not recently encountered the virus,” they added. [J Infect Dis 2023;228:1400-1409] 

The current analysis found the month of November to be associated with the highest risk of severe RSV disease, with the RSV epidemic usually starting at week 48 and lasting for up to 15 weeks. [Euro Surveill 2021;26:2100639] 

“It is important to note that this chart is tailored for countries where RSV circulation follows seasonal patterns,” the researchers said. “Local adaptations will be necessary to align with the specific temporal distribution trends in each region.” 

Machine learning 

The use of machine learning in this study enabled researchers to explain the nonlinear relationships between predictors. This feature is not easily achieved via standard logistic regression techniques used in previous RSV studies, according to the researchers. [Int J Med Inf 2014;83:691-714] 

“In addition, machine-learning models tend to yield more accurate predictions,” they said. “The downsampling of the class of nonhospitalized infants enabled us to deal with the relative rarity of SARI-WI cases.” 

However, machine learning is limited by the need to perform a postprocessing phase of the model “to understand its main characteristics” and the lack of easy-to-understand results such as odds ratios, the researchers noted.