New paper authored by affiliate Antonio P. Ramos and collaborators is accepted for publication in Population Health Metrics

Affiliate Antonio P. Ramos (Pensi Institute, São Paulo, Brazil) and collaborators, Fabio Caldieraro, Marcus L. Nascimento, Raphael Saldanha, paper ‘Reducing Inequalities Using an Unbiased Machine Learning Approach to Identify Births with the Highest Risk of Preventable Neonatal Deaths’ applied machine-learning methods to linked Brazilian birth and death records (2015-2017) to identify newborns at the highest risk of preventable neonatal deaths. They showed that the top 5% of births identified as high risk accounted for over 85% of preventable deaths. Moreover, predictions did not disproportionately exclude disadvantaged groups. Their work demonstrates that health interventions can be directed to those who need them most and where they can be most effective, without creating a bias against disadvantaged populations.

*This work was supported by CCPR through the P2C-HD041022 grant from the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD).