
To develop an early peripheral blood transcriptomic signature that can predict preterm neonates at risk for developing BPD. Neonates with BPD (n=62) exhibited a lower median gestational age and birthweight than non-BPD neonates. From an initial pool, 4,523 genes showed a false discovery rate (FDR) <1%. The machine learning models revealed AUCs ranging between 85.8% and 96.1%. Pathways integral to T cell development and differentiation were most associated with BPD. A derived 5-gene whole blood signature can accurately predict BPD in the first week of life.
Like
Save
Share