Artificial intelligence is emerging as a powerful tool in shaping personalized nutrition plans for preterm infants, according to a new study published in the Journal of Perinatology. The research, conducted by a collaborative team from the IRCCS San Gerardo dei Tintori Foundation (FSGT) and the Department of Electronics, Information and Bioengineering (DEIB) at the Politecnico di Milano, explores how AI can predict the optimal transition from intravenous (IV) nutrition to oral feeding in premature babies. Preterm infants often face significant challenges in feeding and growth due to underdeveloped digestive systems and limited tolerance for oral intake. Clinicians currently rely on clinical judgment and standardized protocols to gradually introduce oral feeding, but this process can be slow and inconsistent, increasing the risk of complications such as necrotizing enterocolitis or feeding intolerance. The study leveraged machine learning models trained on real-time clinical data collected from preterm infants, including vital signs, growth metrics, gut motility patterns, and nutritional intake. By analyzing these variables, the AI system was able to predict with high accuracy when a baby would be ready to transition from IV nutrition to oral feeding—often days before clinical signs became apparent. The researchers found that AI-driven predictions not only improved timing accuracy but also led to earlier initiation of oral feeding, reduced dependency on IV nutrition, and shorter hospital stays. Importantly, the system was designed to be interpretable, allowing clinicians to understand the reasoning behind each prediction and make informed decisions. This approach represents a shift toward precision neonatology, where AI supports individualized care rather than replacing clinical expertise. The team plans to validate the model in larger, multi-center trials and eventually integrate it into clinical workflows. By helping clinicians anticipate feeding readiness, AI has the potential to improve outcomes for preterm infants, reduce complications, and ease the burden on neonatal intensive care units.