Innovative AI Technology Promotes Increased Breastfeeding Success in Neonatal Care

University of Florida has developed AI models to predict and improve breastfeeding success among mothers in NICUs, enhancing neonatal health and maternal well-being.
Researchers at the University of Florida have developed a groundbreaking artificial intelligence (AI) system designed to enhance lactation support and boost breastfeeding rates in neonatal intensive care units (NICUs). This innovative approach aims to help healthcare teams identify mothers at risk of insufficient milk production even before delivery, enabling early intervention strategies tailored to individual needs.
The project, known as Maximizing Initiatives for Lactation Knowledge (MILK+), integrates expertise from physicians, nurses, and AI engineers to predict breastfeeding challenges. Using sophisticated models, clinicians can evaluate factors such as preexisting health conditions, socioeconomic status, and demographic data to assess risks prenatally. Postnatally, the AI analyzes real-time data on breastmilk production to forecast ongoing lactation success after discharge.
The models, trained with data from over 18,000 mothers and more than 22,000 newborns over several years, have achieved an impressive 95% accuracy in predicting breastfeeding outcomes. They also identify the most influential factors affecting a mother’s ability to breastfeed, guiding healthcare providers in delivering targeted support.
Breastfeeding offers significant health benefits for both mother and child, including faster postpartum recovery, reduced risks of chronic conditions like hypertension and diabetes, and enhanced brain development in infants. Despite high initiation rates in Florida (approximately 85%), sustaining breastfeeding remains challenging, especially for mothers of preterm infants or those in the NICU, where separation from the mother can impede the natural feedback loop essential for milk production.
UF Health's NICU has a dedicated lactation support team and has received the Baby-Friendly designation, underscoring its commitment to optimal breastfeeding practices. The AI models are integrated into clinical workflows to identify vulnerable patients early, prompting timely interventions such as additional lactation support and counseling.
As the models continue to improve with ongoing data collection, the team envisions expanding their use across other facilities. The goal is to standardize proactive lactation care, thereby improving breastfeeding success rates and overall neonatal health outcomes. This fusion of advanced technology with compassionate care signifies a promising step toward personalized and predictive healthcare in breastfeeding support.
Stay Updated with Mia's Feed
Get the latest health & wellness insights delivered straight to your inbox.
Related Articles
Increased Risk of Gestational Diabetes Linked to Artificially Sweetened Beverages During Pregnancy
Consuming five or more artificially sweetened beverages weekly before and during pregnancy may increase the risk of gestational diabetes, according to recent research. Learn more about the potential pregnancy health risks associated with low-calorie sweeteners.
Minor Declines in Childhood Vaccination Rates in the US Risk Outbreaks of Preventable Diseases
Small drops in childhood vaccination rates across the U.S. threaten herd immunity, increasing the risk of disease outbreaks such as measles. Stay informed and ensure your children are vaccinated.
Impact of Safety Standards on Reducing Quad Bike Fatalities in Australia Since 2019
Recent Australian research shows a modest decline in work-related quad bike deaths since 2019 safety standards were introduced, highlighting the importance of safety enforcement and helmet use on farms.
Innovative Strategies for Assessing Rheumatic Reactions in Cancer Immunotherapy Patients
A multidisciplinary approach is transforming how healthcare professionals diagnose and manage rheumatic reactions in cancer immunotherapy, emphasizing integrated care and cutting-edge research in onco-rheumatology.



