John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
Artificial intelligence (AI) is showing promise in improving the way doctors provide intravenous (IV) nutrition to premature infants, according to a study from Stanford Medicine. Published in Nature Medicine on March 25, the study is among the first to demonstrate the benefits of using an AI algorithm to enhance clinical decisions for newborns in neonatal intensive care units.
The AI algorithm analyzes data from preemies’ electronic medical records to predict their nutritional needs. It uses historical data from nearly 80,000 past IV nutrition prescriptions to optimize dosages. Senior study author Nima Aghaeepour, PhD, emphasized the importance of this development, noting that “total parenteral nutrition is the single largest source of medical error in neonatal intensive care units.”
The AI system proposes standard formulas to meet patients' nutrition needs, potentially easing the burden of the current system, which requires input from a multidisciplinary team. This could reduce medical errors, save time, and lower costs, particularly in low-resource settings. “If we had manufactured, ready-to-use TPNs, that would be very beneficial. I think it would be safer for patients,” said study co-author and pharmacy expert Shabnam Gaskari, PharmD.
Despite the progress shown by AI in creating nutrient formulas, the research team affirmed the importance of clinician oversight. “The AI recommendation is based on whatever information has been added to a patient’s electronic medical record, so if something is missing from the record, the recommendation won’t be accurate,” Gaskari mentioned.
The AI model was tested using historical data from the Lucile Packard Children’s Hospital Stanford, including nearly 80,000 prescriptions, and validated with data from the University of California, San Francisco. A randomized clinical trial is planned to compare outcomes using AI-recommended prescriptions against traditional methods.
David Stevenson, MD, a study coauthor, expressed optimism about AI's role in neonatal care, noting, “This reflects our hope for how AI will enhance medicine: What it’s going to do is make doctors better and make top-notch care more accessible.”
The study received support from various institutions including the National Institutes of Health and the Burroughs Wellcome Fund. It also involved contributions from the University of Southern California Keck School of Medicine and Children's Hospital of Los Angeles.
Alerts Sign-up