AI-guided precision parenteral nutrition for neonatal intensive care units

One in ten neonates are admitted to neonatal intensive care units, highlighting the need for precise interventions. However, the application of artificial intelligence (AI) in guiding neonatal care remains underexplored. Total parenteral nutrition (TPN) is a life-saving treatment for preterm neonates; however, implementation of the therapy in its current form is subjective, error-prone and resource-consuming. Here, we developed TPN2.0-a data-driven approach that optimizes and standardizes TPN using information collected routinely in electronic health records. We assembled a decade of TPN compositions (79,790 orders; 5,913 patients) at Stanford to train TPN2.0. In addition to internal validation, we also validated our model in an external cohort (63,273 orders; 3,417 patients) from a second hospital. Our algorithm identified 15 TPN formulas that can enable a precision-medicine approach (Pearson's R = 0.94 compared to experts), increasing safety and potentially reducing cost. A blinded study (n = 192) revealed that physicians rated TPN2.0 higher than current best practice. In patients with high disagreement between the actual prescriptions and TPN2.0, standard prescriptions were associated with increased morbidities (for example, odds ratio = 3.33; P value = 0.0007 for necrotizing enterocolitis), while TPN2.0 recommendations were linked to reduced risk. Finally, we demonstrated that TPN2.0 employing a transformer architecture enabled guideline-adhering, physician-in-the-loop recommendations that allow collaboration between the care team and AI.

Authors

Institutions

Publication Details

Journal
Nature Medicine
Published
2025-03-25
DOI
https://doi.org/10.1038/s41591-025-03601-1
Citations
15
Primary Topic
Neonatal Respiratory Health Research
Type
article
Field-Weighted Citation Impact
22.78
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AI-guided precision parenteral nutrition for neonatal intensive care units

Jacquelyn Roger, Davide De Francesco, J Costello, Roberta L. Keller et al.
15 citations
Nature Medicine
Neonatal Respiratory Health Research
22.78
article

AI-guided precision parenteral nutrition for neonatal intensive care units

Jacquelyn Roger, Davide De Francesco, J Costello, Roberta L. Keller, Thanaphong Phongpreecha, Marc Ghanem, Martin S. Angst, Lawrence S. Prince, Steven Levitte, Hannah Gu, Yeasul Kim, Tomiko Oskotsky, Valerie Y. Chock, Janene H. Fuerch, Nima Aghaeepour, Gary M. Shaw, Camilo Espinosa, Brice Gaudillière, John A. Kerner, Sheila Razdan, David Seong, Yuqi Tan, Matthew Szeto, S. Momsen Reincke, Sayane Shome, John Feister, Jonathan D. Reiss, Eloïse Berson, Ronald J. Wong, Laura Rose, Feng Xie, Karl G. Sylvester, Thomas J. Montine, Samson Mataraso, Boris Oskotsky, Faith Myers, Philip Chung, Shabnam Gaskari, Marina Sirota, Yang Liu, David K. Stevenson, Lucas W Y Sin, Chi-Hung Shu, Taryn Ng, Courtney P Verscaj, Jennifer A Sequoia
article en
15 citations

Abstract

One in ten neonates are admitted to neonatal intensive care units, highlighting the need for precise interventions. However, the application of artificial intelligence (AI) in guiding neonatal care remains underexplored. Total parenteral nutrition (TPN) is a life-saving treatment for preterm neonates; however, implementation of the therapy in its current form is subjective, error-prone and resource-consuming. Here, we developed TPN2.0-a data-driven approach that optimizes and standardizes TPN using information collected routinely in electronic health records. We assembled a decade of TPN compositions (79,790 orders; 5,913 patients) at Stanford to train TPN2.0. In addition to internal validation, we also validated our model in an external cohort (63,273 orders; 3,417 patients) from a second hospital. Our algorithm identified 15 TPN formulas that can enable a precision-medicine approach (Pearson's R = 0.94 compared to experts), increasing safety and potentially reducing cost. A blinded study (n = 192) revealed that physicians rated TPN2.0 higher than current best practice. In patients with high disagreement between the actual prescriptions and TPN2.0, standard prescriptions were associated with increased morbidities (for example, odds ratio = 3.33; P value = 0.0007 for necrotizing enterocolitis), while TPN2.0 recommendations were linked to reduced risk. Finally, we demonstrated that TPN2.0 employing a transformer architecture enabled guideline-adhering, physician-in-the-loop recommendations that allow collaboration between the care team and AI.

Nature MedicineVol. 31(6)
Lucile Packard Children's Hospital (US), Children's Hospital of Los Angeles (US), University of California, San Francisco (US), Keck Hospital of USC (US), Stanford Medicine (US), Stanford University (US)
Zero hunger
Openalex Percentile: Top 0%
Neonatal Respiratory Health Research
22.78
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.