AI-guided IV nutrition for newborns in the NICU
Clinical Decision Support for Total Parenteral Nutrition Constituents in Neonatal Intensive Care Unit (NICU) Patients: A Pilot Study
This project will try an AI tool that suggests IV nutrition (TPN) for newborns in the NICU who cannot feed by mouth to see if it helps clinicians order the right formula more quickly and accurately.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 260 (estimated) |
| Ages | N/A to 6 Months |
| Sex | All |
| Sponsor | Takeoff41, Inc. Industry-sponsored |
| Locations | 1 site (Stanford, California) |
| Trial ID | NCT07414576 on ClinicalTrials.gov |
What this trial studies
This pilot deploys an AI-driven clinical decision support tool that suggests prebuilt TPN units for each infant based on daily labs, demographics, and decades of prior data; clinicians can accept, modify, or reject suggestions at any time. The main measure is how often physicians accept the AI recommendations, with secondary outcomes including time to complete TPN orders, weight z-score change, days on TPN, lab abnormalities, provider satisfaction, and a composite morbidity index of common preterm complications. The study plans to enroll about 260 neonates admitted to a participating NICU and will operate within usual care workflows to minimize disruption. The platform is provided by Takeoff41, Inc. in collaboration with Stanford University and will be used at Stanford's NICU site.
Who should consider this trial
Good fit: Newborns and infants up to about 6 months old admitted to a NICU who require total parenteral nutrition and receive daily laboratory testing are the intended participants.
Not a fit: Infants whose treating physicians judge the AI recommendations unsafe, those not receiving daily lab monitoring, or infants treated outside the participating NICU are unlikely to benefit from this pilot.
Why it matters
Potential benefit: If successful, the tool could reduce ordering errors, save clinician time, and help provide more consistent, individualized nutrition that may improve growth and reduce complications.
How similar studies have performed: AI clinical decision support has improved ordering efficiency in some other clinical areas, but AI-guided neonatal TPN is a novel application that has not been tested at scale.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Any newborns or infants requiring total parenteral nutrition in a neonatal ICU that performs daily laboratory tests * 6-month old at the time of admission * Any gestational age or birthweight * Any race or sex Exclusion Criteria: \- Infants deem unfit for the suggested TPN due to safety concerns by physicians
Where this trial is running
Stanford, California
- Stanford University — Stanford, California, United States (Recruiting)
Study contacts
- Principal investigator: David Stevenson, MD — Stanford University
- Study coordinator: Thanaphong Phongpreecha, PhD
- Email: joe@takeoff41.com
- Phone: 551-482-4827
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.