AI-driven Total Parenteral Nutrition Platform

NCT07414576 | Recruiting DMC

• 1 other identifier: 74413
• Study Type: interventional
• Target: 260
• Locations: 1 country
• Sites: 1

Brief Summary

This study tests whether an artificial intelligence (AI) tool can help doctors order total parenteral nutrition (TPN) for babies in the neonatal intensive care unit (NICU). Premature babies often cannot eat by mouth and need nutrition delivered through an IV. Ordering TPN is complex, time-consuming, and mistakes can happen. This study will test an AI tool that suggests TPN formulas to doctors based on each baby's lab values and health information. Doctors can accept, change, or reject the suggestions at any time. The main goal is to measure how often doctors accept the AI suggestions. The study will also track time to complete TPN orders, weight changes, days on TPN, whether lab values stay in normal ranges, provider satisfaction, and baby health outcomes including complications such as lung disease, brain bleeding, infections, and other conditions common in premature babies. Babies admitted to the NICU who need TPN may participate if their doctors agree to use the tool. Each baby will be in the study while they need TPN, typically about 14 days. The AI tool only makes suggestions and does not replace doctor decision-making. All other care remains the same as standard practice.

Conditions

Intestinal Failure

Keywords

parenteral nutrition

Outcome Measures

Primary Outcomes (1)

• System Acceptance Rate

  Percentage of AI-generated recommendations that are accepted or modified by providers for each ingredient of TPN. Measured by retrospective comparison between AI suggestion and actual TPN order submitted.

  10 months

Secondary Outcomes (4)

• Change in Weight Z-Score

  10 months

• Days on TPN

  10 months

• Composite Clinical Outcome

  13 months

• Rate of Laboratory Value Abnormalities

  10 months

Other Outcomes (1)

• Provider Satisfaction

  10 months

Study Arms (2)

Standard TPN Ordering (Control)

NO INTERVENTION

Patients admitted during Period 1. Providers use current standard TPN ordering practice without AI assistance. Serves as baseline comparison.

AI-driven total parenteral nutrition (TPN)

EXPERIMENTAL

Patients admitted during Period 2. Providers use the AI-assisted TPN decision support tool integrated with Epic to order TPN. Providers may opt out and use traditional ordering if needed.

Device: AI-driven total parenteral nutrition (TPN)

Interventions

AI-driven total parenteral nutrition (TPN) DEVICE

An AI-driven clinical decision support (CDS) software integrated with EHR system that provides TPN composition recommendations to NICU providers. The tool uses patient lab values, basic profile (days since birth, weight, gestational age), and physician inputs to suggest TPN components. Providers can accept, modify, or decline if needed. The final prescribing authority remains with the providers. The intervention targets provider workflow efficiency while maintaining precision and equivalent patient outcomes (including labs and long-term adverse outcomes).

AI-driven total parenteral nutrition (TPN)

Eligibility Criteria

• Age: Up to 6 Months
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17)

You may qualify if:

• Any newborns or infants requiring total parenteral nutrition in a neonatal ICU that performs daily laboratory tests
• month old at the time of admission
• Any gestational age or birthweight
• Any race or sex

You may not qualify if:

• \- Infants deem unfit for the suggested TPN due to safety concerns by physicians

Sponsors & Collaborators

• Takeoff41, Inc.: lead
• Stanford University: collaborator

Study Sites (1)

Stanford University

Stanford, California, 94305, United States

RECRUITING

MeSH Terms

Conditions

Intestinal Failure; Hyperphagia

Condition Hierarchy (Ancestors)

Intestinal Diseases; Gastrointestinal Diseases; Digestive System Diseases; Signs and Symptoms, Digestive; Signs and Symptoms; Pathological Conditions, Signs and Symptoms

Study Officials

• David Stevenson, MD

  Stanford University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Thanaphong Phongpreecha, PhD

CONTACT

551-482-4827; joe@takeoff41.com

Chandra Vikram, Bachelor

CONTACT

317-724-2159; chandra101@takeoff41.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: SEQUENTIAL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Model Details: Single-arm sequential design. Patients (participants) are assigned to one arm based on their admission timing: those admitted during Period 1 (first half of the study) receive care from providers using standard TPN ordering, while those admitted during Period 2 (second half) receive care from providers using AI-assisted ordering. Since the average patient stay is \~14 days, patients are exposed to only one condition. A sequential design is necessary because in the NICUs each patient is cared for by multiple rotating providers depending on the day of the week and shift coverage, making parallel randomization impractical-if some providers had AI assistance while others did not, the same patient could receive inconsistent care. This design ensures uniform exposure within each period.

Study Record Dates

• First Submitted: January 28, 2026
• First Posted: February 17, 2026
• Study Start: January 21, 2026
• Primary Completion (Estimated): February 21, 2027
• Study Completion (Estimated): February 21, 2027
• Last Updated: February 17, 2026

Record last verified: 2026-01

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)