Scalable, Clinician-Supervised Generative-AI Food-Chaining Assistant for Pediatric ARFID

NCT07006961 | Not Yet Recruiting

• 1 other identifier: IRB-P000051713
• Study Type: interventional
• Target: 125
• Locations: 0 countries
• Sites: N/A

Brief Summary

Children with Avoidant/Restrictive Food Intake Disorder (ARFID) often lack access to specialty dietitians, and scalable nutritional guidance/food chaining tools are currently not available. The investigators will evaluate a web-based, clinician-supervised, generative-AI assistant that produces individualized food-chaining plans. Develop an AI assistant that generates ≥15 allergy-safe, evidence-based chaining steps per participant and meets ≥90 % expert agreement for safety/appropriateness. Validate the assistant against gold-standard clinician recommendations (Cohen's κ ≥ 0.80). Test clinical impact in a three-month pilot RCT (n = 96) by comparing change in Nine-Item ARFID Screen (NIAS) scores between intervention and usual-care groups. Hypothesis: AI-generated plans will reduce NIAS scores by ≥3 points relative to controls.

Conditions

Avoidant Restrictive Food Intake Disorder

Keywords

ARFID; artificial intelligence; food chaining

Outcome Measures

Primary Outcomes (2)

• Nine Item ARFID Screen Score

  Nine Item ARFID Screen Score/NIAS Description: Individuals respond to each question on a scale from 0 (Strongly Disagree) to 5 (Strongly Agree). Subscales are each scored on a scale from 0-15, with higher scores indicating higher levels of each metric (picky eating, lack of interest, and fear). All items may also be summed to calculate a total score, ranging from 0-45, with higher scores indicating higher levels of avoidant/restrictive eating broadly. The investigators will assess the NIAS at the beginning of the intervention and then after four weeks of intervention and determine the difference (NIASΔ). A lower NIAS will be interpreted as improvement in ARFID symptoms.

  30 days

• Interventions Attempted

  Number of food chaining interventions attempted will be assessed. Success in the number of food chaining interventions that have led to introduction of a new food or a "lost" previously tolerated food will be assessed.

  30 days

Study Arms (2)

Intervention

EXPERIMENTAL

Arm 1 participants will be provided with 15 food chaining recommendations based on individual child dietary preferences, and will be assessed at the one month point to identify the number of food chaining interventions that have been undertaken and the number of recommendations that have been successful, along with a follow-up NIAS survey to determine differences in pre- and post-intervention ARFID severity. Arm 1 participants will exit the study at this point.

Other: Generative AI-based food chaining device

Control

NO INTERVENTION

Arm 2 participants at the time of enrollment will not be provided food chaining recommendations, but will be assessed at the one month point to identify the number of food chaining interventions/new foods that have been introduced, along with a follow-up NIAS survey to determine baseline ARFID severity. At the one month point, Arm 2 participants will be provided with 15 food chaining recommendations based on individual child dietary preferences, and will be assessed after one month to identify the number of food chaining interventions that have been undertaken and the number of recommendations that have been successful, along with a follow-up NIAS survey to determine differences in pre- and post-intervention ARFID severity. Arm 2 participants will exit the study at this point.

Interventions

Generative AI-based food chaining device OTHER

Our group has developed the only generative-AI tool that produces allergy-safe food-chaining recommendations, but it has not yet been clinically tested. This proposal builds on that proof of concept to evaluate its effectiveness in a broader pediatric ARFID population.

Intervention

Eligibility Criteria

• Age: 3 Years - 17 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17)

You may qualify if:

• Children must be aged 3-17 years
• Children must have caregiver- or participant-reported DSM-5 ARFID diagnosis and/or EDYQ-screen-positive Avoidant Restrictive Food Intake Disorder
• English proficiency.

You may not qualify if:

• Lack of English proficiency \[As there is no validated non-English version of the NIAS, we must exclude caregivers who do not have English proficiency\]
• Participants must not have been previously treated at Boston Children's for ARFID

Sponsors & Collaborators

• Boston Children's Hospital: lead

Related Publications (3)

• Fitzsimmons-Craft EE, Chan WW, Smith AC, Firebaugh ML, Fowler LA, Topooco N, DePietro B, Wilfley DE, Taylor CB, Jacobson NC. Effectiveness of a chatbot for eating disorders prevention: A randomized clinical trial. Int J Eat Disord. 2022 Mar;55(3):343-353. doi: 10.1002/eat.23662. Epub 2021 Dec 28.

  PMID: 35274362 BACKGROUND

• Sanchez-Cerezo J, Nagularaj L, Gledhill J, Nicholls D. What do we know about the epidemiology of avoidant/restrictive food intake disorder in children and adolescents? A systematic review of the literature. Eur Eat Disord Rev. 2023 Mar;31(2):226-246. doi: 10.1002/erv.2964. Epub 2022 Dec 16.

  PMID: 36527163 BACKGROUND

• Bialek-Dratwa A, Szymanska D, Grajek M, Krupa-Kotara K, Szczepanska E, Kowalski O. ARFID-Strategies for Dietary Management in Children. Nutrients. 2022 Apr 22;14(9):1739. doi: 10.3390/nu14091739.

  PMID: 35565707 BACKGROUND

Related Links

• News article on chatbot

MeSH Terms

Conditions

Avoidant Restrictive Food Intake Disorder

Condition Hierarchy (Ancestors)

Feeding and Eating Disorders; Mental Disorders

Central Study Contacts

PAUL CROWLEY, MD

CONTACT

16177106519; paul.crowley@childrens.harvard.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: TREATMENT
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Attending Gastroenterologist, Instructor in Pediatrics

Model Details: Arm 1 participants will be provided with 15 food chaining recommendations based on individual child dietary preferences, and will be assessed at the one month point to identify the number of food chaining interventions that have been undertaken and the number of recommendations that have been successful, along with a follow-up NIAS survey to determine differences in pre- and post-intervention ARFID severity. Arm 1 participants will exit the study at this point. Arm 2 participants at the time of enrollment will not be provided food chaining recommendations, but will be assessed at the one month point to identify the number of food chaining interventions/new foods that have been introduced, along with a follow-up NIAS survey to determine baseline ARFID severity. At the one month point, Arm 2 participants will be provided with 15 food chaining recommendations based on individual child dietary preferences, and will be assessed after one month to identify the number of food chaining interve

Study Record Dates

• First Submitted: May 28, 2025
• First Posted: June 5, 2025
• Study Start: June 15, 2025
• Primary Completion: October 31, 2025
• Study Completion: October 31, 2025
• Last Updated: June 6, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, CSR
• Time Frame: 1/1/2026 to 1/1/2032
• Access Criteria: Qualified researchers will have access to PHI-scrubbed data, including specific food-chaining recommendations, comorbid diagnoses, EDYQ and NIAS scores