Large Language Model-Driven Personalization of Virtual Reality Interventions to Improve Pediatric Inpatient Experience and Reduce Needle Anxiety

NCT07637617 | Not Yet Recruiting

• 1 other identifier: 87422
• Study Type: interventional
• Target: 20
• Locations: 0 countries
• Sites: N/A

Brief Summary

Hospitalization strips pediatric patients of the environments, objects, and people that shape their daily lives. Hospitalized pediatric patients routinely experience painful procedures, psychological distress, boredom, and a disorienting loss of personal identity. These experiences measurably worsen anxiety, reduce cooperation with care, and diminish the quality of the inpatient experience for both patients and families.1-7 Immersive digital interventions, including VR and tablet-based experiences, have emerged as a promising class of tools for addressing these challenges. Prior studies from The Stanford Chariot Program have demonstrated that digitally delivered, patient-centered experiences can meaningfully reduce procedural anxiety and improve engagement in hospitalized children.8-12 Yet, an important limitation persists in these technologies - current digital interventions largely remain in one-size-fits-all formats. Every child receives the same content, regardless of who they are, what they love, or what makes them feel at home in the world. This design limits therapeutic relevance, constrains engagement, and represents a missed opportunity to engage children, reduce anxiety, and enhance their quality of life during hospital stays.

Conditions

Large Language Model

Keywords

feasibility; acceptability; usability

Outcome Measures

Primary Outcomes (1)

• Determine the acceptability of the Large Language Model generated audiobook

  Semi-structured focus group interviews conducted in person immediately after intervention. Six core questions plus probing prompts assessing attitudes and opinions, and perceptions of the intervention experience

  Immediately after intervention

Study Arms (1)

Pediatric patient

EXPERIMENTAL

Behavioral: LLM-audiobook

Interventions

LLM-audiobook BEHAVIORAL

Develop and refine a two-stage personalization LLM pipeline: (1) a structured brief interview template and (2) an LLM prompt chain for content generation. The interview instrument will be a structured guide (\~20 minutes) capturing details about the child's background, interests, and aspirations. All information collected during the interview will be deidentified prior to being passed into the LLM. Content Generation: Deidentified interview responses will be input to a standardized LLM prompt pipeline. The pipeline generates a structured patient profile that interprets the participant's interests, personality, and preferences, then uses that profile to produce a personalized narrative, formatted as a picture book story. AI voice synthesis will generate an audio narration of the story. AI image generation tools will produce a set of 6-10 accompanying illustrations. The final product - a synchronized audio picture book - will be delivered via VR headset at bedside.

Pediatric patient

Eligibility Criteria

• Age: 11 Years - 17 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17)

You may qualify if:

• English-speaking patients admitted for ≥24 hours

You may not qualify if:

• Acute medical instability
• Contact or airborne isolation precautions (precluding shared device use)
• Vision or hearing impairment
• Severe cognitive or developmental impairment
• Active seizure disorder

Sponsors & Collaborators

• Stanford University: lead

Study Officials

• Samuel Rodriguez, MD

  Stanford University

  STUDY DIRECTOR

Central Study Contacts

Samuel Rodriguez, MD

CONTACT

650-723-5728; sr1@stanford.edu

ManYee Suen, MMedSc

CONTACT

650-723-5728; smy822@stanford.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: SUPPORTIVE CARE
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: June 3, 2026
• First Posted: June 10, 2026
• Study Start (Estimated): September 1, 2026
• Primary Completion (Estimated): August 31, 2027
• Study Completion (Estimated): August 31, 2027
• Last Updated: June 10, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share