Synthetic Validation of Pediatric Trust Instruments using Persona-Driven Large Language Models

Abstract

ABSTRACT Objectives Trust is foundational to patient-physician relationships and is associated with improved care-seeking and adherence in primary care. However, validated trust instruments for pediatric emergency and surgical contexts are lacking, and traditional instrument development is slow and resource-intensive. Large language models (LLMs) could streamline the validation process by serving as scalable, systematic expert panel surrogates. Materials and Methods We developed four new trust assessment instruments: two for patient-families and two for physicians. Two-phase content validation was conducted using two parallel synthetic and human expert panels. Synthetic panels consisted of three persona-prompted LLMs (Claude Sonnet 4, GPT-5, Grok4). Human panels served as traditional comparators. Scale-Content Validity Index (S-CVI) and Fleiss’ kappa (k) acceptance thresholds were set at ≥0.80. Results Combined human–synthetic expert panels revealed substantial inter-rater reliability across all instruments. Fleiss’ kvalues for dimensional validation were: patient-family = 0.84 (95% CI [0.72, 0.96]), physician = 0.87 (95% CI [0.72, 1.00]);contextual validation: patient-family = 0.83 (95% CI [0.73, 0.93]), physician = 0.88 (95% CI [0.80, 0.96]). All instruments exceeded S-CVI ≥0.80 thresholds across both validation phases. Discussion Persona-prompted LLMs demonstrated comparable validity outcomes to human experts while accelerating validation timelines from months to weeks. Future research needs to evaluate this approach across psychometric testing phases. Conclusion This synthetic instrument validation methodology offers a scalable blueprint for healthcare measurement development, enabling faster creation of validated tools to support evidence-based patient care.

Ähnliche Arbeiten