ORCID

0000-0002-8513-1573 (Zhang)

Document Type

Article

Publication Date

2026

DOI

10.1017/s1368980026101876

Publication Title

Public Health Nutrition

Volume

29

Issue

1

Pages

e32

Abstract

Objective:

To assess the feasibility of using large language models (LLMs) to develop research questions about changes to the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) food packages.

Design:

We conducted a controlled experiment using ChatGPT-4 and its plugin, MixerBox Scholarly, to generate research questions based on a section of the USDA summary of the final public comments on the WIC revision. Five questions weekly for three weeks were generated using LLMs under two conditions: fed with or without relevant literature. The experiment generated 90 questions, which were evaluated using the FINER criteria (Feasibility, Innovation, Novelty, Ethics, and Relevance). T-tests and multivariate regression examined the difference by feeding status, AI model, evaluator, and criterion.

Setting:

The United States.

Participants:

Six WIC expert evaluators from academia, government, industry, and non-profit sectors.

Results:

Five themes were identified: administrative barriers, nutrition outcomes, participant preferences, economics, and other topics. Feeding and non-feeding groups had no significant differences (Coeff. = 0.03, P = 0.52). MixerBox-generated questions received significantly lower scores than ChatGPT (Coeff. = -0.11, P = 0.02). Ethics scores were significantly higher than feasibility scores (Coeff. = 0.65, P < 0.001). Significant differences were found between the evaluators (P < 0.001).

Conclusions:

The LLM applications can assist in developing research questions with acceptable qualities related to the WIC food package revisions. Future research is needed to compare the development of research questions between LLMs and human researchers.

Rights

© The Authors, 2026

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.

Original Publication Citation

Zhang, Q., Neupane, B., Patel, P., Alkhalifah, F. N., He, Y., & Hodges, L. (2026). Large language model-assisted research question development in public health: A case study in the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC). Public Health Nutrition, 29(1), Article e32. https://doi.org/10.1017/s1368980026101876

Download

Share

COinS