Previously submitted to: Journal of Medical Internet Research (no longer under consideration since May 26, 2025)
Date Submitted: Apr 29, 2025
Open Peer Review Period: Apr 30, 2025 - Jun 25, 2025
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Leveraging Large Language Models for Enhanced Quality Assessment of Nutrition and Health Dashboards
ABSTRACT
Background:
Data dashboards have become an essential tool in food and nutrition surveillance, enabling integration, visualization, and dissemination of multi-faceted data. While dashboards enhance data accessibility and decision-making, inconsistencies in data quality, standardization, and responsible conduct, along with misleading visualizations, limit their reliability and usefulness. Large Language Models (LLMs) could offer opportunities to assist in dashboard evaluation, yet their effectiveness compared to human expert assessments remains uncertain.
Objective:
In this study, we evaluate the potential of LLMs in assessing nutrition and health dashboards by comparing ChatGPT-generated evaluations with expert reviews. We examine the alignment and discrepancies in scoring across dashboards and key dashboard quality indicators.
Methods:
We developed a structured evaluation framework based on the 4E principles—Evidence, Efficiency, Emphasis, and Ethics—comprising 45 criteria. Seven publicly available nutrition and health dashboards were selected for evaluation. ChatGPT-4o was prompted to assess dashboards using extracted textual and visual content, generating scores and justifications for each criterion. Results were compared to previously published expert evaluations, analyzing ranking consistency and differences in dashboards and indicator-specific criteria.
Results:
ChatGPT-4o successfully generated scores and justifications in accordance with the instructions provided in the prompt we designed. ChatGPT-4o rankings were well aligned with expert evaluations for dashboards included in our study (Spearman correlation = 0.79). When comparing average scores across all dashboards for specific evaluation criteria, granularity and completeness had high consistency, with both AI and human experts assigning relatively lower scores. However, ChatGPT assigned lower scores for standardization and higher scores for responsible conduct compared to human experts.
Conclusions:
ChatGPT-4o could offer structured, scalable dashboard evaluations, showing reasonable alignment with expert assessments, especially in objective criteria like readability and accessibility. However, inconsistencies in assessing standardization, platform capability, and ethical considerations reveal limitations in contextual reasoning. While LLMs can enhance evaluation efficiency, expert oversight remains essential for accuracy and depth. Future research should explore diverse dashboards, compare multiple LLM models, and integrate multimodal capabilities to better assess interactivity and visualization integrity.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.