ArticleFrontiers in public health2026
ChatGPT-5 as a leisure health advisor: multidimensional assessment of reliability, quality, usefulness and readability.
Article in Frontiers in public health, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
1 author.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: The demonstrated protective effects of leisure activities on physical and mental health underscore the need for accessible guidance. Large Language Models (LLMs) like ChatGPT-5 offer a potential solution, yet their application in non-clinical leisure health advice requires rigorous evaluation. This study aims to conduct a multidimensional assessment of ChatGPT-5's performance in this context. Method: We generated responses from ChatGPT-5 to 34 common leisure-and-health questions, categorized into six thematic areas (e.g., mental, physical, social health). The responses were assessed using validated evaluation instruments, including the modified DISCERN tool (mDISCERN) to determine reliability, the Global Quality Scale (GQS) to assess overall quality, and a 7-point Likert scale to evaluate perceived usefulness. Readability was assessed using the Flesch Reading Ease (FRE) formula. Results: ChatGPT-5 demonstrated moderate reliability, good quality, and relatively high usefulness, with mean scores of 3.58/5 for reliability (mDISCERN), 4.11/5 for quality (GQS), and 5.79/7 for usefulness. However, performance varied thematically, with the highest scores in "Leisure and Social Health" and the lowest in personalized contexts like "Age- and Stage-Appropriate Planning." A critical finding was the low average FRE score of 39, indicating a "difficult" reading level equivalent to U. S. college grades 13-16, which poses a significant accessibility barrier. Conclusion: While ChatGPT-5 shows promise as a complementary tool for generating leisure health advice, its utility is constrained by suboptimal readability, inconsistent source transparency, and limitations in handling nuanced, personalized scenarios. For safe and effective integration, future developments must prioritize readability optimization, enhanced source citation, and emotional intelligence, all within a framework that emphasizes human oversight.
Indexed as
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.