Frontiers in public health · 2026
ChatGPT-5 as a leisure health advisor: multidimensional assessment of reliability, quality, usefulness and readability.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Bayram Alican
Аннотация
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.
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.