Evaluating ChatGPT’s Multilingual Performance in Clinical Nutrition Advice Using Synthetic Medical Text: Insights from Central Asia

This dataset comprises ChatGPT-generated nutritional recommendations and sample diet plans for 50 distinct patient profiles. Each case study represents the patient profile with sociocultural background of ethnic groups in Central Asia and provides comprehensive data on age, gender, cultural and medical history, dietary patterns, anthropometric characteristics, disease-related functional indicators, biochemical and hematological parameters, and lifestyle behaviors. The LLM outputs include general nutritional recommendations and individualized daily meal plans based on Central Asian foods for each profile. At the same time, we are providing codes for translation into local languages.In case of using our dataset, please cite our work: Adilmetova, G., Nassyrov, R., Meyerbekova, A., Karabay, A., Varol, H. A., & Chan, M. Y. (2025). Evaluating ChatGPT's Multilingual Performance in Clinical Nutrition Advice Using Synthetic Medical Text: Insights from Central Asia. The Journal of nutrition, 155(3), 729–735. https://doi.org/10.1016/j.tjnut.2024.12.018本数据集包含ChatGPT生成的、面向50例差异化患者画像的营养建议与膳食计划范本。 每一项案例研究均对应具备中亚族群社会文化背景的患者画像，并提供涵盖年龄、性别、文化背景与病史、饮食模式、人体测量学特征、疾病相关功能指标、生化与血液学参数以及生活方式行为等维度的完整数据。 大语言模型（LLM）的输出内容包含针对每位患者画像的通用营养建议，以及基于中亚本土食材制定的个性化每日膳食计划。 同时，本数据集附带可将内容翻译为当地语言的代码。 若使用本数据集，请引用如下文献：Adilmetova, G., Nassyrov, R., Meyerbekova, A., Karabay, A., Varol, H. A., & Chan, M. Y. (2025). 使用合成医疗文本评估ChatGPT在临床营养咨询中的多语言性能：来自中亚的研究启示. 《营养学杂志》, 155(3), 729–735. https://doi.org/10.1016/j.tjnut.2024.12.018