WU Danting,WANG Yan,HU Wen,et al.Application Management of Artificial Intelligence in Medical Nutrition Diet[J].Journal of Chengdu University of Information Technology,2025,40(05):619-625.[doi:10.16836/j.cnki.jcuit.2025.05.008]
人工智能在医疗膳食中的应用管理
- Title:
- Application Management of Artificial Intelligence in Medical Nutrition Diet
- 文章编号:
- 2096-1618(2025)05-0619-07
- Keywords:
- artificial intelligence; medical diet; large language model
- 分类号:
- TP182
- 文献标志码:
- A
- 摘要:
- 随着慢性疾病患病率的不断上升,科学合理的医疗膳食管理在疾病预防与治疗中的重要性日益显现。然而,传统的人工食谱构建方法存在效率低下、食谱营养成分与标准值之间的计算误差较大、个性化适配不足等问题。为解决这些问题,提出一种结合多目标优化算法与大语言模型的智能膳食管理系统。利用SLSQP算法动态优化食谱中的营养成分比例,确保碳水化合物、脂肪、蛋白质等核心营养素符合膳食营养参考摄入量(DRIs)标准,同时满足特定病理条件下对某些营养素的摄入限制,并将误差控制在目标值的0.9～1.2倍。此外,系统引入大语言模型作为自然语言交互接口,依托其强大的推理能力和垂域知识,并结合检索增强生成技术,综合考虑用户的宗教禁忌、过敏原、疾病特征等多重约束,显著提升食谱生成的个性化、科学性及可交互性,并为用户提供量身定制的膳食建议。结果表明,系统在满足DRIs标准的前提下,能够动态调整其他营养素的摄入限制,且其平均相对误差范围为8.5%～16.2%; 用户调查评估进一步验证该系统膳食方案的合理性与实用性。研究为AI技术在医疗营养领域的应用提供了新的路径,推动慢性病防控向智能化、精准化方向的发展。
- Abstract:
- With the increasing prevalence of chronic diseases,the importance of scientifically-based medical dietary management in disease prevention and treatment has become increasingly evident.However,traditional manual methods of recipe construction are inefficient and prone to significant calculation errors in the nutritional components of recipes when compared to standard values,as well as lacking sufficient personalization.To address these challenges,this study proposes an intelligent dietary management system that combines multi-objective optimization algorithms with large language models.The system uses the SLSQP algorithm to dynamically optimize the nutrient proportions in recipes,ensuring that core nutrients such as carbohydrates,fats,and proteins meet the Dietary Reference Intakes(DRIs)standards while also adhering to specific nutrient intake restrictions under certain pathological conditions,maintaining error within the range of 0.9 to 1.2 times the target values.Additionally,the system introduces a large language model as a natural language interface,leveraging its powerful reasoning capabilities and domain-specific knowledge,along with retrieval-augmented generation techniques,to comprehensively consider multiple constraints such as religious dietary prohibitions,allergens,and disease characteristics.This significantly enhances the personalization,scientific accuracy,and interactivity of the recipe generation,providing users with tailored dietary advice.Experimental results show that the system can dynamically adjust the intake limits of other nutrients while satisfying the DRIs standards,with an average relative error range of 8.5% to 16.2%.User surveys further confirm the rationality and practicality of the dietary plans generated by the system.This study provides a new pathway for the innovative application of AI technologies in the medical nutrition field,driving the development of intelligent and precision-driven chronic disease prevention and control.
参考文献/References:
[1] 世界卫生组织秘书处.饮食、体力活动与健康[R]. 日内瓦:世界卫生组织,2002.
[2] Cao H,Wang Y,Chen J,et al.Swin-unet:Unet-like pure transformer for medical image segmentation[C]. European Conference on Computer Vision.Cham:Springer Nature,2022:205-218.
[3] Koleilat T,Asgariandehkordi H,Rivaz H,et al.Medclip-sam:Bridging text and image towards universal medical image segmentation[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham:Springer Nature,2024:643-653.
[4] 覃伟,高敏,沈莹,等.基于机器学习算法的2型糖尿病患者3个月血糖预测[J]. 中华疾病控制杂志,2019; 23(11):1313-1317.
[5] Zhang H,Chen J,Jiang F,et al.HuatuoGPT,towards taming language model to be a doctor[C]. Findings of the Association for Computational Linguistics.Singapore:EMNLP,2023:10859-10885.
[6] Kraft D.A software package for sequential quadratic programming[R]. Deutsche Forschungs- und Versuchsanstalt für Luft- und Raumfahrt Köln,1988.
[7] 中国营养学会.中国居民膳食指南:2022[M]. 北京:人民卫生出版社,2022:1-305.
[8] Achiam J,Adler S,Agarwal S,et al.Gpt-4 technical report[J]. arXiv preprint arXiv:2303.08774,2023.
[9] Broyden C G,Fletcher R,Goldfarb D,et al.A class of methods for solving nonlinear simultaneous equations[C]. Proceedings of the 2nd International Conference on Optimization Techniques.London:Academic Press,1970:1-10.
[10] Yang A,Yang B,Zhang B,et al.Qwen2.5 technical report[J]. arXiv preprint arXiv:2412.15115,2024.
[11] Liu A,Feng B,Xue B,et al.Deepseek-v3 technical report[J]. arXiv preprint arXiv:2412.19437,2024.
[12] Devlin J,Chang M W,Lee K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C]. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics.Minneapolis:Association for Computational Linguistics,2019:4171-4186.
[13] Liu Y,Ott M,Goyal N,et al.RoBERTa:A robustly optimized BERT pretraining approach[C]. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg:Association for Computational Linguistics,2019:1-10.
[14] Radford A,Wu J,Child R,et al.Language models are unsupervised multitask learners[J]. OpenAI blog,2019,1(8):9.
[15] Brown T,Mann B,Ryder N,et al.Language models are few-shot learners[C]. Advances in Neural Information Processing Systems(NeurIPS).Vancouver:MIT Press,2020:1877-1901.
[16] Hu E,Peng X,Li Z,et al.LoRA:Low-Rank Adaptation of Large Language Models[C]. Proceedings of the 39th International Conference on Machine Learning(ICML).Baltimore:PMLR,2022:12743-12757.
[17] Loshchilov I,Hutter F.Decoupled Weight Decay Regularization[C]. Proceedings of the 7th International Conference on Learning Representations(ICLR).New Orleans:ICLR,2019:1-12.
[18] Lewis P,Oguz B,Liu Y,et al.Retrieval-augmented generation for knowledge-intensive NLP tasks[C]. Proceedings of the 38th International Conference on Machine Learning(ICML).Vienna:PMLR,2021:9385-9396.
相似文献/References:
[1]王 强,李孝杰,陈 俊.基于He-Net的卷积神经网络算法的图像分类研究[J].成都信息工程大学学报,2017,(05):503.[doi:10.16836/j.cnki.jcuit.2017.05.007]
WANG Qing,LI Xiao-jie,CHEN Jun.Research on Image Classification based on HE-Net Convolutional Neural Networks[J].Journal of Chengdu University of Information Technology,2017,(05):503.[doi:10.16836/j.cnki.jcuit.2017.05.007]
[2]禹政阳,陈 军,江明桦,等.基于瓦片重叠法的在线高分遥感图像目标智能提取方法研究[J].成都信息工程大学学报,2022,37(05):520.[doi:10.16836/j.cnki.jcuit.2022.05.006]
YU Zhengyang,CHEN Jun,JIANG Minghua,et al.Research on Intelligent Extraction Method of Spatial Objects from Online High-Resolution Remote Sensing Images based on Tile-overlapping Strategy[J].Journal of Chengdu University of Information Technology,2022,37(05):520.[doi:10.16836/j.cnki.jcuit.2022.05.006]
备注/Memo
收稿日期:2025-07-05
通信作者:饶志勇.E-mail:raozhiyong@scu.edu.cn