生成式人工智能在体重管理中的应用进展

doi:10.12114/j.issn.1007-9572.2025.0308

摘要/Abstract

摘要： 体重管理是慢性病防控的重要环节。国家卫生健康委员会于2024年启动为期3年的"体重管理年"行动计划（2025—2027年），旨在提升全民体重管理意识并推广科学的体重控制方法。体重管理不仅关注体重数值，更强调通过饮食、运动和生活习惯的综合干预，以预防慢性病、提升生活质量。生成式人工智能在体重管理领域展示出巨大潜力，可为用户提供个性化的饮食建议、运动方案及行为干预，从而提升管理效果与依从性。本文系统探讨生成式人工智能在体重管理中的应用路径与实效，指出其在实现饮食方案动态个性化、提升身体活动水平等方面具有优势，同时也面临内容真实性、隐私安全、算法偏见及长期依从性等多重挑战。本文可为我国体重管理模式的优化与生成式人工智能在健康领域的深入应用提供参考。

关键词: 体重, 肥胖症, 体重管理, 生成式人工智能, 聊天机器人, 应用进展

Abstract:

Weight management serves as a critical component in the prevention and control of chronic diseases. In 2024, the National Health Commission of China launched a three-year "Weight Management Year" action plan (2025-2027), aiming to enhance public awareness of weight management and promote scientific control methods. Weight management not only focuses on body weight values but also emphasizes comprehensive interventions in diet, physical activity, and lifestyle to prevent chronic diseases and improve quality of life. Generative artificial intelligence demonstrates significant potential in the field of weight management by providing users with personalized dietary advice, exercise plans, and behavioral interventions, thereby improving management outcomes and adherence. This article systematically explores the application pathways and effectiveness of generative artificial intelligence in weight management, highlighting its advantages in achieving dynamic personalization of dietary plans and increasing physical activity levels, while also addressing multiple challenges such as content authenticity, data privacy, algorithmic biases, and long-term adherence. This study provides valuable insights for the optimization of weight management models in China and the further application of generative artificial intelligence in the health domain.

Key words: Body weight, Obesity, Weight management, Generative artificial intelligence, Chatbots, Application progress

中图分类号:

R 194.3

杨蕾,关华. 生成式人工智能在体重管理中的应用进展[J]. 中国全科医学, 2026, 29(12): 1533-1540. DOI: 10.12114/j.issn.1007-9572.2025.0308.
YANG Lei,GUAN Hua. Application Progress of Generative Artificial Intelligence in Weight Management[J]. Chinese General Practice, 2026, 29(12): 1533-1540. DOI: 10.12114/j.issn.1007-9572.2025.0308.

图/表 2

参考文献 75

[1]	Obesity and overweight[EB/OL]. (2024-03-01)[2025-03-19].
[2]	中国居民营养与慢性病状况报告(2020年)[J]. 营养学报, 2020, 42(6): 521.
[3]	RCHEN Z, IONA A, PARISH S, et al. Adiposity and risk of ischaemic and haemorrhagic stroke in 0.5 million Chinese men and women: a prospective cohort study[J]. Lancet Glob Health, 2018, 6(6): e630-e640. DOI: 10.1016/S2214-109X(18)30216-X.
[4]	MI B B, WU C L, GAO X Y, et al. Long-term BMI change trajectories in Chinese adults and its association with the hazard of type 2 diabetes: evidence from a 20-year China Health and Nutrition Survey[J]. BMJ Open Diabetes Res Care, 2020, 8(1): e000879. DOI: 10.1136/bmjdrc-2019-000879.
[5]	PANG Y, KARTSONAKI C, GUO Y, et al. Adiposity and risks of colorectal and small intestine cancer in Chinese adults: a prospective study of 0.5 million people[J]. Br J Cancer, 2018, 119(2): 248-250. DOI: 10.1038/s41416-018-0124-8.
[6]	SILVA D A, COUTINHO E, FERRIANI L O, et al. Depression subtypes and obesity in adults: a systematic review and meta-analysis[J]. Obes Rev, 2020, 21(3): e12966. DOI: 10.1111/obr.12966.
[7]	JOHNS D J, HARTMANN-BOYCE J, JEBB S A, et al. Diet or exercise interventions vs combined behavioral weight management programs: a systematic review and meta-analysis of direct comparisons[J]. J Acad Nutr Diet, 2014, 114(10): 1557-1568. DOI: 10.1016/j.jand.2014.07.005.
[8]	MIRKARIMI K, KABIR M J, HONARVAR M R, et al. Effect of motivational interviewing on weight efficacy lifestyle among women with overweight and obesity: a randomized controlled trial[J]. Iran J Med Sci, 2017, 42(2): 187-193.
[9]	CHEW H S J, KOH W L, NG J S H Y, et al. Sustainability of weight loss through smartphone apps: systematic review and meta-analysis on anthropometric, metabolic, and dietary outcomes[J]. J Med Internet Res, 2022, 24(9): e40141. DOI: 10.2196/40141.
[10]	CLARKE B, KWON J, SWINBURN B, et al. Understanding the dynamics of obesity prevention policy decision-making using a systems perspective: a case study of Healthy Together Victoria[J]. PLoS One, 2021, 16(1): e0245535. DOI: 10.1371/journal.pone.0245535.
[11]	生成式人工智能服务管理暂行办法[EB/OL]. (2023-08-15)[2025-05-11].
[12]	刘雪, 颜巧元, 周幺玲, 等. 数字疗法用于慢性病管理的研究进展[J]. 护理学杂志, 2023, 38(11): 122-126.
[13]	WACHTER R M, BRYNJOLFSSON E. Will generative artificial intelligence deliver on its promise in health care [J]. JAMA, 2024, 331(1): 65-69. DOI: 10.1001/jama.2023.25054.
[14]	GIBNEY E. China's cheap, open AI model DeepSeek thrills scientists[J]. Nature, 2025, 638(8049): 13-14. DOI: 10.1038/d41586-025-00229-6.
[15]	CONROY G, MALLAPATY S. How China created AI model DeepSeek and shocked the world[J]. Nature, 2025, 638(8050): 300-301. DOI: 10.1038/d41586-025-00259-0.
[16]	郭亚军, 徐苑茜, 梁艳丽, 等. 从ChatGPT到DeepSeek:生成式人工智能迭代对图书馆的影响[J]. 图书馆论坛, 2024. [2025-11-12]. https://doi.org/10.13266/j.issn.1002-1167.20241231.001.
[17]	THIRUNAVUKARASU A J, TING D S J, ELANGOVAN K, et al. Large language models in medicine[J]. Nat Med, 2023, 29(8): 1930-1940. DOI: 10.1038/s41591-023-02448-8.
[18]	KIM T W. Application of artificial intelligence chatbots, including ChatGPT, in education, scholarly work, programming, and content generation and its prospects: a narrative review[J]. J Educ Eval Health Prof, 2023, 20: 38. DOI: 10.3352/jeehp.2023.20.38.
[19]	MADANI A, KRAUSE B, GREENE E R, et al. Large language models generate functional protein sequences across diverse families[J]. Nat Biotechnol, 2023, 41(8): 1099-1106. DOI: 10.1038/s41587-022-01618-2.
[20]	HUANG L Y, HU J H, CAI Q J, et al. The performance evaluation of artificial intelligence ERNIE bot in Chinese National Medical Licensing Examination[J]. Postgrad Med J, 2024, 100(1190): 952-953. DOI: 10.1093/postmj/qgae062.
[21]	SHANG L X, XUE M Y, HOU Y L, et al. Can ChatGPT pass China's national medical licensing examination[J]. Asian J Surg, 2023, 46(12): 6112-6113. DOI: 10.1016/j.asjsur.2023.09.089.
[22]	LAI U H, WU K S, HSU T Y, et al. Evaluating the performance of ChatGPT-4 on the United Kingdom medical licensing assessment[J]. Front Med (Lausanne), 2023, 10: 1240915. DOI: 10.3389/fmed.2023.1240915.
[23]	BARLAS T, ALTINOVA A E, AKTURK M, et al. Credibility of ChatGPT in the assessment of obesity in type 2 diabetes according to the guidelines[J]. Int J Obes(Lond), 2024, 48(2): 271-275. DOI: 10.1038/s41366-023-01410-5.
[24]	CHEONG R C T, UNADKAT S, MCNEILLIS V, et al. Artificial intelligence chatbots as sources of patient education material for obstructive sleep apnoea: ChatGPT versus Google Bard[J]. Eur Arch Otorhinolaryngol, 2024, 281(2): 985-993. DOI: 10.1007/s00405-023-08319-9.
[25]	AI赋能检验医学,提升智能化诊断能力[EB/OL]. (2025-02-17)[2025-05-11].
[26]	全球首个体重管理AI大模型发布[EB/OL]. (2025-03-23)[2025-07-31].
[27]	南晶, 李淑娟, 郭齐雅, 等. 成人中心型肥胖流行状况及健康影响[J]. 卫生研究, 2025, 54(1): 141-147, 174. DOI: 10.19813/j.cnki.weishengyanjiu.2025.01.025.
[28]	CHEN Y, GUO Y D, FAN Q X, et al. Health-aware food recommendation based on knowledge graph and multi-task learning[J]. Foods, 2023, 12(10): 2079. DOI: 10.3390/foods12102079.
[29]	MA W M, LI M Q, DAI J, et al. Nutrition-related knowledge graph neural network for food recommendation[J]. Foods, 2024, 13(13): 2144. DOI: 10.3390/foods13132144.
[30]	李楠, 简钰轩, 闭祖松, 等. 智能冰箱推荐系统设计[J]. 物联网技术, 2022, 12(12): 125-126. DOI: 10.16667/j.issn.2095-1302.2022.12.036.
[31]	陈育康. 基于深度学习的健身者饮食推荐算法研究与应用[D]. 贵阳: 贵州大学, 2022. DOI: 10.27047/d.cnki.ggudu.2022.001004.
[32]	OH Y J, ZHANG J W, FANG M L, et al. A systematic review of artificial intelligence chatbots for promoting physical activity, healthy diet, and weight loss[J]. Int J Behav Nutr Phys Act, 2021, 18(1): 160. DOI: 10.1186/s12966-021-01224-6.
[33]	HUANG C Y, YANG M C, HUANG C, et al. A chatbot-supported smart wireless interactive healthcare system for weight control and health promotion[C]//2018 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM). December 16-19, 2018, Bangkok, Thailand. IEEE, 2018: 1791-1795. DOI: 10.1109/IEEM.2018.8607399.
[34]	ASENSIO-CUESTA S, BLANES-SELVA V, CONEJERO J A, et al. A user-centered chatbot (wakamola) to collect linked data in population networks to support studies of overweight and obesity causes: design and pilot study[J]. JMIR Med Inform, 2021, 9(4): e17503. DOI: 10.2196/17503.
[35]	MOSCHONIS G, TRAKMAN G L. Overweight and obesity: the interplay of eating habits and physical activity[J]. Nutrients, 2023, 15(13): 2896. DOI: 10.3390/nu15132896.
[36]	AN R P, SHEN J, WANG J J, et al. A scoping review of methodologies for applying artificial intelligence to physical activity interventions[J]. J Sport Health Sci, 2024, 13(3): 428-441. DOI: 10.1016/j.jshs.2023.09.010.
[37]	HAN R, TODD A, WARDAK S, et al. Feasibility and acceptability of chatbots for nutrition and physical activity health promotion among adolescents: systematic scoping review with adolescent consultation[J]. JMIR Hum Factors, 2023, 10: e43227. DOI: 10.2196/43227.
[38]	AGGARWAL A, TAM C C, WU D Z, et al. Artificial intelligence-based chatbots for promoting health behavioral changes: systematic review[J]. J Med Internet Res, 2023, 25: e40789. DOI: 10.2196/40789.
[39]	STEIN N, BROOKS K. A fully automated conversational artificial intelligence for weight loss: longitudinal observational study among overweight and obese adults[J]. JMIR Diabetes, 2017, 2(2): e28. DOI: 10.2196/diabetes.8590.
[40]	MAHER C A, DAVIS C R, CURTIS R G, et al. A physical activity and diet program delivered by artificially intelligent virtual health coach: proof-of-concept study[J]. JMIR Mhealth Uhealth, 2020, 8(7): e17558. DOI: 10.2196/17558.
[41]	PIAO M H, RYU H, LEE H, et al. Use of the healthy lifestyle coaching chatbot app to promote stair-climbing habits among office workers: exploratory randomized controlled trial[J]. JMIR Mhealth Uhealth, 2020, 8(5): e15085. DOI: 10.2196/15085.
[42]	TO Q G, GREEN C, VANDELANOTTE C. Feasibility, usability, and effectiveness of a machine learning-based physical activity chatbot: quasi-experimental study[J]. JMIR Mhealth Uhealth, 2021, 9(11): e28577. DOI: 10.2196/28577.
[43]	HERMES E D, LYON A R, SCHUELLER S M, et al. Measuring the implementation of behavioral intervention technologies: recharacterization of established outcomes[J]. J Med Internet Res, 2019, 21(1): e11752. DOI: 10.2196/11752.
[44]	STEPHENS T N, JOERIN A, RAUWS M, et al. Feasibility of pediatric obesity and prediabetes treatment support through Tess, the AI behavioral coaching chatbot[J]. Transl Behav Med, 2019, 9(3): 440-447. DOI: 10.1093/tbm/ibz043.
[45]	WESTBURY S, OYEBODE O, VAN RENS T, et al. Obesity stigma: causes, consequences, and potential solutions[J]. Curr Obes Rep, 2023, 12(1): 10-23. DOI: 10.1007/s13679-023-00495-3.
[46]	Diabetes Prevention Program Research Group. Long-term effects of lifestyle intervention or metformin on diabetes development and microvascular complications over 15-year follow-up: the Diabetes Prevention Program Outcomes Study[J]. Lancet Diabetes Endocrinol, 2015, 3(11): 866-875. DOI: 10.1016/S2213-8587(15)00291-0.
[47]	HOLMES S, MOORHEAD A, BOND R, et al. WeightMentor, bespoke chatbot for weight loss maintenance: needs assessment & development[C]//2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). San Diego, CA, USA. IEEE, 2019: 2845-2851. DOI: 10.1109/BIBM47256.2019.8983073.
[48]	HABICHT J, DINA L M, MCFADYEN J, et al. Generative AI-enabled therapy support tool for improved clinical outcomes and patient engagement in group therapy: real-world observational study[J]. J Med Internet Res, 2025, 27: e60435. DOI: 10.2196/60435.
[49]	XUE J, ZHANG B L, ZHAO Y X, et al. Evaluation of the current state of chatbots for digital health: scoping review[J]. J Med Internet Res, 2023, 25: e47217. DOI: 10.2196/47217.
[50]	DEMSZKY D, YANG D Y, YEAGER D S, et al. Using large language models in psychology[J]. Nat Rev Psychol, 2023, 2(11): 688-701. DOI: 10.1038/s44159-023-00241-5.
[51]	林曦. 人工智能"幻觉"的存在主义阐释[J]. 社会科学辑刊, 2025(2): 81-91.
[52]	RAY P P, MAJUMDER P. Assessing the accuracy of responses by the language model ChatGPT to questions regarding bariatric surgery: a critical appraisal[J]. Obes Surg, 2023, 33(8): 2588-2589. DOI: 10.1007/s11695-023-06664-6.
[53]	YEO Y H, SAMAAN J S, NG W H, et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma[J]. Clin Mol Hepatol, 2023, 29(3): 721-732. DOI: 10.3350/cmh.2023.0089.
[54]	TOPOL E J. High-performance medicine: the convergence of human and artificial intelligence[J]. Nat Med, 2019, 25(1): 44-56. DOI: 10.1038/s41591-018-0300-7.
[55]	宗绍昊, 罗世龙. DeepSeek类生成式人工智能的新型数据安全风险治理[J/OL]. 科学学研究, 2025.[2025-07-30].
[56]	NGIAM K Y, KHOR I W. Big data and machine learning algorithms for health-care delivery[J]. Lancet Oncol, 2019, 20(5): e262-e273. DOI: 10.1016/S1470-2045(19)30149-4.
[57]	RACINE E, BOEHLEN W, SAMPLE M. Healthcare uses of artificial intelligence: challenges and opportunities for growth[J]. Healthc Manage Forum, 2019, 32(5): 272-275. DOI: 10.1177/0840470419843831.
[58]	HU Y P, KUANG W X, QIN Z, et al. Artificial intelligence security: threats and countermeasures[J]. ACM Comput Surv, 2023, 55(1): 1-36. DOI: 10.1145/3487890.
[59]	KIM B N, DOLZ J, JODOIN P M, et al. Privacy-net: an adversarial approach for identity-obfuscated segmentation of medical images[J]. IEEE Trans Med Imaging, 2021, 40(7): 1737-1749. DOI: 10.1109/TMI.2021.3065727.
[60]	LI J, CAIRNS B J, LI J S, et al. Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications[J]. NPJ Digit Med, 2023, 6(1): 98. DOI: 10.1038/s41746-023-00834-7.
[61]	MORLEY J, MACHADO C C V, BURR C, et al. The ethics of AI in health care: a mapping review[J]. Soc Sci Med, 2020, 260: 113172. DOI: 10.1016/j.socscimed.2020.113172.
[62]	王绍源, 李梦. 从ChatGPT4.0到DeepSeek-R1:人工智能在医疗卫生领域应用的革新场景和伦理治理范式转变[J/OL]. 中国医学伦理学.[2025-11-12].
[63]	AICARDI C, DEL SAVIO L, DOVE E S, et al. Emerging ethical issues regarding digital health data. On the world medical association draft declaration on ethical considerations regarding health databases and biobanks[J]. Croat Med J, 2016, 57(2): 207-213. DOI: 10.325/cmj.2016.57.207.
[64]	GREAVES F, JOSHI I, CAMPBELL M, et al. What is an appropriate level of evidence for a digital health intervention[J]. Lancet, 2019, 392(10165): 2665-2667. DOI: 10.1016/S0140-6736(18)33129-5.
[65]	WANG Z. Data integration of electronic medical record under administrative decentralization of medical insurance and healthcare in China: a case study[J]. Isr J Health Policy Res, 2019, 8(1): 24. DOI: 10.1186/s13584-019-0293-9.
[66]	KORDZADEH N, GHASEMAGHAEI M. Algorithmic bias: review, synthesis, and future research directions[J]. Eur J Inf Syst, 2022, 31(3): 388-409. DOI: 10.1080/0960085x.2021.1927212.
[67]	车万翔, 窦志成, 冯岩松, 等. 大模型时代的自然语言处理:挑战、机遇与发展[J]. 中国科学:信息科学, 2023, 53(9): 1645-1687.
[68]	GARATTINI C, RAFFLE J, AISYAH D N, et al. Big data analytics, infectious diseases and associated ethical impacts[J]. Philos Technol, 2019, 32(1): 69-85. DOI: 10.1007/s13347-017-0278-y.
[69]	Fitbits and other wearables may not accurately track heart rates in people of color[EB/OL]. (2019-07-24)[2025-06-08].
[70]	Ethics and governance of artificial intelligence for health[EB/OL]. (2021-09-28)[2025-07-31].
[71]	DREW R J, MORGAN P J, COLLINS C E, et al. Behavioral and cognitive outcomes of an online weight loss program for men with low mood: a randomized controlled trial[J]. Ann Behav Med, 2022, 56(10): 1026-1041. DOI: 10.1093/abm/kaab109.
[72]	AMIRI S, BEHNEZHAD S. Obesity and anxiety symptoms: a systematic review and meta-analysis[J]. neuropsychiatrie, 2019, 33(2): 72-89. DOI: 10.1007/s40211-019-0302-9.
[73]	BURGESS E, HASSMÉN P, WELVAERT M, et al. Behavioural treatment strategies improve adherence to lifestyle intervention programmes in adults with obesity: a systematic review and meta-analysis[J]. Clin Obes, 2017, 7(2): 105-114. DOI: 10.1111/cob.12180.
[74]	FITZPATRICK K K, DARCY A, VIERHILE M. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (woebot): a randomized controlled trial[J]. JMIR Ment Health, 2017, 4(2): e19. DOI: 10.2196/mental.7785.
[75]	KALMADY S V, GREINER R, AGRAWAL R, et al. Towards artificial intelligence in mental health by improving schizophrenia prediction with multiple brain parcellation ensemble-learning[J]. NPJ Schizophr, 2019, 5: 2. DOI: 10.1038/s41537-018-0070-8.

第一作者（年份）	国家/地区	研究目的	研究对象	样本量（例）	年龄（岁）	性别（女/男）	BMI（±s，kg/m²）/体重（±s，kg）	输入输出形式	AI语言	是否加入可穿戴设备或物联网	技术载体
ASENSIO-CUESTA（2021）^[34]	西班牙	设计以用户为中心的肥胖数据，收集聊天机器人Wakamola，支持社交网络分析	大学生	74	20.7	54/20	BMI：21.4±2.4	文本	西班牙语、英语、加泰罗尼亚语	否	Telegram聊天机器人
HUANG（2018）^[33]	中国台湾	开发智能无线医疗系统SWITCHes，结合人工智能聊天机器人实现个性化体重管理	超重或肥胖人群	未报告	未报告	未报告	未报告	文本、语音	中文、英语	是	智能手机
HOLMES（2019）^[47]	英国	开发体重管理聊天机器人Weight Mentor，提供个性化反馈与激励	减肥反弹的成年人	15	41.9±11.6	8/7	BMI：27.6±6.9	文本	英语	否	智能手机/平板/电脑
STEIN（2017）^[39]	美国	评估人工智能健康教练Lark HCAI对肥胖成人的减重效果、饮食质量与用户接受度	超重和肥胖的成年人	70	46.9±15.8	35/12^a	BMI：37.0±1.4	文本	英语	是	智能手机
STEPHENS（2019）^[44]	美国	评估人工智能聊天机器人Tess辅助治疗儿童肥胖及前驱糖尿病的可行性	肥胖儿童及青少年	23	15.2±3.4	13/10	未报告	文本	英语	否	Facebook Messenger/SMS
TO（2021）^[42]	澳大利亚	评估机器学习驱动的身体活动聊天机器人的可行性、可用性与有效性	不活跃的成年人	116	49.1±9.3	95/21	BMI：32.5±8.0	文本	英语	是	Facebook Messenger
PIAO（2020）^[41]	韩国	评估聊天机器人健康干预对上班族爬楼梯习惯的促进作用	办公室职员	106	未明确报告	干预组：32/25；对照组：28/21	干预组体重：64.2±14.1；对照组体重：64.5±14.1	文本、图像	韩语	否	KakaoTalk聊天机器人
MAHER（2020）^[40]	澳大利亚	评估人工智能健康教练Paola实施身体活动与饮食干预的可行性及初步效果	缺乏身体活动的成年人	31	56.2±8.0	21/10	体重：83.6±19.0	文本、图像	英语	是	Slack平台
BARLAS（2023）^[23]	土耳其	评估ChatGPT在2型糖尿病肥胖评估中的可信度	ChatGPT-3.5	20个体重管理问题	不涉及	不涉及	不涉及	文本	英语	否	ChatGPT-3.5

第一作者（年份）	国家/地区	研究目的	研究对象	样本量（例）	年龄（岁）	性别（女/男）	BMI（±s，kg/m²）/体重（±s，kg）	输入输出形式	AI语言	是否加入可穿戴设备或物联网	技术载体
ASENSIO-CUESTA（2021）^[34]	西班牙	设计以用户为中心的肥胖数据，收集聊天机器人Wakamola，支持社交网络分析	大学生	74	20.7	54/20	BMI：21.4±2.4	文本	西班牙语、英语、加泰罗尼亚语	否	Telegram聊天机器人
HUANG（2018）^[33]	中国台湾	开发智能无线医疗系统SWITCHes，结合人工智能聊天机器人实现个性化体重管理	超重或肥胖人群	未报告	未报告	未报告	未报告	文本、语音	中文、英语	是	智能手机
HOLMES（2019）^[47]	英国	开发体重管理聊天机器人Weight Mentor，提供个性化反馈与激励	减肥反弹的成年人	15	41.9±11.6	8/7	BMI：27.6±6.9	文本	英语	否	智能手机/平板/电脑
STEIN（2017）^[39]	美国	评估人工智能健康教练Lark HCAI对肥胖成人的减重效果、饮食质量与用户接受度	超重和肥胖的成年人	70	46.9±15.8	35/12^a	BMI：37.0±1.4	文本	英语	是	智能手机
STEPHENS（2019）^[44]	美国	评估人工智能聊天机器人Tess辅助治疗儿童肥胖及前驱糖尿病的可行性	肥胖儿童及青少年	23	15.2±3.4	13/10	未报告	文本	英语	否	Facebook Messenger/SMS
TO（2021）^[42]	澳大利亚	评估机器学习驱动的身体活动聊天机器人的可行性、可用性与有效性	不活跃的成年人	116	49.1±9.3	95/21	BMI：32.5±8.0	文本	英语	是	Facebook Messenger
PIAO（2020）^[41]	韩国	评估聊天机器人健康干预对上班族爬楼梯习惯的促进作用	办公室职员	106	未明确报告	干预组：32/25；对照组：28/21	干预组体重：64.2±14.1；对照组体重：64.5±14.1	文本、图像	韩语	否	KakaoTalk聊天机器人
MAHER（2020）^[40]	澳大利亚	评估人工智能健康教练Paola实施身体活动与饮食干预的可行性及初步效果	缺乏身体活动的成年人	31	56.2±8.0	21/10	体重：83.6±19.0	文本、图像	英语	是	Slack平台
BARLAS（2023）^[23]	土耳其	评估ChatGPT在2型糖尿病肥胖评估中的可信度	ChatGPT-3.5	20个体重管理问题	不涉及	不涉及	不涉及	文本	英语	否	ChatGPT-3.5