人工智能（Artificial Intelligence, AI）,特别是生成式人工智能（Generative AI, GenAI）的快速发展,正在深刻重塑卫生技术评估（Health Technology Assessment, HTA）的研究范式与实践路径。当前,AI已在HTA多个核心环节展现出显著应用潜力,包括系统性文献综述与证据整合、临床证据（涵盖随机对照试验与真实世界数据）的自动化提取与分析,以及卫生经济模型的智能化构建等。本文通过系统梳理国内外AI在HTA领域的最新进展,深入剖析其在科学严谨性、数据隐私、算法偏倚、监管政策及人才技术等方面面临的关键挑战,并结合我国医保制度、数据生态与政策环境的独特优势,提出推动AI-HTA本土化发展路径,旨在为我国AI赋能HTA的规范应用、标准制定与政策落地提供参考依据。
Abstract
The rapid advancement of artificial intelligence (AI), particularly generative AI (GenAI), is profoundly reshaping the research paradigms and practical approaches of health technology assessment (HTA). AI has already demonstrated significant potential across multiple core components of HTA, including the systematic literature reviews and evidence synthesis, the automatic extraction and analysis of clinical evidence (encompassing both randomized controlled trials and real-world data), and the intelligent development of health economic models. This review systematically examines recent global and domestic advances in the application of AI in HTA, critically analyzes key challenges related to scientific rigor, data privacy, algorithmic bias, regulatory frameworks, and technical workforce capacity, and proposes a localized implementation pathway for AI-enabled HTA in China, leveraging China's unique strengths in its national healthcare security system, data ecosystem, and policy environment. The aim of this article is to provide a reference for the standardized application, guideline development, and policy integration of AI in HTA within the Chinese context.
关键词
人工智能 /
生成式人工智能 /
卫生技术评估
Key words
artificial intelligence /
generative artificial intelligence /
health technology assessment
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] FLEURENCE R L, BIAN J, WANG X, et al.Generative artificial intelligence for health technology assessment: opportunities, challenges, and policy considerations: an ISPOR working group report[J]. Value in health, 2025, 28(2): 175-183.
[2] National Institute for Health and Care Excellence. Use of AI in evidence generation: NICE position statement[EB/OL]. (2024-09-20) [2024-09-20]. https://www.nice.org.uk/corporate/ecd11/resources/use-of-ai-in-evidence-generation-nice-position-statement-pdf-40464268944325.
[3] SCHERBAKOV D, HUBIG N, JANSARI V, et al.The emergence of large language models as tools in literature reviews: a large language model-assisted systematic review[J]. Journal of the American Medical Informatics Association, 2025, 32(6): 1071-1086.
[4] GUO E, GUPTA M, DENG J, et al.Automated paper screening for clinical reviews using large language models: data analysis study[J]. Journal of medical Internet research, 2024, 26: e48996.
[5] HASAN B, SAADI S, RAJJOUF N S, et al. Integrating large language models in systematic reviews: a framework and case study using ROBINS-I for risk of bias assessment[J/OL]. BMJ evidence-based medicine, 2024. https://doi.org/10.1136/bmjebm-2023-112597.
[6] REASON T, BENBOW E, LANGHAM J, et al.Artificial intelligence to automate network meta-analyses: four case studies to evaluate the potential application of large language models[J]. PharmacoEconomics open, 2024, 8(2): 205-220.
[7] GARTLEHNER G, KAHWATI L, HILSCHER R, et al.Data extraction for evidence synthesis using a large language model: a proof-of-concept study[J]. Research synthesis methods, 2024, 15(4): 576-589.
[8] SCHOPOW N, OSTERHOFF G, BAUR D.Applications of the natural language processing tool ChatGPT in clinical practice: comparative study and augmented systematic review[J]. JMIR medical informatics, 2023, 11: e48933.
[9] WU S, MA X, LUO D, et al. Automated literature research and review-generation method based on large language models[J]. National science review, 2025, 12(6): nwaf169.
[10] LEE K, PAEK H, OFOEGBU N, et al.A4SLR: an agentic artificial intelligence-assisted systematic literature review framework to augment evidence synthesis for health economics and outcomes research and health technology assessment[J]. Value in health, 2025, 28(11): 1655-1664.
[11] 黄涛,李灿,黄先琴,等.真实世界数据用于药品医保决策的国内外政策分析[J]. 中国循证医学杂志,2024,24(5):510-515.
[12] FLEURENCE R L, KENT S, ADAMSON B, et al.assessing real-world data from electronic health records for health technology assessment: the suitability checklist: a good practices report of an ISPOR task force[J]. Value in health, 2024, 27(6): 692-701.
[13] BOEHM K M, AHERNE E A, ELLENSON L, et al.Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer[J]. Nature cancer, 2022, 3(6): 723-733.
[14] SHIVADE C, RAGHAVAN P, FOSLER-LUSSIER E, et al.A review of approaches to identifying patient phenotype cohorts using electronic health records[J]. Journal of the American Medical Informatics Association, 2014, 21(2): 221-230.
[15] XU H, USUYAMA N, BAGGA J, et al.A whole-slide foundation model for digital pathology from real-world data[J]. Nature, 2024, 630(8015): 181-188.
[16] LEE W, SCHWARTZ N, BANSAL A, et al.A scoping review of the use of machine learning in health economics and outcomes research: Part 1-data from wearable devices[J]. Value in health, 2023, 26(2): 292-299.
[17] PADULA W V, KREIF N, VANNESS D J, et al.Machine learning methods in health economics and outcomes research-the palisade checklist: a good practices report of an ISPOR task force[J]. Value in health, 2022, 25(7): 1063-1080.
[18] LEE W, SCHWARTZ N, BANSAL A, et al.A scoping review of the use of machine learning in health economics and outcomes research: Part 2-data from nonwearables[J]. Value in health, 2022, 25(12): 2053-2061.
[19] LAI T C, NGORSURACHES S.Roles of artificial intelligence-based synthetic data in health economics and outcomes research[J]. Value in health, 2025, 28(11): 1690-1695.
[20] CHHATWAL J, Samur S, Yildirm IF, et al.EE247 fully replicating published Markov health economic models using fenerative AI[J]. Value in health, 2024, 27(12): S102.
[21] REASON T, RAWLINSON W, LANGHAM J, et al.Artificial intelligence to automate health economic modelling: a case study to evaluate the potential application of large language models[J]. PharmacoEconomics open, 2024, 8(2): 191-203.
[22] GU X, ZHANG H, PATIL D, et al.Use of large language models to extract cost-effectiveness analysis data: a case study[J]. Value in health, 2025, 28(11): 1637-1645.
[23] REASON T, KLIJN S, RAWLINSON W, et al.Using generative artificial intelligence in health economics and outcomes research: a primer on techniques and breakthroughs[J]. PharmacoEconomics open, 2025, 9(4): 501-517.
[24] ALKAISSI H, MCFARLANE S I.Artificial hallucinations in ChatGPT: implications in scientific writing[J]. Cureus, 2023, 15(2): e35179.
[25] FLEURENCE R L, DAWOUD D, BIAN J, et al.ELEVATE-GenAI: reporting guidelines for the use of large language models in health economics and outcomes research: an ISPOR working group report[J]. Value in health, 2025, 28(11): 1611-1625.
[26] REASON T, WU Y, JONES C, et al.The "artificial intelligence statistician": utilizing generative artificial intelligence to select an appropriate model and execute network meta-analyses[J]. Value in health, 2025, 28(11): 1646-1654.
[27] RAMEZANI M, BAKHTIARI A, DAROUDI R, et al.Applications of artificial intelligence and the challenges in health technology assessment: a scoping review and framework with a focus on economic dimensions[J]. Health economics review, 2025, 15(1): 46.
[28] TEMPLIN T, PEREZ M W, SYLVIA S, et al.Addressing 6 challenges in generative AI for digital health: a scoping review[J]. PLOS Digital Health, 2024, 3(5): e0000503.
[29] FLEURENCE R L, WANG X, BIAN J, et al.A taxonomy of generative artificial intelligence in health economics and outcomes research: an ISPOR working group report[J]. Value in health, 2025, 28(11): 1601-1610.
[30] YANG Y, LIN M, ZHAO H, et al.A survey of recent methods for addressing AI fairness and bias in biomedicine[J]. Journal of biomedical informatics, 2024, 154: 104646.
[31] BÉLISLE-PIPON J C, COUTURE V, ROY M C, et al. What makes artificial intelligence exceptional in health technology assessment?[J]. Frontiers in artificial intelligence, 2021, 4: 736697.
[32] National Institute for Health and Care Excellence. NICE statement of intent for artificial intelligence (AI)[EB/OL]. (2024-12-16) [2025-12-16]. https://www.nice.org.uk/corporate/ecd12/resources/nice-statement-of-intent-for-artificial-intelligence-ai-pdf-40464270623941.
[33] ZEMPLÉNYI A, TACHKOV K, BALKANYI L, et al. Recommendations to overcome barriers to the use of artificial intelligence-driven evidence in health technology assessment[J]. Frontiers in public health, 2023, 11: 1088121.
[34] YOU M, XIAO Y, YAO H, et al.Evaluation and regulation of medical artificial intelligence applications in China[J]. Chinese medical sciences journal, 2025, 40(1): 3-8.
[35] 国家医疗保障局办公室.关于开展真实世界医保综合价值评价试点工作的通知[EB/OL]. (2025-09-23)[2025-12-20]. https://www.nhsa.gov.cn/art/2025/9/23/art_109_17984.html.
[36] 海南省医疗保障局.一文带您了解海南省真实世界研究[EB/OL]. (2025-09-23) [2025-12-20]. https://ybj.hainan.gov.cn/jdhy/zxjd/202504/t20250411_3847642.html.
[37] 新华网.苗伟代表:加快卫生技术评估立法助力健康中国建设[EB/OL]. (2025-03-05) [2025-12-20]. https://www.news.cn/politics/20250305/3b54bbc1e74c441f81e6a5fa102e9225/c.html.
[38] 复旦大学公共卫生学院.人工智能赋能卫生技术评估医疗科技助力健康中国[EB/OL]. (2025-11-23)[2025-12-20]. https://sph.fudan.edu.cn/a/2583.
