今日药学

人工智能在罕见病超说明书用药不良反应主动监测与预警中的应用

PDF下载

王权 , 许嘉越 , 付昱 ^*

今日药学 | 临床药学 2026,36(7): 530-535

收起

今日药学 |临床药学 2026 , 36 (7) : 530 -535

人工智能在罕见病超说明书用药不良反应主动监测与预警中的应用

全屏

[Author(id=1321826825811112509, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1321826825882415679, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826825811112509, language=EN, stringName=Quan WANG, firstName=Quan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321826825957913152, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826825811112509, language=CN, stringName=王权, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中山大学附属第三医院药剂科，广东　广州　510630, bio={"content":"

王权，博士，研究方向：临床药学

"}, bioImg=null, bioContent=

王权，博士，研究方向：临床药学

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1321826825706254905, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, xref=null, ext=[AuthorCompanyExt(id=1321826825718837818, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China), AuthorCompanyExt(id=1321826825727226427, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中山大学附属第三医院药剂科，广东　广州　510630)])]), Author(id=1321826826041799234, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1321826826134073924, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826826041799234, language=EN, stringName=Jiayue XU, firstName=Jiayue, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321826826201182789, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826826041799234, language=CN, stringName=许嘉越, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中山大学附属第三医院药剂科，广东　广州　510630, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1321826825706254905, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, xref=null, ext=[AuthorCompanyExt(id=1321826825718837818, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China), AuthorCompanyExt(id=1321826825727226427, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中山大学附属第三医院药剂科，广东　广州　510630)])]), Author(id=1321826826276680263, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fuyu28@mail.sysu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1321826826360566345, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826826276680263, language=EN, stringName=Yu FU, firstName=Yu, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=^*, address=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1321826826452841034, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, authorId=1321826826276680263, language=CN, stringName=付昱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=^*, address=中山大学附属第三医院药剂科，广东　广州　510630, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1321826825706254905, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, xref=null, ext=[AuthorCompanyExt(id=1321826825718837818, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China), AuthorCompanyExt(id=1321826825727226427, tenantId=1146029695717560320, journalId=1227999776411738115, articleId=1321826824997417526, companyId=1321826825706254905, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中山大学附属第三医院药剂科，广东　广州　510630)])])]

王权, 许嘉越, 付昱^*

作者信息

中山大学附属第三医院药剂科，广东　广州　510630

通讯作者:

付昱，主管药师，研究方向：临床药学，E-mail：fuyu28@mail.sysu.edu.cn

作者简介:

王权，博士，研究方向：临床药学

Application of Artificial Intelligence in Active Surveillance and Early Warning of Adverse Drug Reactions Associated with Off-Label Drug Use in Rare Diseases

Quan WANG, Jiayue XU, Yu FU^*

Affiliations

Department of Pharmacy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510630, China

出版时间: 2026-07-25 doi: 10.12048/j.issn.1674-229X.2026.07.007

文章导航

摘要

收起

超说明书用药是罕见病治疗的主要手段，但其不良反应风险缺乏系统评估，传统药物警戒体系因数据稀疏、报告不足和信号识别困难而难以有效覆盖。人工智能（Artificial Intelligence，AI）技术为构建主动、精准、实时的不良反应监测与预警体系提供了新路径。本文综述了AI在罕见病超说明书用药不良反应主动监测中的应用进展，涵盖隐匿患者识别、基于多源数据的智能风险预警以及面向临床的实用化系统（如DrugGPT、“协和·太初”“哪吒·灵童”）。尽管前景广阔，AI应用仍面临数据稀缺与异质性、模型可解释性不足、隐私伦理风险及监管框架缺失等挑战。未来需医学、药学、数据科学与政策制定者协同合作，推动建立以患者为中心、数据驱动、可信可控的罕见病用药安全智能监测新生态。

关键词

人工智能 / 罕见病 / 超说明书用药 / 不良反应

Abstract

收起

Off-label drug use serves as the primary therapeutic approach for rare diseases，yet systematic evaluation of the risks of its associated adverse drug reactions (ADRs) is lacking. Conventional pharmacovigilance systems are often inadequate due to data sparsity，underreporting，and challenges in signal detection. Artificial intelligence (AI) enables the development of proactive，precise，and real-time ADR surveillance and early-warning frameworks. This review summarizes recent advances in applying AI for active surveillance of off-label ADRs in rare diseases. Key applications include identification of concealed patients，intelligent risk early warning based on multi-source data，and clinical decision support systems powered by AI，such as DrugGPT，“Xiehe-TaiChu” and “Nezha-LingTong”. Despite their promising prospects，significant challenges persist，including data scarcity and heterogeneity，limited model interpretability，privacy and ethical concerns，and the absence of a mature regulatory framework. Future efforts require multidisciplinary collaboration among clinicians，pharmacists，data scientists，and policymakers to establish a patient-centered，data-driven，trustworthy and controllable intelligent monitoring ecosystem for the medication safety of rare diseases.

Key words

artificial intelligence / rare diseases / off-label drug use / adverse drug reactions

引用本文

王权, 许嘉越, 付昱. 人工智能在罕见病超说明书用药不良反应主动监测与预警中的应用. 今日药学, 2026 , 36 (7) : 530 -535 . DOI: 10.12048/j.issn.1674-229X.2026.07.007

Quan WANG, Jiayue XU, Yu FU. Application of Artificial Intelligence in Active Surveillance and Early Warning of Adverse Drug Reactions Associated with Off-Label Drug Use in Rare Diseases[J]. Pharmacy Today, 2026 , 36 (7) : 530 -535 . DOI: 10.12048/j.issn.1674-229X.2026.07.007

基金

收起

广东省药学会科学研究基金(2025HJB01004)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Roessler H I, Knoers N V A M, van Haelst M M, et al. Drug repurposing for rare diseases[J]. Trends Pharmacol Sci, 2021, 42(4): 255-267.

[2]

Zuo W, Sun Y J, Liu R J, et al. Management guideline for the off-label use of medicine in China (2021)[J]. Expert Rev Clin Pharmacol, 2022, 15(10): 1253-1268.

[3]

Mazzucato M, Minichiello C, Vianello A, et al. Real-world use of orphan medicinal products (OMPs) in rare disease (RD) patients: a population-based registry study[J]. Front Pharmacol, 2022, 13: 940010.

[4]

Fung A, Yue X M, Wigle P R, et al. Off-label medication use in rare pediatric diseases in the United States[J]. Intractable Rare Dis Res, 2021, 10(4): 238-245.

[5]

Dooms M, Cassiman D, Simoens S. Off-label use of orphan medicinal products: a Belgian qualitative study[J]. Orphanet J Rare Dis, 2016, 11(1): 144.

[6]

中国药学会罕见病药物专委会. 医疗机构罕见病药学服务专家共识(2025)[J]. 协和医学杂志, 2025, 16(3): 659-672.

[7]

陈超阳, 段玥涵, 卓琳, 等. 罕见病超说明书用药专家共识计划书[J]. 药物流行病学杂志, 2025, 34(9): 1066-1073.

[8]

左玮, 刘容吉, 孙雅佳, 等. 《中国超药品说明书用药管理指南(2021)》推荐意见及要点解读[J]. 协和医学杂志, 2023, 14(1): 86-93.

[9]

Sardella M, Belcher G. Pharmacovigilance of medicines for rare and ultrarare diseases[J]. Ther Adv Drug Saf, 2018, 9(11): 631-638.

[10]

Phillips C, Parkinson A, Namsrai T, et al. Time to diagnosis for a rare disease: managing medical uncertainty. A qualitative study[J]. Orphanet J Rare Dis, 2024, 19(1): 297.

[11]

Isono M, Kokado M, Kato K. Why does it take so long for rare disease patients to get an accurate diagnosis: a qualitative investigation of patient experiences of hereditary angioedema[J]. PLoS One, 2022, 17(3): e0265847.

[12]

Crowe A L, McKnight A J, McAneney H. Communication needs for individuals with rare diseases within and around the healthcare system of northern Ireland[J]. Front Public Health, 2019, 7: 236.

[13]

Tang S J, Yuan K, Chen L N. Molecular biomarkers, network biomarkers, and dynamic network biomarkers for diagnosis and prediction of rare diseases[J]. Fundam Res, 2022, 2(6): 894-902.

[14]

Han S F, Zhang R F, Shi L Y, et al. Classifying social determinants of health from unstructured electronic health records using deep learning-based natural language processing[J]. J Biomed Inform, 2022, 127: 103984.

[15]

Zolnoori M, Fung K W, Patrick T B, et al. A systematic approach for developing a corpus of patient reported adverse drug events: a case study for SSRI and SNRI medications[J]. J Biomed Inform, 2019, 90: 103091.

[16]

Hurvitz N, Azmanov H, Kesler A, et al. Establishing a second-generation artificial intelligence-based system for improving diagnosis, treatment, and monitoring of patients with rare diseases[J]. Eur J Hum Genet, 2021, 29(10): 1485-1490.

[17]

Spahn C, Toda N, Groat B, et al. Transforming pharmacovigilance with pharmacogenomics: toward personalized risk management[J]. Clin Pharmacol Ther, 2025, 118(6): 1286-1296.

[18]

Elhaddad M, Hamam S. AI-driven clinical decision support systems: an ongoing pursuit of potential[J]. Cureus, 2024, 16(4): e57728.

[19]

Markus A F, Kors J A, Rijnbeek P R. The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies[J]. J Biomed Inform, 2021, 113: 103655.

[20]

Johnson R, Stephens A V, Mester R, et al. Electronic health record signatures identify undiagnosed patients with common variable immunodeficiency disease[J]. Sci Transl Med, 2024, 16(745): eade4510.

[21]

Jordan D M, Vy H M T, Do R. A deep learning transformer model predicts high rates of undiagnosed rare disease in large electronic health systems[J]. medRxiv Prepr Serv Health Sci, 2023. Doi: 10.1101/2023.12.21.23300393.

[22]

Arku D, Yousef C, Abraham I. Changing paradigms in detecting rare adverse drug reactions: from disproportionality analysis, old and new, to machine learning[J]. Expert Opin Drug Saf, 2022, 21(10): 1235-1238.

[23]

Gao Y, Zhang X, Sun Z Q, et al. Precision adverse drug reactions prediction with heterogeneous graph neural network[J]. Adv Sci (Weinh), 2024, 12(4): e2404671.

[24]

Cai Z, Tang H, Gao S, et al. HyperADRs: a hierarchical hypergraph framework for drug-gene-ADR prediction[J]. Quantitative Methods, 2025.

[25]

Li S, Zhang L C, Wang L Y, et al. BiMPADR: a deep learning framework for predicting adverse drug reactions in new drugs[J]. Molecules, 2024, 29(8): 1784.

[26]

Yadav M, Ahlawat P, Singh V. A graph-based transformer neural network for multi-label ADR prediction[J]. Arab J Sci Eng, 2025, 50(10): 7323-7341.

[27]

Asfand-E-Yar M, Hashir Q, Shah A A, et al. Multimodal CNN-DDI: using multimodal CNN for drug to drug interaction associated events[J]. Sci Rep, 2024, 14(1): 4076.

[28]

Zhou H J, Liu F L, Wu J G, et al. A collaborative large language model for drug analysis[J]. Nat Biomed Eng, 2026, 10(5): 870-881.

[29]

Chen L, Wang W, Bai Z, et al. PharmaGPT: Domain-specific large language models for bio-pharmaceutical and chemistry[J]. arXiv, 2024.

[30]

Dou Y T, Huang Y W, Zhao X J, et al. ShennongMGS: An LLM-based Chinese medication guidance system[C]//ACM Transactions on Management Information Systems. ACM, 2025: 1-14.

[31]

Li W Q, Yu L N, Wu M, et al. DoctorGPT: A large language model with Chinese medical question-answering capabilities[C]//2023 International Conference on High Performance Big Data and Intelligent Systems (HDIS). December 6-8, 2023, Macau, China. IEEE, 2023: 186-193.

[32]

徐鹏航, 宋晨. 全国首个! 罕见病有了AI大模型[N]. 新华每日电讯, 2025-02-21.

[33]

Edvard Smith C I E, Bergman P, Hagey D W. Estimating the number of diseases - the concept of rare, ultra-rare, and hyper-rare[J]. iScience, 2022, 25(8): 104698.

[34]

吴敏敏, 王伟炳. 多源异构电子健康记录在观察性研究中的偏倚和控制[J]. 复旦学报(医学版), 2025, 52(5): 765-770.

[35]

Iyer A A, Barzilay J R, Tabor H K. Patient and family social media use surrounding a novel treatment for a rare genetic disease: a qualitative interview study[J]. Genet Med, 2020, 22(11): 1830-1837.

[36]

Khalid N, Qayyum A, Bilal M, et al. Privacy-preserving artificial intelligence in healthcare: techniques and applications[J]. Comput Biol Med, 2023, 158: 106848.

[37]

Krishnamoorthy M, Sjoding M W, Wiens J. Off-label use of artificial intelligence models in healthcare[J]. Nat Med, 2024, 30(6): 1525-1527.

2026年第36卷第7期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.12048/j.issn.1674-229X.2026.07.007

接收时间：2026-01-21
首发时间：2026-10-27
出版时间：2026-07-25

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2026-01-21

基金

广东省药学会科学研究基金(2025HJB01004)

作者信息

中山大学附属第三医院药剂科，广东　广州　510630

通讯作者:

付昱，主管药师，研究方向：临床药学，E-mail：fuyu28@mail.sysu.edu.cn

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/jryx/CN/10.12048/j.issn.1674-229X.2026.07.007

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT