1.苏州大学附属第一医院药学部,江苏 苏州 215006
2.苏州大学药学院,江苏 苏州 215100
Received:06 August 2025,
Revised:2025-12-11,
Accepted:14 December 2025,
Published:15 January 2026
移动端阅览
许梦佳,宋林,杨婷婷,等.机器学习在药物不良反应预测中的应用进展 [J].中国药房,2026,37(01):105-110.
XU Mengjia,SONG Lin,YANG Tingting,et al.Advances in the application of machine learning in the prediction of adverse drug reactions[J].ZHONGGUO YAOFANG,2026,37(01):105-110.
许梦佳,宋林,杨婷婷,等.机器学习在药物不良反应预测中的应用进展 [J].中国药房,2026,37(01):105-110. DOI: 10.6039/j.issn.1001-0408.2026.01.19.
XU Mengjia,SONG Lin,YANG Tingting,et al.Advances in the application of machine learning in the prediction of adverse drug reactions[J].ZHONGGUO YAOFANG,2026,37(01):105-110. DOI: 10.6039/j.issn.1001-0408.2026.01.19.
药物不良反应(ADRs)是药物出现有害的或与用药目的无关的反应,可导致疾病进程加快、患者住院时间延长等诸多问题。传统ADRs监测(如自发呈报系统)存在上报率低、数据质量参差不齐等问题,这制约了ADRs的早期防控。随着信息技术的飞速发展,机器学习凭借其强大的特征挖掘能力和动态时序分析能力,为临床ADRs的管理与决策提供了强有力的支持。本文通过梳理近年来国内外的相关文献,对机器学习在ADRs预测中的应用进展进行了归纳总结。结果显示,机器学习已逐渐应用于肾脏、肝脏、心脏及骨髓等靶器官ADRs(如急性肾损伤、药物性肝损伤等)的早期预警和风险预测;虽然机器学习在ADRs预测领域表现出巨大的应用潜力,但是仍存在临床数据质量控制不足、模型性能评价标准缺失、模型可解释性不足与临床转化困难等局限。未来,机器学习在ADRs预测领域的发展趋势应遵循“技术-验证-整合”途径,系统性地推动模型落地。
Adverse drug reactions (ADRs) refer to harmful or unintended reactions unrelated to the intended purpose of medication administration, which can lead to various issues such as accelerated disease progression and prolonged hospitalization. Traditional ADRs monitoring systems (such as spontaneous reporting systems) suffer from limitations such as low reporting rates and inconsistent data quality, which hinder the early prevention and control of ADRs. With the rapid development of information technology, machine learning has emerged as a powerful tool for management and decision-making of ADRs by leveraging its strengths in feature extraction and dynamic temporal pattern analysis. By reviewing relevant literature at home and abroad in recent years, this paper summarizes the progress in the application of machine learning for ADRs prediction. It is found that machine learning has gradually been applied to the early warning and risk prediction of ADRs in target organs such as the kidneys, liver, heart and bone marrow (such as acute kidney injury, drug-induced liver injury, and so on). Although machine learning demonstrates significant application potential in the field of ADRs prediction, it still faces limitations such as inadequate quality control of clinical data, lack of standardized criteria for model performance evaluation, insufficient model interpretability and difficulties in clinical translation. In the future, the development trend of machine learning in the field of ADRs prediction should follow a “technology-validation-integration” pathway to systematically promote the practical implementation of models.
EDWARDS I R , ARONSON J K . Adverse drug reactions:definitions,diagnosis,and management [J ] . Lancet , 2000 , 356 ( 9237 ): 1255 - 1259 .
国家药品不良反应监测中心 . 国家药品不良反应监测年度报告(2024年) [J ] . 中国病毒病杂志 , 2025 , 15 ( 4 ): 317 - 326 .
PIRMOHAMED M , JAMES S , MEAKIN S , et al . Adverse drug reactions as cause of admission to hospital:prospective analysis of 18 820 patients [J ] . BMJ , 2004 , 329 ( 7456 ): 15 - 19 .
INÁCIO P , CAVACO A , AIRAKSINEN M . The value of patient reporting to the pharmacovigilance system:a systematic review [J ] . Br J Clin Pharmacol , 2017 , 83 ( 2 ): 227 - 246 .
LOPEZ-GONZALEZ E , HERDEIRO M T , FIGUEIRAS A . Determinants of under-reporting of adverse drug reactions:a systematic review [J ] . Drug Saf , 2009 , 32 ( 1 ): 19 - 31 .
詹世鹏 , 马攀 , 刘芳 . 机器学习在治疗药物监测与个体化用药中的应用 [J ] . 中国药房 , 2023 , 34 ( 1 ): 117 - 121,128 .
LI Q Y , TANG B H , WU Y E , et al . Machine learning:a new approach for dose individualization [J ] . Clin Pharmacol Ther , 2024 , 115 ( 4 ): 727 - 744 .
HANDELMAN G S , KOK H K , CHANDRA R V , et al . eDoctor:machine learning and the future of medicine [J ] . J Intern Med , 2018 , 284 ( 6 ): 603 - 619 .
SETO H , OYAMA A , KITORA S , et al . Gradient boosting decision tree becomes more reliable than logistic regression in predicting probability for diabetes with big data [J ] . Sci Rep , 2022 , 12 ( 1 ): 15889 .
IOSIFIDIS A , TEFAS A , PITAS I . Graph embedded extreme learning machine [J ] . IEEE Trans Cybern , 2016 , 46 ( 1 ): 311 - 324 .
BRESSO E , MONNIN P , BOUSQUET C , et al . Investigating ADR mechanisms with explainable AI:a feasibility study with knowledge graph mining [J ] . BMC Med Inform Decis Mak , 2021 , 21 ( 1 ): 171 .
HOSTE E A J , KELLUM J A , SELBY N M , et al . Global epidemiology and outcomes of acute kidney injury [J ] . Nat Rev Nephrol , 2018 , 14 ( 10 ): 607 - 625 .
KIM J Y , KIM K Y , YEE J , et al . Risk scoring system for vancomycin-associated acute kidney injury [J ] . Front Pharmacol , 2022 , 13 : 815188 .
YANG Y L , YAN H Y , WANG X Y , et al . Clinical risk assessment of serum creatinine abnormalities during vancomycin therapy:a retrospective study using machine lear- ning models [J ] . Int J Clin Pharm , 2025 , 47 ( 6 ): 1830 - 1840 .
ZHANG P , CHEN Q , LAO J H , et al . Machine learning modeling for the risk of acute kidney injury in inpatients receiving amikacin and etimicin [J ] . Front Pharmacol , 2025 , 16 : 1538074 .
HUANG S H , CHU C Y , HSU Y C , et al . How platinum-induced nephrotoxicity occurs machine learning prediction in non-small cell lung cancer patients [J ] . Comput Methods Programs Biomed , 2022 , 221 : 106839 .
YU X , WU R , JI Y W , et al . Identifying patients at risk of acute kidney injury among patients receiving immune checkpoint inhibitors:a machine learning approach [J ] . Diagnostics (Basel) , 2022 , 12 ( 12 ): 3157 .
MIAO T , LEE L H N , SUN T , et al . Safety of nonselective nonsteroidal anti-inflammatory drugs in cardiac surgery:a historical cohort study [J ] . Can J Anaesth , 2025 , 72 ( 7 ): 1056 - 1065 .
肇丽梅 , 缪丽燕 . 药物性肝损伤研究进展及展望 [J ] . 药学进展 , 2023 , 47 ( 2 ): 81 - 83 .
HE X , YAO P L , LI M T , et al . A risk scoring model for high-dose methotrexate-induced liver injury in children with acute lymphoblastic leukemia based on gene polymorphism study [J ] . Front Pharmacol , 2021 , 12 : 726229 .
HAN J M , YEE J , CHO S , et al . A risk scoring system utilizing machine learning methods for hepatotoxicity prediction one year after the initiation of tyrosine kinase inhibitors [J ] . Front Oncol , 2022 , 12 : 790343 .
ZENG Y , LU H , LI S , et al . Risk prediction of liver injury in pediatric tuberculosis treatment:development of an automated machine learning model [J ] . Drug Des Devel Ther , 2025 , 19 : 239 - 250 .
XIAO Y , CHEN Y F , HUANG R J , et al . Interpretable machine learning in predicting drug-induced liver injury among tuberculosis patients:model development and validation study [J ] . BMC Med Res Methodol , 2024 , 24 ( 1 ): 92 .
CARDINALE D , CICERI F , LATINI R , et al . Anthracycline-induced cardiotoxicity:a multicenter randomised trial comparing two strategies for guiding prevention with enalapril:the International CardioOncology Society-one trial [J ] . Eur J Cancer , 2018 , 94 : 126 - 137 .
CHAIX M A , PARMAR N , KINNEAR C , et al . Machine learning identifies clinical and genetic factors associated with anthracycline cardiotoxicity in pediatric cancer survivors [J ] . JACC CardioOncol , 2020 , 2 ( 5 ): 690 - 706 .
ÖZTÜRK C , VALIDYEV D , BECHER U M , et al . A novel scoring system to estimate chemotherapy-induced myocardial toxicity:risk assessment prior to non-anthracycline chemotherapy regimens [J ] . Int J Cardiol Heart Vasc , 2021 , 33 : 100751 .
LI C , CHEN L , CHOU C , et al . Using machine learning approaches to predict short-term risk of cardiotoxicity among patients with colorectal cancer after starting fluoropyrimidine-based chemotherapy [J ] . Cardiovasc Toxicol , 2022 , 22 ( 2 ): 130 - 140 .
YUE X N , YAN C , LIU X Y . Construction of a risk prediction model for chemotherapy-induced cardiotoxicity in breast cancer patients based on machine learning algorithm [J ] . Zhonghua Xin Xue Guan Bing Za Zhi , 2025 , 53 ( 8 ): 898 - 905 .
HEILBRONER S P , FEW R , MUELLER J , et al . Predic- ting cardiac adverse events in patients receiving immune checkpoint inhibitors:a machine learning approach [J ] . J Immunother Cancer , 2021 , 9 ( 10 ): e002545 .
ARAÚJO D C , SIMÕES R , DE PAULA SABINO A , et al . Predicting doxorubicin-induced cardiotoxicity in breast cancer:leveraging machine learning with synthetic data [J ] . Med Biol Eng Comput , 2025 , 63 ( 5 ): 1535 - 1550 .
朱荟萃 , 杨静 . 抗肿瘤药物引起骨髓抑制的中西医治疗研究进展 [J ] . 中西医结合研究 , 2024 , 16 ( 4 ): 245 - 249,254 .
刘阳 , 骆亭亭 , 李红健 , 等 . 乳腺癌AC-T化疗方案致骨髓抑制的危险因素分析及其风险预测模型的构建 [J ] . 中国医院药学杂志 , 2024 , 44 ( 21 ): 2503 - 2511 .
JIANG D , SONG Z W , LIU P , et al . A prediction model for severe hematological toxicity of BTK inhibitors [J ] . Ann Hematol , 2023 , 102 ( 10 ): 2765 - 2777 .
VAN DUNG H , TAN V M , DIEU N T , et al . Development and external validation of a machine learning model for predicting drug-induced immune thrombocytopenia in a real-world hospital cohort [J ] . BMC Med Inform Decis Mak , 2025 , 25 ( 1 ): 265 .
SHIBAHARA T , IKUTA S , MURAGAKI Y . Machine-learning approach for modeling myelosuppression at- tributed to nimustine hydrochloride [J ] . JCO Clin Cancer Inform , 2018 , 2 : 1 - 21 .
LAVIERI L , KOENIG C , BODMER N , et al . Predicting fever in neutropenia with safety-relevant events in children undergoing chemotherapy for cancer:the prospective multicenter SPOG 2015 FN Definition Study [J ] . Pediatr Blood Cancer , 2021 , 68 ( 12 ): e29253 .
LI M J , WANG Q , LU P , et al . Development of a machine learning-based prediction model for chemotherapy-induced myelosuppression in children with Wilms’ tumor [J ] . Cancers (Basel) , 2023 , 15 ( 4 ): 1078 .
MAGNUSON A , SEDRAK M S , GROSS C P , et al . Development and validation of a risk tool for predicting severe toxicity in older adults receiving chemotherapy for early-stage breast cancer [J ] . J Clin Oncol , 2021 , 39 ( 6 ): 608 - 618 .
WU Y F , ZHAO W , ZHANG L X , et al . Machine learning models for predicting chemotherapy-induced adverse drug reactions in colorectal cancer patients [J ] . Dig Liver Dis , 2025 , 57 ( 9 ): 1845 - 1852 .
CUI L Q , ZHU M , WANG T L , et al . Clinical prediction of sodium valproate-induced movement disorders in hospitalized patients:a nomogram-based model using real-world data [J ] . Int J Clin Pharm , 2025 , 47 ( 6 ): 1841 - 1851 .
CHO Y A , MOON Y , PARK W , et al . Factors inducing cutaneous adverse reactions in cancer patients treated with PD-1 and PD-L1 inhibitors:a machine-learning algorithm approach [J ] . Immunopharmacol Immunotoxicol , 2025 , 47 ( 1 ): 53 - 58 .
COLLINS G S , REITSMA J B , ALTMAN D G , et al . Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD):the TRIPOD statement [J ] . BMJ , 2015 , 350 : g7594 .
国家卫生健康委 , 国家中医药局 , 国家疾控局 . 卫生健康行业人工智能应用场景参考指引 [EB/OL ] . [ 2025-07-23 ] . https://www.nhc.gov.cn/guihuaxxs/c100133/202411/3dee-425b8dc34f739d63483c4e5c334c.shtml https://www.nhc.gov.cn/guihuaxxs/c100133/202411/3dee-425b8dc34f739d63483c4e5c334c.shtml .
ZHOU H J , LIU F L , WU J G , et al . A collaborative large language model for drug analysis [J ] . Nat Biomed Eng , 2025 : 1 - 12 .
0
Views
20
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621
