Received:18 March 2026,
Revised:2026-07-07,
Accepted:08 July 2026,
Online First:24 July 2026,
Published:30 July 2026
移动端阅览
《基于多模态数据的人工智能方法预测抗肿瘤药物不良反应专家共识》编写组,辽宁省生命科学学会临床药学与转化药学分会,中国药师协会药物治疗管理专业委员会,等.基于多模态数据的人工智能方法预测抗肿瘤药物不良反应专家共识 [J].中国药房,2026,37(14):1797-1804.
.Expert consensus on artificial intelligence methods based on multimodal data for predicting adverse drug reactions of antineoplastics[J].ZHONGGUO YAOFANG,2026,37(14):1797-1804.
《基于多模态数据的人工智能方法预测抗肿瘤药物不良反应专家共识》编写组,辽宁省生命科学学会临床药学与转化药学分会,中国药师协会药物治疗管理专业委员会,等.基于多模态数据的人工智能方法预测抗肿瘤药物不良反应专家共识 [J].中国药房,2026,37(14):1797-1804. DOI: 10.6039/j.issn.1001-0408.2026.14.01.
.Expert consensus on artificial intelligence methods based on multimodal data for predicting adverse drug reactions of antineoplastics[J].ZHONGGUO YAOFANG,2026,37(14):1797-1804. DOI: 10.6039/j.issn.1001-0408.2026.14.01.
目的
2
为科学、规范地应用人工智能(AI)与多模态数据融合技术,基于多模态数据构建抗肿瘤药物不良反应(ADR)预测模型提供指导性意见,提升抗肿瘤药物治疗的安全性。
方法
2
由辽宁省生命科学学会临床药学与转化药学分会等行业学会联合发起,中国医科大学附属第四医院牵头组织,编写组以“多模态数据”“人工智能”“不良反应”“抗肿瘤药物”“模型”等为关键词全面检索国内外数据库,收集指南、专家共识及相关指导性文献,结合我国AI技术在肿瘤药学服务中的实践经验,起草本共识编写大纲;经外审专家组评估和讨论后,编写组结合评估结果并将90%及以上专家同意的内容判定为推荐意见形成。
结果与结论
2
经过多轮审议和讨论修订,本共识梳理了“明确研究目标-数据准备-算法框架选择-多模态数据融合策略设计-模型训练与验证-可解释性分析-临床部署-成果发表”的抗肿瘤药物ADR预测模型构建流程,并就数据准备、算法框架选择、多模态数据融合策略设计、模型验证与可解释性分析、临床部署等核心环节形成了18条推荐意见,供肿瘤领域医师、临床药师、研究人员及AI技术开发者参考使用,以协助临床作出最优治疗决策。
OBJECTIVE
2
To provide guidance on the scientific and standardized application of artificial intelligence (AI) and multimodal fusion techniques in constructing predictive models for adverse drug reactions (ADR) of antineoplastics, thereby enhancing the safety of antineoplastic therapy.
METHODS
2
Jointly initiated by the Clinical Pharmacy and Translational Pharmacy Society of the Liaoning Provincial Life Sciences Association and other professional societies, and organized by the Fourth Affiliated Hospital of China Medical University, the writing group conducted a comprehensive search of domestic and international databases using keywords such as “multimodal data” “artificial intelligence” “adverse drug reactions”“antineoplastics” and “models” to collect guidelines, expert consensuses, and relevant guidance literature. Based on this search, and combined with China’s practical experience in applying AI to oncology pharmaceutical care, a consensus framework and preliminary recommendations were drafted. Following evaluation and discussion by an external expert panel, the writing group incorporated the assessment results and formulated recommendations based on those endorsed by 90% or more of the experts.
RESULTS &CONCLUSIONS
2
After multiple rounds of review, discussion and revision, this consensus outlines the process for constructing an ADR prediction model of antineoplastics, encompassing “defining research objectives-data preparation-selection of algorithmic frameworks-design of multimodal data fusion strategies-model training and validation-interpretability analysis-clinical deployment-publication of results”. It also formulates 18 recommendations regarding core aspects such as data preparation, algorithm framwork selection, multimodal data fusion strategy design, model validation and interpretability analysis, and clinical deployment. These recommendations are intended for use by physicians in the field of oncology, clinical pharmacists, researchers, and AI technology developers to assist in making optimal clinical treatment decisions.
丁年羊 , 李莉 , 方攀奇 , 等 . 我院贝伐珠单抗生物类似药与原研药相关不良反应回顾性分析 [J ] . 中国药房 , 2024 , 35 ( 4 ): 472 - 475 .
Bossi P , Antonuzzo A , Cherny N I , et al . Diarrhoea in adult cancer patients:ESMO clinical practice guidelines [J ] . Ann Oncol , 2018 , 29 ( Suppl. 4 ): iv126 - iv142 .
Moey M Y Y , Gougis P , Goldschmidt V , et al . Increased reporting of fatal pneumonitis associated with immune checkpoint inhibitors:a WHO pharmacovigilance database analysis [J ] . Eur Respir J , 2020 , 55 ( 6 ): 2000038 .
吴蕊 , 孔前进 , 王世勋 , 等 . 双模态Logistic Regression及其应用 [J ] . 计算机应用与软件 , 2020 , 37 ( 12 ): 244 - 248,333 .
Gao J Y , Zhang P , Tang M , et al . Predictors of immune checkpoint inhibitor-related adverse events in older patients with lung cancer:a prospective real-world analysis [J ] . J Cancer Res Clin Oncol , 2023 , 149 ( 11 ): 8993 - 9006 .
曾江 , 王春江 , 吴洪文 , 等 . 来氟米特诱导的间质性肺炎文献分析 [J ] . 中国药房 , 2022 , 33 ( 1 ): 79 - 83 .
崔晓辉 , 王天琳 . 把握人工智能机遇推动药物警戒工作提质增效与创新发展 [J ] . 药物不良反应杂志 , 2026 , 28 ( 1 ): 10 - 14 .
Bera K , Braman N , Gupta A , et al . Predicting cancer outcomes with radiomics and artificial intelligence in radiol-ogy [J ] . Nat Rev Clin Oncol , 2022 , 19 ( 2 ): 132 - 146 .
van Griethuysen J J M , Fedorov A , Parmar C , et al . Computational radiomics system to decode the radiographic phenotype [J ] . Cancer Res , 2017 , 77 ( 21 ): e104 - e107 .
Wu Y M , Zhang W , Liang X , et al . Habitat radiomics analysis for progression free survival and immune-related adverse reaction prediction in non-small cell lung cancer treated by immunotherapy [J ] . J Transl Med , 2025 , 23 ( 1 ): 393 .
Du Y H , Zhang S , Jia X H , et al . Radiomics biomarkers to predict checkpoint inhibitor pneumonitis in non-small cell lung cancer [J ] . Acad Radiol , 2025 , 32 ( 3 ): 1685 - 1695 .
Prelaj A , Miskovic V , Zanitti M , et al . Artificial intel-ligence for predictive biomarker discovery in immuno-oncology:a systematic review [J ] . Ann Oncol , 2024 , 35 ( 1 ): 29 - 65 .
Chen D X , Fu M T , Chi L J , et al . Prognostic and predictive value of a pathomics signature in gastric cancer [J ] . Nat Commun , 2022 , 13 ( 1 ): 6903 .
Søgaard K K , Farkas D K , Pedersen L , et al . Pneumonia and the incidence of cancer:a Danish nationwide cohort study [J ] . J Intern Med , 2015 , 277 ( 4 ): 429 - 438 .
She L , Chen J , Liu J Y , et al . A two-stage genome-wide association study to identify novel genetic loci associated with irAEs in lung cancer patients receiving PD-1/PD-L1 inhibitors [J ] . Cancer Lett , 2026 , 639 : 218168 .
He Y F , Dong X H , Yang Q H , et al . An integrated study of glutamine alleviates enteritis induced by glycinin in hybrid groupers using transcriptomics,proteomics and microRNA analyses [J ] . Front Immunol , 2023 , 14 : 1301033 .
Rodríguez-Garzotto A , Iglesias-Docampo L , Díaz-García C V , et al . Topical heparin as an effective and safe treatment for patients with capecitabine-induced hand-foot syndrome:results of a phase ⅡA trial supported by proteomic profiling of skin biopsies [J ] . Ther Adv Med Oncol , 2022 , 14 : 17588359221086911 .
Wang M G , Wu S Q , Zhang M M , et al . Plasma metabo-lomic and lipidomic alterations associated with anti-tuberculosis drug-induced liver injury [J ] . Front Pharmacol , 2022 , 13 : 1044808 .
Wu W Z , Huang H C , Zhu G H , et al . Serum multiomics prediction of prognosis and adverse reactions to concurrent chemoradiotherapy in patients with esophageal cancer [J ] . Br J Cancer , 2025 , 133 ( 12 ): 1829 - 1843 .
Hou Y L , Wu H , Zhang Z Y , et al . Bacteroides intestinalis mediates the sensitivity to irinotecan toxicity via tryptophan catabolites [J ] . Gut , 2026 , 75 ( 7 ): 1322 - 1337 .
贾颖 , 苏敏敏 , 牛亚平 , 等 . 基因多态性与伊立替康不良反应及化疗疗效相关性的研究进展 [J ] . 中国药房 , 2020 , 31 ( 11 ): 1403 - 1408 .
Peduzzi P , Concato J , Kemper E , et al . A simulation study of the number of events per variable in logistic regression analysis [J ] . J Clin Epidemiol , 1996 , 49 ( 12 ): 1373 - 1379 .
Concato J , Peduzzi P , Holford T R , et al . Importance of events per independent variable in proportional hazards analysis Ⅰ: background,goals,and general strategy [J ] . J Clin Epidemiol , 1995 , 48 ( 12 ): 1495 - 1501 .
Tian Y T . Trade-off analysis of classical machine learning and deep learning models for robust brain tumor detection:benchmark study [J ] . JMIR AI , 2025 , 4 : e76344 .
Bertsimas D , Wiberg H . Machine learning in oncology:methods,applications,and challenges [J ] . JCO Clin Cancer Inform , 2020 , 4 : 885 - 894 .
Ionescu G , Frood R , Scarsbrook A , et al . Impact of training dataset size on technical performance of a deep learning model for detection and quantification of lymphomatous disease on 18 F-FDG PET/CT [J ] . J Nucl Med , 2023 , 64 ( Suppl. ): 2 .
López-Sánchez M , Hernández-Ocaña B , Chávez-Bosquez O , et al . Supervised deep learning techniques for image description:a systematic review [J ] . Entropy(Basel) , 2023 , 25 ( 4 ): 553 .
Misera L , Müller-Franzes G , Truhn D , et al . Weakly supervised deep learning in radiology [J ] . Radiology , 2024 , 312 : e232085 .
杨帆 . 多模态医学数据融合技术及应用 [J ] . 山东大学学报(医学版) , 2025 , 63 ( 8 ): 17 - 40 .
Arango-Argoty G , Kipkogei E , Stewart R , et al . Pretrained transformers applied to clinical studies improve predictions of treatment efficacy and associated biomarkers [J ] . Nat Commun , 2025 , 16 : 2101 .
Libbrecht M W , Noble W S . Machine learning applications in genetics and genomics [J ] . Nat Rev Genet , 2015 , 16 ( 6 ): 321 - 332 .
Maimon O , Rokach L . Data mining and knowledge discovery handbook [M ] . New York : Springer US , 2005 : 809 - 835 .
Lu M Y , Williamson D F K , Chen T Y , et al . Data-efficient and weakly supervised computational pathology on whole-slide images [J ] . Nat Biomed Eng , 2021 , 5 ( 6 ): 555 - 570 .
Kazerouni A , Aghdam E K , Heidari M , et al . Diffusion models in medical imaging:a comprehensive survey [J ] . Med Image Anal , 2023 , 88 : 102846 .
Zhang C Q , Cui Y J , Han Z B , et al . Deep partial multi-view learning [J ] . IEEE Trans Pattern Anal Mach Intell , 2022 , 44 ( 5 ): 2402 - 2415 .
van Smeden M , Penning de Vries B B L , Nab L , et al . Approaches to addressing missing values,measurement error,and confounding in epidemiologic studies [J ] . J Clin Epidemiol , 2021 , 131 : 89 - 100 .
Tang S P , Davarmanesh P , Song Y M , et al . Democratizing EHR analyses with FIDDLE:a flexible data-driven preprocessing pipeline for structured clinical data [J ] . J Am Med Inform Assoc , 2020 , 27 ( 12 ): 1921 - 1934 .
Zhao F , Zhang C C , Geng B C . Deep multimodal data fusion [J ] . ACM Comput Surv , 2024 , 56 ( 9 ): 1 - 36 .
Ramachandram D , Taylor G W . Deep multimodal learning:a survey on recent advances and trends [J ] . IEEE Signal Process Mag , 2017 , 34 ( 6 ): 96 - 108 .
Kiela D , Grave E , Joulin A , et al . Efficient large-scale multi-modal classification [C/OL ] // Thirty-second AAAI Conference on Artificial Intelligence , 2018 . https://arxiv.org/pdf/1802.02892 https://arxiv.org/pdf/1802.02892 . DOI: 10.1609/aaai.v32i1.11945 http://dx.doi.org/10.1609/aaai.v32i1.11945 .
Vaezi Joze H R , Shaban A , Iuzzolino M L , et al . MMTM:multimodal transfer module for CNN fusion [C/OL ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) , 2020 . https://ieeexplore.ieee.org/document/9156844 https://ieeexplore.ieee.org/document/9156844 . DOI: 10.1109/CVPR42600.2020.01330 http://dx.doi.org/10.1109/CVPR42600.2020.01330 .
Karpathy A , Toderici G , Shetty S , et al . Large-scale video classification with convolutional neural networks [C/OL ] // 2014 IEEE Conference on Computer Vision and Pattern Recognition , 2014 . https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909619&tag=1 https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909619&tag=1 . DOI: 10.1109/CVPR. 2014.223 http://dx.doi.org/10.1109/CVPR.2014.223 .
Ramanathan T T , Hossen M J , Sayeed M S . Naïve Bayes based multiple parallel fuzzy reasoning method for medical diagnosis [J ] . J Eng Sci Technol , 2022 , 17 ( 1 ): 472 - 490 .
Efthimiou O , Seo M , Chalkou K , et al . Developing clinical prediction models:a step-by-step guide [J ] . BMJ , 2024 , 386 : e078276 .
Crowson C S , Atkinson E J , Therneau T M . Assessing calibration of prognostic risk scores [J ] . Stat Methods Med Res , 2016 , 25 ( 4 ): 1692 - 1706 .
Austin P C , Jr Harrell F E , van Klaveren D . Graphical calibration curves and the integrated calibration index(ICI)for survival models [J ] . Stat Med , 2020 , 39 ( 21 ): 2714 - 2742 .
Paul P , Pennell M L , Lemeshow S . Standardizing the power of the Hosmer-Lemeshow goodness of fit test in large data sets [J ] . Stat Med , 2013 , 32 ( 1 ): 67 - 80 .
Wang S R , Liu X Y , Yuan S H , et al . Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study [J ] . NPJ Digit Med , 2025 , 8 ( 1 ): 228 .
Steyerberg E W , Jr Harrell F E . Prediction models need appropriate internal,internal-external,and external validation [J ] . J Clin Epidemiol , 2016 , 69 : 245 - 247 .
Riley R D , Archer L , Snell K I E , et al . Evaluation of clinical prediction models:part 2:how to undertake an external validation study [J ] . BMJ , 2024 , 384 : e074820 .
Lipkova J , Chen R J , Chen B W , et al . Artificial intel-ligence for multimodal data integration in oncology [J ] . Cancer Cell , 2022 , 40 ( 10 ): 1095 - 1110 .
Chen R J , Lu M Y , Williamson D F K , et al . Pan-cancer integrative histology-genomic analysis via multimodal deep learning [J ] . Cancer Cell , 2022 , 40 ( 8 ): 865 - 878.e6 .
Donoghue M T A , Schram A M , Hyman D M , et al . Discovery through clinical sequencing in oncology [J ] . Nat Cancer , 2020 , 1 ( 8 ): 774 - 783 .
Lee E H , Han M , Wright J , et al . An international study presenting a federated learning AI platform for pediatric brain tumors [J ] . Nat Commun , 2024 , 15 ( 1 ): 7615 .
0
Views
4
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621
