
浏览全部资源
扫码关注微信
1.天津医科大学总医院药剂科,天津 300052
2.天津市环湖医院药剂科,天津 300350
3.天津医科大学总医院肿瘤科,天津 300052
副主任药师,硕士。研究方向:医院药学。E-mail:13032286389@163.com
主任药师,硕士生导师,博士。研究方向:临床药学。电话:022-60362951。E-mail:yuanhengjie006@sina.com
收稿:2025-07-22,
修回:2025-08-13,
录用:2025-10-11,
纸质出版:2026-01-30
移动端阅览
张靖悦,张涵煦,杨翀,等.神经激肽1受体拮抗剂联合5-羟色胺3受体拮抗剂、地塞米松预防HEC相关性恶心呕吐的有效性预测模型研究 [J].中国药房,2026,37(02):220-225.
ZHANG Jingyue,ZHANG Hanxu,YANG Chong,et al.Study on the predictive model for the efficacy of neurokinin-1 receptor antagonists combined with 5-hydroxytryptamine 3 receptor antagonists and dexamethasone for preventing nausea and vomiting induced by highly emetogenic chemotherapy[J].ZHONGGUO YAOFANG,2026,37(02):220-225.
张靖悦,张涵煦,杨翀,等.神经激肽1受体拮抗剂联合5-羟色胺3受体拮抗剂、地塞米松预防HEC相关性恶心呕吐的有效性预测模型研究 [J].中国药房,2026,37(02):220-225. DOI: 10.6039/j.issn.1001-0408.2026.02.15.
ZHANG Jingyue,ZHANG Hanxu,YANG Chong,et al.Study on the predictive model for the efficacy of neurokinin-1 receptor antagonists combined with 5-hydroxytryptamine 3 receptor antagonists and dexamethasone for preventing nausea and vomiting induced by highly emetogenic chemotherapy[J].ZHONGGUO YAOFANG,2026,37(02):220-225. DOI: 10.6039/j.issn.1001-0408.2026.02.15.
目的
2
构建一种基于可解释深度学习的预测模型,用于评估三联止吐方案(神经激肽1受体拮抗剂+5-羟色胺3受体拮抗剂+地塞米松)预防高致吐性化疗(HEC)相关性恶心呕吐的有效性。
方法
2
回顾性收集2018年1月至2022年12月就诊于天津医科大学总医院肿瘤科接受HEC且采用三联止吐方案的癌症患者的临床数据,整合人口学、临床及代谢等相关变量,数据预处理后,分别采用深度随机森林和全连接神经网络2种深度学习算法以及4种机器学习算法(支持向量机、分类提升、随机森林、决策树)构建预测模型,并进行模型性能评估和模型可解释性分析。
结果
2
6种模型中,深度随机森林模型在测试集中表现出最优预测性能,受试者工作特征曲线下面积为0.850,准确率为0.911,精确率为0.805,召回率为0.783,F1值为0.793,Brier评分为0.075。该模型可解释性分析结果表明,肌酐清除率(Ccr)为关键预测因子,低Ccr水平、女性、低龄患者、高致吐性药物(特别是含顺铂化疗方案)、存在预期性恶心呕吐与HEC相关性恶心呕吐的发生风险呈正相关。
结论
2
深度随机森林模型在预测三联止吐方案预防HEC相关性恶心呕吐的有效性方面表现最优,该模型关键预测因子以Ccr、预期性恶心呕吐、性别、年龄、高致吐性药物为主。
OBJECTIVE
2
To construct a predictive model for evaluating the efficacy of a triple antiemetic regimen (neurokinin-1 receptor antagonist+5-hydroxytryptamine 3 receptor antagonist+dexamethasone) for preventing nausea and vomiting induced by highly emetogenic chemotherapy (HEC) based on interpretable deep learning algorithms.
METHODS
2
Clinical data of cancer patients who received HEC and were treated with the standard triple antiemetic regimen in the oncology department of Tianjin Medical University General Hospital from January 2018 to December 2022 were collected retrospectively. Demographic, clinical and metabolism-related variables were integrated. After data pre-processing, two deep learning algorithms (deep random forest and dense neural network) and four machine learning algorithms (support vector machine, categorical boosting, random forest and decision tree) were used to build predictive models. Subsequently, model performance evaluation and model interpretability analysis were conducted.
RESULTS
2
Among the six candidate models, the deep random forest model demonstrated the best predictive performance on the test set, with an area under the receiver operating characteristic curve of 0.850, an accuracy of 0.911, a precision of 0.805, a recall of 0.783, an F1 score of 0.793, and a Brier score of 0.075. Interpretability analysis revealed that creatinine clearance rate (Ccr) was the key predictive factor, and low Ccr levels, female gender, younger age, highly emetogenic drugs (particularly cisplatin-containing chemotherapy regimens), and anticipatory nausea and vomiting were positively correlated with the risk of HEC-related nausea and vomiting.
CONCLUSIONS
2
The deep random forest model exhibits the best performance in predicting the efficacy of triple antiemetic regimen for preventing HEC-related nausea and vomiting. The key predictors in this model primarily include Ccr, anticipatory nausea and vomiting, gender, age, and highly emetogenic drugs.
PIECHOTTA V , ADAMS A , HAQUE M , et al . Antiem-etics for adults for prevention of nausea and vomiting caused by moderately or highly emetogenic chemotherapy:a network meta-analysis [J ] . Cochrane Database Syst Rev , 2021 , 11 ( 11 ): CD012775 .
KENNEDY S K F , GOODALL S , LEE S F , et al . 2020 ASCO,2023 NCCN,2023 MASCC/ESMO,and 2019 CCO:a comparison of antiemetic guidelines for the treatment of chemotherapy-induced nausea and vomiting in cancer patients [J ] . Support Care Cancer , 2024 , 32 ( 5 ): 280 .
YEO W , NGAI N T Y , YIP C C H , et al . Risk factors associa-ted with chemotherapy-induced nausea and vomiting among women with breast cancer receiving highly emetogenic chemotherapy:individual patient-based analysis of three prospective antiemetic trials [J ] . Cancer Manag Res , 2024 , 16 : 283 - 297 .
MOSA A S M , HOSSAIN A M , LAVOIE B J , et al . Patient-related risk factors for chemotherapy-induced nausea and vomiting:a systematic review [J ] . Front Pharmacol , 2020 , 11 : 329 .
KHOSRAVI B , WESTON A D , NUGEN F , et al . Demys-tifying statistics and machine learning in analysis of structured tabular data [J ] . J Arthroplasty , 2023 , 38 ( 10 ): 1943 - 1947 .
EGGER J , GSAXNER C , PEPE A , et al . Medical deep learning:a systematic meta-review [J ] . Comput Methods Programs Biomed , 2022 , 221 : 106874 .
QAMAR T , BAWANY N Z . Understanding the black-box:towards interpretable and reliable deep learning models [J ] . PeerJ Comput Sci , 2023 , 9 : e1629 .
ROBSON B , COOPER R . Glass box and black box machine learning approaches to exploit compositional des-criptors of molecules in drug discovery and aid the medicinal chemist [J ] . ChemMedChem , 2024 , 4 : e202400169 .
MUL FEDELE M L , DEL PILAR LÓPEZ GABEIRAS M , SIMONELLI G , et al . Multivariate analysis of the impact of sleep and working hours on medical errors:a MICE approach [J ] . BMC Public Health , 2023 , 23 ( 1 ): 2317 .
ALKHAWALDEH I M , ALBALKHI I , NASWHAN A J . Challenges and limitations of synthetic minority oversampling techniques in machine learning [J ] . World J Metho-dol , 2023 , 13 ( 5 ): 373 - 378 .
ZHOU Z H , FENG J . Deep forest [J ] . Natl Sci Rev , 2019 , 6 ( 1 ): 74 - 86 .
LUNDBERG S M , ERION G , CHEN H , et al . From local explanations to global understanding with explainable AI for trees [J ] . Nat Mach Intell , 2020 , 2 ( 1 ): 56 - 67 .
DRANITSARIS G , MOLASSIOTIS A , CLEMONS M , et al . The development of a prediction tool to identify cancer patients at high risk for chemotherapy-induced nausea and vomiting [J ] . Ann Oncol , 2017 , 28 ( 6 ): 1260 - 1267 .
HU Z H , LIANG W H , YANG Y P , et al . Personalized estimate of chemotherapy-induced nausea and vomiting:development and external validation of a nomogram in cancer patients receiving highly/moderately emetogenic chemotherapy [J ] . Medicine , 2016 , 95 ( 2 ): e2476 .
AGUIAR ZDOVC J , VAUPOTIČ M , MAROLT G , et al . Population pharmacokinetics of cisplatin in small cell lung cancer patients guided with informative priors [J ] . Cancer Chemother Pharmacol , 2022 , 90 ( 4 ): 301 - 313 .
BÉGUIN J , MAHFOUDHI S , UZEL M , et al . Population pharmacokinetics modelling for clinical dose adjustment of carboplatin in dogs [J ] . BMC Vet Res , 2024 , 20 ( 1 ): 575 .
IMAMURA Y , KIYOTA N , TAHARA M , et al . Effect of acute kidney injury and overall survival in patients with postoperative head and neck cancer who received chemoradiotherapy with cisplatin:a supplementary analysis of the phase Ⅱ/Ⅲ trial of JCOG1008 [J ] . Cancer Med , 2024 , 13 ( 18 ): e70235 .
中国药学会医院药学专业委员会 . 化疗所致恶心呕吐的药物防治指南 [J ] . 中国医院药学杂志 , 2022 , 42 ( 5 ): 457 - 473 .
程颖 , 柳菁菁 . 《中国肿瘤药物治疗相关恶心呕吐防治专家共识(2022年版)》解读 [J ] . 临床内科杂志 , 2023 , 40 ( 5 ): 351 - 353 .
NAVARI R M , AAPRO M . Antiemetic prophylaxis for chemotherapy-induced nausea and vomiting [J ] . N Engl J Med , 2016 , 374 ( 14 ): 1356 - 1367 .
PETCH J , DI S , NELSON W . Opening the black box:the promise and limitations of explainable machine learning in cardiology [J ] . Can J Cardiol , 2022 , 38 ( 2 ): 204 - 213 .
BLACKMAN J , VEERAPEN R . On the practical,ethical,and legal necessity of clinical artificial intelligence explainability:an examination of key arguments [J ] . BMC Med Inform Decis Mak , 2025 , 25 ( 1 ): 111 .
SAKAI C , SHIMOKAWA M , IIHARA H , et al . Low-dose olanzapine plus granisetron and dexamethasone for carboplatin-induced nausea and vomiting in patients with thoracic malignancies:a prospective multicenter phase Ⅱ trial [J ] . Oncologist , 2021 , 26 ( 6 ): e1066 - e1072 .
SARMA I D , BURAGOHAIN S , LAHON J , et al . Aprepitant versus olanzapine in patients of breast cancer on adriamycin and cyclophosphamide regimen:role in effectiveness of prevention of nausea and vomiting [J ] . Acta Med Litu , 2025 , 32 ( 1 ): 118 - 119 .
BOURDEANU L , FRANKEL P , YU W , et al . Chemotherapy-induced nausea and vomiting in Asian women with breast cancer receiving anthracycline-based adjuvant chemotherapy [J ] . J Support Oncol , 2012 , 10 ( 4 ): 149 - 154 .
KAISER R , SEZER O , PAPIES A , et al . Patient-tailored antiemetic treatment with 5-hydroxytryptamine type 3 receptor antagonists according to cytochrome P-450 2D6 genotypes [J ] . J Clin Oncol , 2002 , 20 ( 12 ): 2805 - 2811 .
PERWITASARI D A , GELDERBLOM H , ATTHOBARI J , et al . Anti-emetic drugs in oncology:pharmacology and individualization by pharmacogenetics [J ] . Int J Clin Pharm , 2011 , 33 ( 1 ): 33 - 43 .
ELIASEN A , DALHOFF K , MATHIASEN R , et al . Pharmacogenetics of antiemetics for chemotherapy-induced nausea and vomiting:a systematic review and meta-analysis [J ] . Crit Rev Oncol Hematol , 2020 , 149 : 102939 .
MEHROTRA S , SHARMA M R , GRAY E , et al . Kinetic-pharmacodynamic model of chemotherapy-induced peripheral neuropathy in patients with metastatic breast cancer treated with paclitaxel,nab-paclitaxel,or ixabepilone:CALGB 40502 (alliance) [J ] . AAPS J , 2017 , 19 ( 5 ): 1411 - 1423 .
0
浏览量
27
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621