Page 94 - 《中国药房》2026年2期

·智慧药学·

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 Δ

1 #
张靖悦 ，张涵煦 ，杨 翀 ，孙银娟 ，钟殿胜 ，张琳琳 ，袁恒杰 （1. 天津医科大学总医院药剂科，天津
1＊
2
3
1
3
3
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）
中图分类号 R911 文献标志码 A 文章编号 1001-0408（2026）02-0220-06
DOI 10.6039/j.issn.1001-0408.2026.02.15
摘 要 目的 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 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 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 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。
关键词 高致吐性化疗；化疗相关性恶心呕吐；神经激肽1受体拮抗剂；5-羟色胺3受体拮抗剂；地塞米松；预测模型

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
1
2
ZHANG Jingyue ，ZHANG Hanxu ，YANG Chong ，SUN Yinjuan ，ZHONG Diansheng ，ZHANG Linlin ，YUAN
1
3
3
3
Hengjie（1. Dept. of Pharmacy， Tianjin Medical University General Hospital， Tianjin 300052， China；2. Dept. of
1
Pharmacy， Tianjin Huanhu Hospital， Tianjin 300350， China；3. Dept. of Medical Oncology， Tianjin Medical
University General Hospital， Tianjin 300052， China）
ABSTRACT OBJECTIVE 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 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 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.
Δ 基金项目 国家自然科学基金项目（No.72404207） CONCLUSIONS The deep random forest model exhibits the
＊第一作者 副主任药师，硕士。研究方向：医院药学。E-mail：
best performance in predicting the efficacy of triple antiemetic
13032286389@163.com
# 通信作者 主任药师，硕士生导师，博士。研究方向：临床药学。 regimen for preventing HEC-related nausea and vomiting. The
电话：022-60362951。E-mail：yuanhengjie006@sina.com key predictors in this model primarily include Ccr，

· 220 · China Pharmacy 2026 Vol. 37 No. 2 中国药房 2026年第37卷第2期