Page 120 - 《中国药房》2026年1期

tion with enalapril：the International CardioOncology learning approach for modeling myelosuppression at-
Society-one trial[J]. Eur J Cancer，2018，94：126-137. tributed to nimustine hydrochloride[J]. JCO Clin Cancer
[25] CHAIX M A，PARMAR N，KINNEAR C，et al. Machine Inform，2018，2：1-21.
learning identifies clinical and genetic factors associated [36] LAVIERI L，KOENIG C，BODMER N，et al. Predicting
with anthracycline cardiotoxicity in pediatric cancer survi‐ fever in neutropenia with safety-relevant events in chil‐
vors[J]. JACC CardioOncol，2020，2（5）：690-706. dren undergoing chemotherapy for cancer：the prospective
[26] ÖZTÜRK C，VALIDYEV D，BECHER U M，et al. A multicenter SPOG 2015 FN Definition Study[J]. Pediatr
novel scoring system to estimate chemotherapy-induced Blood Cancer，2021，68（12）：e29253.
myocardial toxicity：risk assessment prior to non- [37] LI M J，WANG Q，LU P，et al. Development of a machine
anthracycline chemotherapy regimens[J]. Int J Cardiol learning-based prediction model for chemotherapy-
Heart Vasc，2021，33：100751. induced myelosuppression in children with Wilms’ tumor
[27] LI C，CHEN L，CHOU C，et al. Using machine learning [J]. Cancers （Basel），2023，15（4）：1078.
approaches to predict short-term risk of cardiotoxicity [38] MAGNUSON A，SEDRAK M S，GROSS C P，et al. De‐
among patients with colorectal cancer after starting velopment and validation of a risk tool for predicting se‐
fluoropyrimidine-based chemotherapy[J]. Cardiovasc vere toxicity in older adults receiving chemotherapy for
Toxicol，2022，22（2）：130-140. early-stage breast cancer[J]. J Clin Oncol，2021，39（6）：
[28] YUE X N，YAN C，LIU X Y. Construction of a risk predic‐ 608-618.
tion model for chemotherapy-induced cardiotoxicity in [39] WU Y F，ZHAO W，ZHANG L X，et al. Machine learning
breast cancer patients based on machine learning algorithm models for predicting chemotherapy-induced adverse drug
[J]. Zhonghua Xin Xue Guan Bing Za Zhi，2025，53（8）： reactions in colorectal cancer patients[J]. Dig Liver Dis，
898-905. 2025，57（9）：1845-1852.
[29] HEILBRONER S P，FEW R，MUELLER J，et al. Predic- [40] CUI L Q，ZHU M，WANG T L，et al. Clinical prediction
ting cardiac adverse events in patients receiving immune of sodium valproate-induced movement disorders in hospi‐
checkpoint inhibitors：a machine learning approach[J]. J talized patients：a nomogram-based model using real-
Immunother Cancer，2021，9（10）：e002545. world data[J]. Int J Clin Pharm，2025，47（6）：1841-1851.
[30] ARAÚJO D C，SIMÕES R，DE PAULA SABINO A， [41] CHO Y A，MOON Y，PARK W，et al. Factors inducing cu‐
et al. Predicting doxorubicin-induced cardiotoxicity in taneous adverse reactions in cancer patients treated with
breast cancer：leveraging machine learning with synthetic PD-1 and PD-L1 inhibitors：a machine-learning algorithm
data[J]. Med Biol Eng Comput，2025，63（5）：1535-1550. approach[J]. Immunopharmacol Immunotoxicol，2025，47
[31] 朱荟萃，杨静. 抗肿瘤药物引起骨髓抑制的中西医治疗 （1）：53-58.
研 究 进 展 [J]. 中 西 医 结 合 研 究 ，2024，16（4）：245- [42] COLLINS G S，REITSMA J B，ALTMAN D G，et al.
249，254. Transparent reporting of a multivariable prediction model
[32] 刘阳，骆亭亭，李红健，等 . 乳腺癌 AC-T 化疗方案致骨 for individual prognosis or diagnosis （TRIPOD）：the
髓抑制的危险因素分析及其风险预测模型的构建[J]. 中 TRIPOD statement[J]. BMJ，2015，350：g7594.
国医院药学杂志，2024，44（21）：2503-2511. [43] 国家卫生健康委，国家中医药局，国家疾控局.卫生健康
[33] JIANG D，SONG Z W，LIU P，et al. A prediction model 行业人工智能应用场景参考指引[EB/OL]. [2025-07-23].
for severe hematological toxicity of BTK inhibitors[J]. https：//www.nhc.gov.cn/guihuaxxs/c100133/202411/3dee-
Ann Hematol，2023，102（10）：2765-2777. 425b8dc34f739d63483c4e5c334c.shtml.
[34] VAN DUNG H，TAN V M，DIEU N T，et al. Development [44] ZHOU H J，LIU F L，WU J G，et al. A collaborative large
and external validation of a machine learning model for language model for drug analysis[J]. Nat Biomed Eng，
predicting drug-induced immune thrombocytopenia in a 2025：1-12.
real-world hospital cohort[J]. BMC Med Inform Decis （收稿日期：2025-08-06 修回日期：2025-12-11）
Mak，2025，25（1）：265. （编辑：唐晓莲）
[35] SHIBAHARA T，IKUTA S，MURAGAKI Y. Machine-

· 110 · China Pharmacy 2026 Vol. 37 No. 1 中国药房 2026年第37卷第1期