
浏览全部资源
扫码关注微信
重庆医科大学附属儿童医院护理部/儿童少年健康与疾病国家临床医学研究中心/儿童发育疾病研究教育部重点实验室/儿童神经发育与认知障碍重庆市重点实验室,重庆 400014
护士,硕士研究生。研究方向:儿童肿瘤、心理护理。E-mail:2550650722@qq.com
教授,主任护师,硕士生导师,硕士。研究方向:儿童肿瘤、心理护理。E-mail:1439638239@qq.com
收稿:2025-10-19,
修回:2026-02-28,
录用:2026-03-02,
纸质出版:2026-04-15
移动端阅览
何莉,林欣,蒋小平.化疗致恶性肿瘤患儿骨髓抑制风险预测模型的系统评价 [J].中国药房,2026,37(07):954-959.
HE Li,LIN Xin,JIANG Xiaoping.Systematic review of risk prediction models for chemotherapy-induced myelosuppression in pediatric patients with malignant tumors[J].ZHONGGUO YAOFANG,2026,37(07):954-959.
何莉,林欣,蒋小平.化疗致恶性肿瘤患儿骨髓抑制风险预测模型的系统评价 [J].中国药房,2026,37(07):954-959. DOI: 10.6039/j.issn.1001-0408.2026.07.22.
HE Li,LIN Xin,JIANG Xiaoping.Systematic review of risk prediction models for chemotherapy-induced myelosuppression in pediatric patients with malignant tumors[J].ZHONGGUO YAOFANG,2026,37(07):954-959. DOI: 10.6039/j.issn.1001-0408.2026.07.22.
目的
2
系统评价儿童恶性肿瘤化疗后骨髓抑制风险预测模型的建模策略、关键预测因子与预测性能,为临床决策与研究提供循证依据。
方法
2
检索2025年4月之前发表于中国知网、万方数据、PubMed等11个数据库中的相关文献。文献筛选和信息提取由2位研究人员独立完成,模型的偏倚风险和适用性依照PROBAST工具进行严格评估。
结果
2
最终筛选得到7项研究,其中英文文献4篇、中文文献3篇,涉及12个风险预测模型。多数模型在判别能力方面表现良好,受试者工作特征曲线下面积(AUC)为0.748~0.981,但仅有2项研究实施了外部验证;有3项研究未充分报告模型的校准信息。PROBAST评估结果显示,所有模型在偏倚风险方面均为高水平,主要问题包括以回顾性设计为主、样本代表性不足以及缺乏盲法评估等;但在适用性方面,所有模型的评价结果均为良好。在建模方法方面,多数研究采用传统logistic回归方法构建模型,仅少数研究引入了机器学习算法并对多种算法进行了系统性比较;采用机器学习方法的模型表现明显优于传统统计方法构建的模型。
结论
2
现有的儿童恶性肿瘤化疗后骨髓抑制风险预测模型在临床风险预警中显示出潜力,但普遍存在以回顾性单中心设计为主、每变量事件数较低、缺失数据处理不透明、模型系数报告不一致等设计与方法学局限。未来研究应推进前瞻性设计,融合机器学习与关键临床变量,并严格遵循TRIPOD声明等报告规范,以提升模型的科学严谨性与临床适用性。
OBJECTIVE
2
To systematically evaluate risk prediction models for chemotherapy-induced myelosuppression in pediatric patients with malignant tumors, evaluate their modeling strategies, key predictors, and predictive performance, and provide evidence-based references for clinical decision-making and research.
METHODS
2
A literature search was conducted across 11 databases, including CNKI, Wanfang Data, and PubMed, for relevant studies published before April 2025. Two reviewers independently performed literature screening and data extraction, and the risk of bias and applicability of the models were evaluated using the PROBAST tool.
RESULTS
2
Ultimately, seven studies were selected, of which four were English articles and three were Chinese articles, involving 12 risk prediction models. Although model discrimination was good (AUC 0.748-0.981), only two models underwent external validation; furthermore, calibration was inadequately reported in three studies. PROBAST indicated that all models exhibited a high risk of bias, with major issues including a predominance of retrospective designs, inadequate sample representativeness, and lack of blinding. However, in terms of applicability, all models received favorable evaluations. In terms of modeling methods, most studies employed traditional logistic regression approaches to construct models, while only a minority introduced machine learning algorithms and conducted systematic comparisons among multiple algorithms. Models developed using machine learning methods significantly outperformed those constructed with traditional statistical methods.
CONCLUSIONS
2
The existing risk prediction models for myelosuppression after chemotherapy in children with malignant tumors demonstrate potential in clinical risk early warning. However, they generally suffer from design and methodological limitations, such as a predominance of retrospective single-center designs, few events per variable, opaque handling of missing data, and inconsistent reporting of model coefficients. Future studies should adopt prospective designs, incorporate machine learning with key clinical predictors, and follow TRIPOD reporting guidelines to enhance scientific rigor and clinical utility.
倪鑫 . 国家儿童肿瘤监测年报:2022 [M ] . 北京 : 人民卫生出版社 , 2022 : 4 .
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 , 2023 , 15 ( 4 ): 1078 .
QIU B , MATTHAY K K . Advancing therapy for neuroblastoma [J ] . Nat Rev Clin Oncol , 2022 , 19 ( 8 ): 515 - 533 .
HUANG J T , LU S Y , WANG J , et al . A multicenter phase Ⅱ trial of primary prophylactic PEG-rhG-CSF in pedi- atric patients with solid tumors and non-Hodgkin lymphoma after chemotherapy:an interim analysis [J ] . Cancer Med , 2023 , 12 ( 13 ): 14130 - 14137 .
刘若彤 . 肿瘤患儿化疗后骨髓抑制合并医院感染临床特点及风险预测模型建立的研究 [D ] . 济南 : 山东大学 , 2024 .
SALVADOR C , MERYK A , HETZER B , et al . Immature platelet fraction predicts early marrow recovery after severe chemotherapy associated neutropenia [J ] . Sci Rep , 2023 , 13 ( 1 ): 3371 .
GURUMURTHY G , GURUMURTHY J , GURUMURTHY S . Machine learning in paediatric haematological malignancies:a systematic review of prognosis,toxicity and treatment response models [J ] . Pediatr Res , 2025 , 97 ( 2 ): 524 - 531 .
刘阳 , 李红健 , 吴建华 , 等 . 乳腺癌化疗致骨髓抑制风险预测模型的系统评价 [J ] . 中国药房 , 2025 , 36 ( 5 ): 612 - 618 .
WHO Classification of Tumours Editorial Board . WHO classification of paediatric tumours [EB/OL ] .[ 2026-03-18 ] . https://publications.iarc.who.int/Book-And-Report-Series/Who-Classification-Of-Tumours https://publications.iarc.who.int/Book-And-Report-Series/Who-Classification-Of-Tumours .
MOONS K G M , DE GROOT J A H , BOUWMEESTER W , et al . Critical appraisal and data extraction for systematic reviews of prediction modelling studies:the CHARMS checklist [J ] . PLoS Med , 2014 , 11 ( 10 ): e1001744 .
陈香萍 , 张奕 , 庄一渝 , 等 . PROBAST:诊断或预后多因素预测模型研究偏倚风险的评估工具 [J ] . 中国循证医学杂志 , 2020 , 20 ( 6 ): 737 - 744 .
李祎涵 . 基于自我报告的血液肿瘤患儿治疗相关发热性中性粒细胞减少的预测模型研究 [D ] . 上海 : 上海交通大学 , 2022 .
徐蕊 . 淋巴系恶性肿瘤患者大剂量甲氨蝶呤化疗后不良反应预测模型的初步建立 [D ] . 乌鲁木齐 : 新疆医科大学 , 2018 .
MIEDEMA K G E , DE BONT E S J M , OUDE NIJHUIS C S M , et al . Validation of a new risk assessment model for predicting adverse events in children with fever and chemotherapy-induced neutropenia [J ] . J Clin Oncol , 2011 , 29 ( 7 ): e182 - e184 .
LYMAN G H , PONIEWIERSKI M S . A patient risk model of chemotherapy-induced febrile neutropenia:lessons learned from the ANC study group [J ] . J Natl Compr Canc Netw , 2017 , 15 ( 12 ): 1543 - 1550 .
WICKI S , KEISKER A , AEBI C , et al . Risk prediction of fever in neutropenia in children with cancer:a step towards individually tailored supportive therapy [J ] . Pediatr Blood Cancer , 2008 , 51 ( 6 ): 778 - 783 .
JIA H Y , LIANG L , CHEN X , et al . Predictive value of peri-chemotherapy hematological parameters for febrile neutropenia in patients with cancer [J ] . Front Oncol , 2024 , 14 : 1380195 .
VENÄLÄINEN M S , HEERVÄ E , HIRVONEN O , et al . Improved risk prediction of chemotherapy-induced neutropenia-model development and validation with real-world data [J ] . Cancer Med , 2022 , 11 ( 3 ): 654 - 663 .
CHEN W Q , PENG L , ZENG X L , et al . Predictors of myelosuppression for patients with head and neck squamous cell carcinoma after induction chemotherapy [J ] . Clin Med Insights Oncol , 2024 , 18 : 11795549231219497 .
MIELNIK M , PODGAJNA-MIELNIK M , SZUDY-SZCZYREK A , et al . Predicting chemotherapy toxicity in multiple myeloma:the prognostic value of pre-treatment serum cytokine levels of interleukin-6,interleukin-8,monocyte chemoattractant protein-1,and vascular endothelial growth factor [J ] . Front Immunol , 2024 , 15 : 1377546 .
AL TAWIL A , ALMAZAYDEH L , ALQUDAH B , et al . Predictive modeling for breast cancer based on machine learning algorithms and features selection methods [J ] . Int J Electr Comput Eng , 2024 , 14 ( 2 ): 1937 .
XIAO J L , MO M , WANG Z Z , et al . The application and comparison of machine learning models for the prediction of breast cancer prognosis:retrospective cohort study [J ] . JMIR Med Inform , 2022 , 10 ( 2 ): e33440 .
MONIRUJJAMAN KHAN M , ISLAM S , SARKAR S , et al . Machine learning based comparative analysis for breast cancer prediction [J ] . J Healthc Eng , 2022 , 2022 : 4365855 .
LOBATO-DELGADO B , PRIEGO-TORRES B , SANCHEZ- MORILLO D . Combining molecular,imaging,and clinical data analysis for predicting cancer prognosis [J ] . Cancers , 2022 , 14 ( 13 ): 3215 .
BUICK J E , AUSTIN P C , CHESKES S , et al . Prediction models in prehospital and emergency medicine research:how to derive and internally validate a clinical prediction model [J ] . Acad Emerg Med , 2023 , 30 ( 11 ): 1150 - 1160 .
TOUSIGNANT-LAFLAMME Y , HOULE C , COOK C , et al . Mastering prognostic tools:an opportunity to enhance personalized care and to optimize clinical outcomes in physical therapy [J ] . Phys Ther , 2022 , 102 ( 5 ): pzac023 .
MISHRA A , MCCLELLAND R L , INOUE L Y T , et al . Recalibration methods for improved clinical utility of risk scores [J ] . Med Decis Making , 2022 , 42 ( 4 ): 500 - 512 .
DHIMAN P , MA J , ANDAUR NAVARRO C L , et al . Risk of bias of prognostic models developed using machine learning:a systematic review in oncology [J ] . Diagn Progn Res , 2022 , 6 ( 1 ): 13 .
BRACHER-SMITH M , CRAWFORD K , ESCOTT-PRICE V . Machine learning for genetic prediction of psychiatric disorders:a systematic review [J ] . Mol Psychiatry , 2021 , 26 ( 1 ): 70 - 79 .
COLLINS G S , DHIMAN P , ANDAUR NAVARRO C L , et al . Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence [J ] . BMJ Open , 2021 , 11 ( 7 ): e048008 .
0
浏览量
101
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