乳腺癌内分泌治疗患者骨关节症状风险预测模型的构建与初步验证

doi:10.3761/j.issn.0254-1769.2026.04.009

摘要/Abstract

摘要：

目的构建并初步验证乳腺癌内分泌治疗患者骨关节症状风险预测模型，为临床早期预防内分泌治疗相关骨关节症状提供依据。方法采用前瞻性研究设计，从2023年4月—2024年1月，采用便利抽样法，选取在上海市某三级甲等医院连续入组262例乳腺癌术后内分泌治疗的患者为调查对象，在基线采集相关社会人口学资料、临床资料及骨关节症状信息，每3个月随访评估患者的骨关节症状发生情况，共计随访1年。按照7∶3的比例随机分为训练集和测试集，采用6种生存机器学习算法训练模型。结果共纳入262例患者，发现XGBoost生存机器学习算法表现最佳，在训练集、Bootstrap训练集和测试集中预测内分泌治疗12个月骨关节症状发生的受试者操作特征曲线下面积分别是0.812、0.815和0.753，在训练集和测试集中Bootstrap校准曲线的Brier评分分别是0.184和0.219。此外，XGBoost能准确划分乳腺癌内分泌治疗患者12个月内骨关节症状发生风险的高低，在训练集和测试集中Log-rank检验P值分别为<0.001和0.024。预测因子的重要性排序依次为骨密度、睡眠质量、焦虑抑郁、内分泌药物类型、孕激素受体表达、经济压力、BMI和关节炎史。结论该研究构建的乳腺癌内分泌治疗患者骨关节症状风险预测模型具有较好的预测性能，可为早期识别和预防骨关节症状提供决策依据。

关键词: 乳腺癌, 内分泌治疗, 骨关节症状, 机器学习, 预测模型, 护理

Abstract:

Objective To develop and preliminarily validate a risk prediction model for musculoskeletal symptoms in breast cancer patients undergoing endocrine therapy，providing a basis for early clinical prevention of endocrine therapy-related musculoskeletal symptoms. Methods This was a prospective study，and 262 patients with early-stage breast cancer who were undergoing postoperative endocrine therapy were consecutively enrolled in a tertiary hospital in Shanghai from April 2023 to January 2024. Sociodemographic data，clinical data，and information on musculoskeletal symptoms were collected at baseline. Then，we followed up the occurrence of musculoskeletal symptoms among these participants every 3 months，with a total period of one-year therapy. The samples were randomly divided into a training set and a test set at a ratio of 7∶3. Totally 6 survival machine learning algorithms were used to construct risk prediction models. Results There were 262 patients included in this study. The results showed that the XGBoost survival machine learning algorithm performed the best. The areas under the receiver operating characteristic（ROC） curve（AUC） for predicting the risk of musculoskeletal symptoms after 12 months of endocrine therapy were 0.812（training set），0.815（bootstrap training set），and 0.753（test set），respectively. The brier scores of the bootstrap calibration curves in the training set and test set were 0.184 and 0.219，respectively. In addition，XGBoost model could accurately classify the risk levels of the musculoskeletal symptoms. The P-values of the Log-rank test in the training set and the test set are <0.001 and 0.024 respectively. The importance of the predictors was ranked in the following order：bone mineral density，sleep quality，anxiety and depression，type of endocrine agent，progesterone receptor expression，financial stress，BMI，and history of arthritis. Conclusion This study developed a risk prediction model for musculoskeletal symptoms among breast cancer patients with endocrine therapy，showing a well predictive performance，which could contribute to providing nursing decision and making bases for the early identification and prevention of musculoskeletal symptoms.

Key words: Breast Cancer, Endocrine Therapy, Musculoskeletal Symptoms, Machine Learning, Prediction Model, Nursing Care

荆凤, 蒋凌云, 曹玉伶, 田茂婷, 裘佳佳, 汤立晨, 胡雁. 乳腺癌内分泌治疗患者骨关节症状风险预测模型的构建与初步验证[J]. 中华护理杂志, 2026, 61(4): 498-505.

JING Feng, JIANG Lingyun, CAO Yuling, TIAN Maoting, QIU Jiajia, TANG Lichen, HU Yan. Development and preliminary validation of a risk prediction model for musculoskeletal symptoms among breast cancer patients with endocrine therapy[J]. Chinese Journal of Nursing, 2026, 61(4): 498-505.

图/表 2

表1 乳腺癌内分泌治疗患者的一般资料及骨关节症状发生的单因素Cox回归分析（n=262）

Table 1 Baseline characteristics of breast cancer patients with endocrine therapy and univariate Cox regression analysis of musculoskeletal symptoms（n=262）

图1 训练集和测试集中预测模型的ROC曲线注：ROC为受试者操作特征，AUC为ROC曲线下面积。

Figure 1 ROC curves of the predictive model in the training and test sets

参考文献 28

[1]	Beckwée D, Leysen L, Meuwis K, et al. Prevalence of aromatase inhibitor-induced arthralgia in breast cancer:a systematic review and meta-analysis[J]. Support Care Cancer, 2017, 25(5):1673-1686. DOI PMID
[2]	荆凤, 王园园, 邢唯杰, 等. 乳腺癌患者芳香化酶抑制剂诱导的骨关节症状预防和管理的证据总结[J]. 中华护理杂志, 2023, 58(7):808-815. DOI URL
	Jing F, Wang YY, Xing WJ, et al. Evidence summary of the prevention and management in breast cancer patients for aroma-tase inhibitors-induced musculoskeletal symptoms[J]. Chin J Nurs, 2023, 58(7):808-815.
[3]	Seneviratne S, Campbell I, Scott N, et al. Adherence to adjuvant endocrine therapy:is it a factor for ethnic differences in breast cancer outcomes in New Zealand?[J]. Breast, 2015, 24(1):62-67. DOI PMID
[4]	Yuan XF, Xu QR, Du FX, et al. Development and validation of a model to predict cognitive impairment in traumatic brain injury patients:a prospective observational study[J]. EClinical-Medicine, 2025,80:103023.
[5]	Jing F, Jiang LY, Cao YL, et al. Musculoskeletal symptoms asso-ciated with aromatase inhibitors in the treatment of early breast cancer:a scoping review of risk factors and outcomes[J]. Support Care Cancer, 2025, 33(2):124.
[6]	Sautner J, Andel I, Rintelen B, et al. Development of the M-SACRAH,a modified,shortened version of SACRAH (Score for the Assessment and Quantification of Chronic Rheumatoid Af-fections of the Hands)[J]. Rheumatology, 2004, 43(11):1409-1413. DOI URL
[7]	Bellamy N, Buchanan WW, Goldsmith CH, et al. Validation study of WOMAC:a health status instrument for measuring clinically important patient relevant outcomes to antirheumatic drug therapy in patients with osteoarthritis of the hip or knee[J]. J Rheu-matol, 1988, 15(12):1833-1840.
[8]	Symonds T, Hughes B, Liao SM, et al. Validation of the Chinese western Ontario and McMaster Universities Osteoarthritis Index in patients from mainland China with osteoarthritis of the knee[J]. Arthritis Care Res, 2015, 67(11):1553-1560. DOI URL
[9]	Kroenke K, Spitzer RL, Williams JBW, et al. An Ultra-Brief Scree-ning Scale for Anxiety and Depression:the PHQ-4[J]. Psycho-somatics, 2009, 50(6):613-621.
[10]	Kanis JA. Assessment of fracture risk and its application to screening for postmenopausal osteoporosis:synopsis of a WHO report[J]. Osteoporos Int, 1994, 4(6):368-381. DOI PMID
[11]	国家肿瘤质控中心乳腺癌专家委员会. 中国乳腺癌随诊随访与健康管理指南(2022版)[J]. 中华肿瘤杂志, 2022, 44(1):1-28.
	Breast Cancer Expert Committee of National Cancer Quality Control Center. Comprehensive management guideline for breast cancer follow-up and healthcare(2022 edition)[J]. Chin J Oncol, 2022, 44(1):1-28.
[12]	Kanematsu M, Morimoto M, Honda J, et al. The time since last menstrual period is important as a clinical predictor for non-steroidal aromatase inhibitor-related arthralgia[J]. BMC Cancer, 2011,11:436.
[13]	Egawa C, Hirokaga K, Takao S, et al. Risk factors for joint sym-ptoms in postmenopausal Japanese breast cancer patients trea-ted with anastrozole:a prospective multicenter cohort study of patient-reported outcomes[J]. Int J Clin Oncol, 2016, 21(2):262-269. DOI URL
[14]	Ramchand SK. Optimising bone health during endocrine the-rapy for hormone sensitive cancer[J]. Endocrinology Today, 2021, 10(4):14-18.
[15]	Muslimani AA, Spiro TP, Chaudhry AA, et al. Aromatase inhi-bitor-related musculoskeletal symptoms:is preventing osteopo-rosis the key to eliminating these symptoms?[J]. Clin Breast Cancer, 2009, 9(1):34-38. DOI PMID
[16]	Coleman RE, Banks LM, Girgis SI, et al. Skeletal effects of exemestane on bone-mineral density,bone biomarkers,and frac-ture incidence in postmenopausal women with early breast cancer participating in the Intergroup Exemestane Study(IES):a randomised controlled study[J]. Lancet Oncol, 2007, 8(2):119-127. DOI PMID
[17]	林方圆. 基于“肝肾同源”理论探讨乳腺癌芳香化酶抑制剂相关关节痛的影响因素及中药干预的临床研究[D]. 天津: 天津中医药大学, 2021.
	Lin FY. Based on the theory of “liver and kidney homology” to explore the influencing factors of breast cancer aromatase inhibitor-related arthralgia and clinical research of traditional Chinese medicine intervention[D]. Tianjin: Tianjin University of Traditional Chinese Medicine, 2021.
[18]	Husak AJ, Bair MJ. Chronic pain and sleep disturbances:a pragmatic review of their relationships,comorbidities,and treat-ments[J]. Pain Med, 2020, 21(6):1142-1152. DOI URL
[19]	Mibu A, Manfuku M, Nishigami T, et al. Association of aroma-tase inhibitor-induced musculoskeletal symptoms with central sensitization-related symptoms:a cross-sectional study[J]. Breast Care, 2024, 19(4):207-214. DOI URL
[20]	Lopez C, Charles C, Rouby P, et al. Relations between arthra-lgia and fear of recurrence:results of a cross-sectional study of breast cancer patients treated with adjuvant aromatase inhibitors therapy[J]. Support Care Cancer, 2015, 23(12):3581-3588.
[21]	Bauml J, Chen L, Chen JB, et al. Arthralgia among women tak-ing aromatase inhibitors:is there a shared inflammatory mecha-nism with co-morbid fatigue and insomnia?[J]. Breast Cancer Res, 2015, 17(1):89. DOI URL
[22]	Hyder T, Marino CC, Ahmad S, et al. Aromatase inhibitor-asso-ciated musculoskeletal syndrome:understanding mechanisms and management[J]. Front Endocrinol, 2021,12:713700.
[23]	Høegh-Andersen P, Tankó LB, Andersen TL, et al. Ovariectomi-zed rats as a model of postmenopausal osteoarthritis:validation and application[J]. Arthritis Res Ther, 2004, 6(2):R169-R180.
[24]	Dizdar O, Ozçakar L, Malas FU, et al. Sonographic and elec-trodiagnostic evaluations in patients with aromatase inhibitor-related arthralgia[J]. J Clin Oncol, 2009, 27(30):4955-4960. DOI PMID
[25]	张中宁, 沈傲梅, 漆维方, 等. 基于阶段变化理论的乳腺癌内分泌治疗患者运动依从体验的质性研究[J]. 中华护理杂志, 2025, 60(6):696-702. DOI URL
	Zhang ZN, Shen AM, Qi WF, et al. The experience of exercise adherence in breast cancer patients with endocrine-therapy based on the theory of stage change:a qualitative study[J]. Chin J Nurs, 2025, 60(6):696-702.
[26]	王莉杰, 彭思意, 陈婕君, 等. 乳腺癌患者内分泌治疗相关骨关节疼痛发展轨迹及护理启示[J]. 中华护理杂志, 2024, 59(14):1732-1738.
	Wang LJ, Peng SY, Chen JJ, et al. Analysis of the develop-ment trajectory and influencing factors of endocrine therapy associated arthralgia in breast cancer patients[J]. Chin J Nurs, 2024, 59(14):1732-1738.
[27]	赵菊, 赵久达, 王淼舟, 等. 芳香化酶抑制剂诱导乳腺癌患者关节痛风险预测模型的建立[J]. 中国肿瘤临床, 2024, 51(18):919-926.
	Zhao J, Zhao JD, Wang MZ, et al. Establishment of a risk-prediction model for aromatase inhibitor-induced arthralgia in patients with breast cancer[J]. Chin J Clin Oncol, 2024, 51(18):919-926.
[28]	Reinbolt RE, Sonis S, Timmers CD, et al. Genomic risk predic-tion of aromatase inhibitor-related arthralgia in patients with breast cancer using a novel machine-learning algorithm[J]. Can-cer Med, 2018, 7(1):240-253.