乳腺癌患者化疗期症状群困扰风险预测模型的构建与评价

doi:10.3761/j.issn.0254-1769.2023.06.005

摘要/Abstract

摘要：

目的构建化疗期乳腺癌患者自我报告症状群困扰高风险预测模型并评价模型的预测性能。方法采用便利抽样法，选取2019年10月—2021年5月在上海市、山东省、江苏省、浙江省4所三级甲等医院接受化疗并符合纳入标准的乳腺癌患者647例，按5折交叉验证法以8 ∶ 2的比例随机分为建模组和验证组。在建模组中采用随机森林算法构建，在验证组中采用受试者操作特征曲线、Hosmer-Lemeshow拟合优度检验、校准曲线以及决策曲线综合评价模型的预测性能，最后对各影响因素进行重要性排序。结果乳腺癌患者高症状困扰发生率建模组为33.27%，验证组为29.23%。预测模型的受试者操作特征曲线下面积为0.91，灵敏度为65.8%，特异度为93.5%；Hosmer-Lemeshow拟合优度检验P=0.136；决策曲线显示高于参考线。身体心像、自我效能感、经济负担等为最主要的预测因子。结论基于随机森林算法构建的预测模型具有良好的预测性能，对识别症状困扰高风险的乳腺癌患者有重要意义。

关键词: 乳腺肿瘤, 症状困扰, 症状群, 随机森林算法, 预测模型

Abstract:

Objective To develop and evaluate a risk predictive model for high level of self-reported symptom cluster distress in breast cancer patients undergoing chemotherapy. Methods 647 patients who received chemotherapy and met the inclusion and exclusion criteria were selected at 4 tertiary hospitals in Shanghai，Shandong，Jiangsu，and Zhejiang from October 2019 to May 2021. Cases were randomly assigned to a modeling group and a validation group based on 5-fold cross-validation method at a ratio of 8：2. The random forest algorithm was used to develop the risk predictive model in the modeling group. The receiver operating characteristic curve，Hosmer-Lemeshow goodness-of-fit test，calibration curve，and decision curve were used to comprehensively evaluate the prediction performance of the model in the validation group. Risk factors were identified based on the order of the importance of each influencing factors. Results The incidence of high symptom cluster distress was 33.27% in the modeling group and 29.23% in the validation group. The area under the receiver operating characteristic curve of the prediction model was 0.91；the sensitivity was 65.8%；the specificity was 93.5%；Hosmer-Lemeshow goodness-of-fit test was insignificant（P=0.1365）；the decision curve was above the reference line. Body image，self-efficacy，and financial burden were the most important predictors. Conclusion The risk predictive model based on random forest algorithm has good predictive performance，which is of great significance to help identify breast cancer subgroups at high risk of symptom cluster distress，and will potentially promote symptom management.

Key words: Breast Neoplasm, Symptom Distress, Symptom Cluster, Random Forest Algorithms, Predictive Model

吴傅蕾, 袁长蓉, 杨瑒, 尚美美, 闫荣, 郑叶平, 钮美娥, 黄青梅. 乳腺癌患者化疗期症状群困扰风险预测模型的构建与评价[J]. 中华护理杂志, 2023, 58(6): 676-681.

WU Fulei, YUAN Changrong, YANG Yang, SHANG Meimei, YAN Rong, ZHENG Yeping, NIU Meie, HUANG Qingmei. Development and evaluation of a risk predictive model for high level of self-reported symptom cluster distress in breast cancer patients undergoing chemotherapy[J]. Chinese Journal of Nursing, 2023, 58(6): 676-681.

图/表 6

表1 化疗期乳腺癌患者自我报告症状群困扰的单因素分析

Table 1 Screening of predictors of the group with high symptom distress

续表1 化疗期乳腺癌患者自我报告症状群困扰的单因素分析

Table 1 （Continued）Screening of predictors of the group with high symptom distress

图1 随机森林预测模型在验证组的ROC曲线分析

Figure 1 ROC curve analysis of random forest prediction model in validation group

图2 随机森林预测模型在验证组的校准曲线分析

Figure 2 Calibration curve analysis of random forest prediction model in validation group

图3 随机森林预测模型在验证组的决策曲线分析

Figure 3 Decision curve analysis of random forest prediction model in validation group

图4 随机森林预测模型的变量重要性评分排序

Figure 4 Ranking of variable importance scores for random forest prediction model

参考文献 29

[1]	Siegel RL, Miller KD, Fuchs HE, et al. Cancer statistics,2022[J]. CA Cancer J Clin, 2022, 72(1):7-33. DOI URL
[2]	Rossi L, Mazzara C, Pagani O. Diagnosis and treatment of breast cancer in young women[J]. Curr Treat Options Oncol, 2019, 20(12):86. DOI
[3]	Browall M, Brandberg Y, Nasic S, et al. A prospective exploration of symptom burden clusters in women with breast cancer during chemotherapy treatment[J]. Support Care Cancer, 2017, 25(5):1423-1429. DOI PMID
[4]	Lawrence DP, Kupelnick B, Miller K, et al. Evidence report on the occurrence,assessment,and treatment of fatigue in cancer patients[J]. J Natl Cancer Inst Monogr, 2004(32):40-50.
[5]	Lim CC, Devi MK, Ang E. Anxiety in women with breast cancer undergoing treatment:a systematic review[J]. Int J Evid-based Hea, 2011, 9(3):215-235.
[6]	Doong SH, Dhruva A, Dunn LB, et al. Associations between cytokine genes and a symptom cluster of pain,fatigue,sleep disturbance,and depression in patients prior to breast cancer surgery[J]. Biol Res Nurs, 2015, 17(3):237-247. DOI URL
[7]	Langford DJ, Paul SM, Cooper B, et al. Comparison of subgroups of breast cancer patients on pain and co-occurring symptoms following chemotherapy[J]. Support Care Cancer, 2016, 24(2):605-614. DOI PMID
[8]	Nguyen J, Cramarossa G, Bruner D, et al. A literature review of symptom clusters in patients with breast cancer[J]. Expert Rev Pharmacoeconomics Outcomes Res, 2011, 11(5):533-539. DOI URL
[9]	Bjerkeset E, Röhrl K, Schou-Bredal I. Symptom cluster of pain,fatigue,and psychological distress in breast cancer survivors:prevalence and characteristics[J]. Breast Cancer Res Treat, 2020, 180(1):63-71. DOI
[10]	Hamer J, McDonald R, Zhang L, et al. Quality of life(QOL) and symptom burden(SB) in patients with breast cancer[J]. Support Care Cancer, 2017, 25(2):409-419. DOI URL
[11]	黄青梅, 耿朝辉, 吴傅蕾, 等. 乳腺癌患者化疗期间症状群特征及预测指标的研究[J]. 中华护理杂志, 2020, 55(9):1297-1303. DOI
	Huang QM, Geng ZH, Wu FL, et al. Study on differential characters of symptom clusters and predictors of breast cancer patients during chemotherapy[J]. Chin J Nurs, 2020, 55(9):1297-1303. DOI
[12]	中国抗癌协会乳腺癌专业委员会. 中国抗癌协会乳腺癌诊治指南与规范(2021年版)[J]. 中国癌症杂志, 2021, 31(10):954-1040.
	China Anti-Cancer Association Breast Cancer Committee. Guidelines for diagnosis and treatment of breast cancer of China Anti-Cancer Association(2021 version)[J]. China Oncol, 2021, 31(10):954-1040.
[13]	van der Ploeg T, Austin PC, Steyerberg EW. Modern modelling techniques are data hungry:a simulation study for predicting dichotomous endpoints[J]. BMC Med Res Methodol, 2014, 14:137. DOI URL
[14]	Cella D, Yount S, Rothrock N, et al. The Patient-Reported Outcomes Measurement Information System(PROMIS):progress of an NIH Roadmap cooperative group during its first two years[J]. Med Care, 2007, 45(5 suppl 1):S3-S11.
[15]	吴傅蕾. 乳腺癌阶段特异性患者报告结局测量系统的构建研究[D]. 上海: 海军军医大学, 2019.
	Wu FL. Study on the construction of stage-specific patient reporting outcome measurement system for breast cancer[D]. Shanghai: Second Military Medical University, 2019.
[16]	Erickson BJ, Korfiatis P, Akkus Z, et al. Machine learning for medical imaging[J]. Radiographics, 2017, 37(2):505-515. DOI PMID
[17]	杨剑锋, 乔佩蕊, 李永梅, 等. 机器学习分类问题及算法研究综述[J]. 统计与决策, 2019, 35(6):36-40.
	Yang JF, Qiao PR, Li YM, et al. A review of machine-learning classification and algorithms[J]. Stat Decis, 2019, 35(6):36-40.
[18]	Min N, Wei Y, Zheng Y, et al. Advancement of prognostic models in breast cancer:a narrative review[J]. Gland Surg, 2021, 10(9):2815-2831. DOI URL
[19]	张华, 陶立元, 赵一鸣. 临床研究中预测模型的效能评价[J]. 中华儿科杂志, 2018, 56(9):719.
	Zhang H, Tao LY, Zhao YM. Effectiveness evaluation of prediction model in clinical research[J]. Chin J Pediatr, 2018, 56(9):719.
[20]	MacEachern SJ, Forkert ND. Machine learning for precision medicine[J]. Genome, 2021, 64(4):416-425. DOI PMID
[21]	Nindrea RD, Aryandono T, Lazuardi L, et al. Diagnostic accuracy of different machine learning algorithms for breast cancer risk calculation:a Meta-analysis[J]. Asian Pac J Cancer Prev, 2018, 19(7):1747-1752.
[22]	Vickers AJ, Elkin EB. Decision curve analysis:a novel method for evaluating prediction models[J]. Med Decis Making, 2006, 26(6):565-574. DOI PMID
[23]	薛翠翠, 刘均娥. 乳腺癌患者体像及心理干预的研究进展[J]. 中华护理杂志, 2015, 50(6):728-732.
	Xue CC, Liu JE. A review of psychological intervention in the body image of breast cancer patients[J]. Chin J Nurs, 2015, 50(6):728-732.
[24]	马冬花, 程康文, 杜华. 体像不满意乳腺癌病人现况及其影响因素的横断面研究[J]. 现代临床护理, 2020, 19(6):7-11.
	Ma DH, Cheng KW, Du H. Influencing factors of body image dissatisfaction of breast cancer patients[J]. Mod Clin Nurs, 2020, 19(6):7-11.
[25]	Kołodziejczyk A, Pawłowski T. Negative body image in breast cancer patients[J]. Adv Clin Exp Med, 2019, 28(8):1137-1142. DOI PMID
[26]	Li M. Associations of body image with depressive symptoms and PTG among breast cancer patients:the mediating role of social support[J]. Front Psychol, 2022, 13:1-10.
[27]	鲁佳, 李英, 周佳欣, 等. 乳腺癌患者性健康管理的最佳证据总结[J]. 中华护理杂志, 2022, 57(17):2156-2163. DOI
	Lu J, Li Y, Zhou JX, et al. Best evidence summary for sexual health management in breast cancer patients[J]. Chin J Nurs, 2022, 57(17):2156-2163. DOI
[28]	Eller LS, Lev EL, Yuan C, et al. Describing self-care self-efficacy:definition,measurement,outcomes,and implications[J]. Int J Nurs Knowl, 2018, 29(1):38-48.
[29]	Wu F, Howell D, Fang Q, et al. Trajectory patterns and factors influencing self-management behaviors in Chinese patients with breast cancer[J]. Cancer Nurs, 2020, 43(2):E105-E112. DOI URL