基于贝叶斯累加回归树模型的非小细胞肺癌患者个性化疗效研究

doi:10.6040/j.issn.1671-7554.0.2021.1507

摘要/Abstract

摘要： 目的应用贝叶斯累加回归树(BART)模型对非小细胞肺癌(NSCLC)患者的仅手术与手术+化疗两种治疗方案的疗效进行个性化评价,并识别高受益患者亚组。方法提取美国SEER数据库中2012—2013年间所有NSCLC患者资料,以总生存时间不小于5年作为结局,按照治疗方案分类进行比较。运用倾向性评分匹配法使比较组间协变量均衡,应用BART模型计算个体处理效应(ITE),运用决策树模型进行亚组分析。结果本研究BART所对应的模型曲线下面积(AUC)大于0.8,结果可信度较高,99.5%患者采用手术+化疗方案获得不同程度更优疗效,得到AJCC分期、原发灶位置、转移程度等临床实践中重要的亚组分类特征,并得出疗效最优的亚组。所得亚组中,相较于仅手术的治疗方案,远处转移、原发灶位于肺中叶的女性患者更能于手术+化疗方案中受益。结论构建的BART模型可以较好地评价NSCLC患者两种治疗方案的个性化疗效,为今后同类疾病的个性化医疗实践提供依据。

关键词: 贝叶斯累加回归树, 个体处理效应, 非小细胞肺癌, 手术, 辅助化疗

Abstract: Objective Bayesian Additive Regression Tree(BART)model was applied to personalize efficacy of surgery-only and surgical adjuvant chemotherapy regimens for patients with non-small cell lung cancer(NSCLC), and to identify high yield subgroups. Methods The data of all NSCLC patients from 2012 to 2013 were extracted from the SEER database. With the overall survival time no less than 5 years as the outcome, the treatment regimens were compared. The propensity scores matching method was used to equalize the covariates between the two groups, the BART model was applied to calculate the individual treatment effect(ITE), and subgroup analysis was performed by decision tree model. Results The area under the curve(AUC)of the BART model was larger than 0.8, indicating that the results had high confidence. Most patients had better efficacy with surgical adjuvant chemotherapy regimen. Important subgroup taxonomic features in clinical practice such as AJCC stage, location of primary foci and degree of tumor metastasis were obtained and the subgroup with the best efficacy was derived. Among these subgroups, compared to surgery-only options, surgical adjuvant chemotherapy regimens produced better outcomes in female patients with distant metastasis and primary site in the middle lobe of the lung. Conclusion The constructed BART model can effectively evaluate personalized efficacy of the two treatment regimens for NSCLC patients and provide a basis for personalized medical practice for similar diseases in the future.

Key words: Bayesian Additive Regression Tree, Individual treatment effect, Non-small cell lung cancer, Surgery, Adjuvant chemotherapy

中图分类号:

R181

丁子琛,王浩桦,周立雯,丛慧文,李承圣,包绮晗,杨毅,王廉源,王素珍,石福艳. 基于贝叶斯累加回归树模型的非小细胞肺癌患者个性化疗效研究[J]. 山东大学学报 (医学版), 2022, 60(10): 92-98.

DING Zichen, WANG Haohua, ZHOU Liwen, CONG Huiwen, LI Chengsheng, BAO Qihan, YANG Yi, WANG Lianyuan, WANG Suzhen, SHI Fuyan. Study on the individualized efficacy for non-small cell lung cancer patients based on Bayesian Additive Regression Tree model[J]. Journal of Shandong University (Health Sciences), 2022, 60(10): 92-98.

参考文献

[1] 刘宗超, 李哲轩, 张阳, 等.2020全球癌症统计报告解读[J].肿瘤综合治疗电子杂志, 2021, 7(2): 1-14. LIU Zongchao, LI Zhexuan, ZHANG Yang, et al. Interpretation on the report of Global Cancer Statistics 2020[J]. Journal of Multidisciplinary Cancer Management(Electronic Version), 2021, 7(2): 1-14.
[2] Herbst RS, Morgensztern D, Boshoff C. The biology and management of non-small cell lung cancer[J]. Nature, 2018, 553(7689): 446-454.
[3] Duma N, Santana-Davila R, Molina JR. Non-small cell lung cancer: epidemiology, screening, diagnosis, and treatment[J]. Mayo Clin Proc, 2019, 94(8): 1623-1640.
[4] Bargagli-Stoffi FJ, De-Witte K, Gnecco G. Heterogeneous causal effects with imperfect compliance: a Bayesian machine learning approach[J]. Ann Appl Stat, 2021. doi: 10.48550/arXiv.1905.12707.
[5] Rosenbaum PR, Rubin DB. The central role of the propensity score in observational studies for causal effects[J]. Biometrika, 1983, 70(1): 41-55.
[6] Ettinger DS, Wood DE, Aisner DL, et al. NCCN guidelines insights: non-small cell lung cancer, version 2.2021[J]. J Natl Compr Canc Netw, 2021, 19(3): 254-266.
[7] Arriagada R, Bergman B, Dunant A, et al. Cisplatin-based adjuvant chemotherapy in patients with completely resected non-small-cell lung cancer[J]. N Engl J Med, 2004, 350(4): 351-360.
[8] 王永吉, 蔡宏伟, 夏结来, 等.倾向指数第一讲倾向指数的基本概念和研究步骤[J].中华流行病学杂志, 2010, 31(3): 347-348. WANG Yongji, CAI Hongwei, XIA Jielai, et al. Scores on propensity(Ⅰ)Conception and measures[J]. Chinese Journal of Epidemiology, 2010, 31(3): 347-348.
[9] Wang J. To use or not to use propensity score matching?[J]. Pharm Stat, 2021, 20(1): 15-24.
[10] 王永吉, 蔡宏伟, 夏结来, 等.倾向指数第二讲倾向指数常用研究方法[J].中华流行病学杂志, 2010, 31(5): 584-585. WANG Yongji, CAI Hongwei, XIA Jielai, et al. Propensity score(Ⅱ)Three commonly used methods on propensity score[J]. Chinese Journal of Epidemiology, 2010, 31(5): 584-585.
[11] Chipman HA, George EI, McCulloch RE. BART: Bayesian additive regression trees[J]. Ann Appl Stat, 2010, 4(1): 266-298.
[12] Hill J, Linero A, Murray J. Bayesian additive regression trees: a review and look forward[J]. Annu Rev Stat Appl, 2020, 7(1): 251-278.
[13] Sivaganesan S, Muller P, Huang B. Subgroup finding via Bayesian additive regression trees[J]. Stat Med, 2017, 36(15): 2391-2403.
[14] 马晓天.基于BART的高血压合并糖尿病患者社区干预个性化治疗效果评价[D].济南:山东大学, 2019.
[15] 李文钊.因果推理中的潜在结果模型:起源、逻辑与意蕴[J].公共行政评论, 2018, 11(1): 124-149, 221-222.
[16] Sparapani R, Spanbauer C, McCulloch R. Nonparametric machine learning and efficient computation with Bayesian additive regression trees: the BART R Package[J]. J Stat Softw, 97(1): 1-66.
[17] Arriagada R, Dunant A, Pignon JP, et al. Long-term results of the international adjuvant lung cancer trial evaluating adjuvant cisplatin-based chemotherapy in resected lung cancer[J]. J Clin Oncol, 2010, 28(1): 35-42.
[18] Morgensztern D, Du L, Waqar SN, et al. Adjuvant chemotherapy for patients with T2N0M0 NSCLC[J]. J Thorac Oncol, 2016, 11(10): 1729-1735.
[19] Xie J, Zhang X, Hu S, et al. Effects of adjuvant chemotherapy on survival of patients with stage IB non-small cell lung cancer with visceral pleural invasion[J]. J Cancer Res Clin Oncol, 2020, 146(9): 2231-2239.
[20] 宋朋, 高树庚. ⅠB期NSCLC术后辅助化疗争议及病理预后因素[J].中国肿瘤, 2017, 26(4): 286-290. SONG Peng, GAO Shugeng. Adjuvant chemotherapy and pathological prognostic factors in patients with non-small cell lung cancer stage ⅠB[J]. China Cancer, 2017, 26(4): 286-290.
[21] Kolek V, Losse S, Kultan J, et al. Real life adjuvant chemotherapy uptake and survival in patients with non-small cell lung cancer after complete resection[J]. Curr Med Res Opin, 2018, 34(9): 1687-1694.
[22] Sonobe M, Hamaji M, Motoyama H, et al. Adjuvant vinorelbine and cisplatin after complete resection of stage II and III non-small cell lung cancer: long-term follow-up of our study of Japanese patients[J]. Surg Today, 2018, 48(7): 687-694.
[23] 沈辉, 张扬, 陈海泉. ⅢA期非小细胞肺癌以外科为基础的多学科治疗[J].临床外科杂志, 2020, 28(11): 1003-1006.
[24] Lacour M, Hiltbrunner S, Lee SY, et al. Adjuvant chemotherapy increases programmed death-ligand 1(PD-L1)expression in non-small cell lung cancer recurrence[J]. Clin Lung Cancer, 2019, 20(5): 391-396.
[25] 董永强, 殷桂林, 张晓明, 等.右肺中叶病变的诊断及外科治疗[J].临床肺科杂志, 2010, 15(10): 1395-1396. DONG Yongqiang, YIN Guilin, ZHANG Xiaoming, et al. Diagnosis and surgical treatment of pathologic changes in middle lobe of right lung[J]. Journal of Clinical Pulmonary Medicine, 2010, 15(10): 1395-1396.

相关文章 15

[1]	徐宁宇王磊郝恩魁苏国海. STEMI患者急诊PCI前口服阿托伐他汀对炎症介质及左心室功能的影响[J]. 山东大学学报(医学版), 2209, 47(6): 69-72.
[2]	张小艳李刚王令平. 不同剂量舒芬太尼对脊柱手术患者全麻诱导期血流动力学及血浆皮质醇的影响[J]. 山东大学学报(医学版), 2209, 47(6): 76-79.
[3]	田超群,吕亚峰,李霄飞,宋永栋,孔利刚,樊兆民,王海波,张道宫. 半规管阻塞术与迷路切除术治疗70例晚期顽固性梅尼埃病的疗效[J]. 山东大学学报 (医学版), 2022, 60(8): 30-33.
[4]	秦静,杨飞,陈谦,夏涵岱,刘延国,王秀问. 晚期驱动基因阴性、PD-L1表达阴性非鳞非小细胞肺癌一线治疗方案的网状Meta分析[J]. 山东大学学报 (医学版), 2022, 60(7): 74-82.
[5]	匡风霞,赵晓虹,韩宝佳,高成杰. 对控制机器人甲状腺癌根治术患者手术应激反应麻醉深度的探讨[J]. 山东大学学报 (医学版), 2022, 60(5): 81-86.
[6]	陈兆波,方敏,薛浩然,刘春艳. 去泛素化酶USP35促进非小细胞肺癌细胞迁移和侵袭[J]. 山东大学学报 (医学版), 2022, 60(4): 30-37.
[7]	孙振国,田辉. 加速康复外科指导下微创食管癌切除术流程优化之齐鲁实践[J]. 山东大学学报 (医学版), 2022, 60(11): 33-37.
[8]	高树庚. 加速康复外科在肺癌围术期管理中的应用[J]. 山东大学学报 (医学版), 2022, 60(11): 1-10.
[9]	韩丁培,严越,曹羽钦,孙昕,胡琰霞,汪敏娴,罗艳,施咏梅,谢青,杭钧彪,李鹤成. 加速康复外科理念在胸外科临床实践指导的瑞金医院专家共识[J]. 山东大学学报 (医学版), 2022, 60(11): 11-16.
[10]	刘会宁,彭军,任迎春,杨光,王文豪,刘金锋,田勍. 34例胸腔镜下肺楔形切除与21例肺段切除对位于肺段P区的ⅠA1期非小细胞肺癌治疗比较[J]. 山东大学学报 (医学版), 2022, 60(11): 38-43.
[11]	仲明惟,胡三元. 我国腹腔镜技术治疗肥胖症手术方式的探索[J]. 山东大学学报 (医学版), 2021, 59(9): 72-77.
[12]	王沂峰,何丽清. 外阴癌腹股沟淋巴结手术的研究进展[J]. 山东大学学报 (医学版), 2021, 59(9): 103-109.
[13]	初竹秀,赵文静,李小燕,孔晓丽,马婷婷,江立玉,杨其峰. 218例女性乳腺癌患者行新辅助化疗及伴随分子标志物改变的临床价值[J]. 山东大学学报 (医学版), 2021, 59(9): 130-139.
[14]	杨贵霞,徐阳,马明明,宋然,朱鹏飞. 宫腹腔镜联合治疗Robert子宫合并子宫腺肌病1例[J]. 山东大学学报 (医学版), 2021, 59(1): 122-124.
[15]	庄大勇,贺青卿,李小磊,周鹏,岳涛,徐婧. 达芬奇机器人在儿童及青少年甲状腺癌中的应用[J]. 山东大学学报 (医学版), 2021, 59(1): 45-48.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed