基于决策树算法构建鼻咽癌患者放疗后发生放射性口腔黏膜炎风险的预测模型

doi:10.6040/j.issn.1673-3770.0.2023.447

摘要/Abstract

摘要： 目的构建预测鼻咽癌患者放疗后放射性口腔黏膜炎(radiation oral mucositis, ROM)发生风险的决策树模型。方法选取2022年1月至2023年6月医院收治的100例鼻咽癌患者作为研究对象,根据是否发生≥3级ROM,将患者分为<3级ROM(81例)和≥3级ROM(19例)。使用单因素和多因素Logistic回归分析鼻咽癌患者放疗后发生≥3级ROM的危险因素,并建立相关决策树预测模型。结果 100例鼻咽癌患者放疗后ROM的发生率为96.0%。单因素和多因素Logistic回归分析显示,吸烟、同期化疗、白蛋白水平<35 g/L和口腔pH值<7.0是鼻咽癌患者放疗后发生≥3级ROM的独立危险因素,而使用口腔黏膜保护剂是其保护因素(P<0.05)。利用其构建的决策树模型的准确性验证结果表明,其受试者工作特征曲线下面积为0.924(95%CI:0.901~0.946)。结论鼻咽癌患者放疗后发生≥3级ROM的影响因素较多,基于影响因素构建的决策树模型对鼻咽癌患者放疗后≥3级ROM的发生风险具有良好的预测能力。

关键词: 鼻咽癌, 放疗, 放射性口腔黏膜炎, 决策树

Abstract: Objective To construct a decision tree model for predicting the risk of radiation oral mucositis(ROM)in nasopharyngeal cancer patients after radiotherapy. Methods One hundred nasopharyngeal cancer patients admitted to the hospital from January 2022 to June 2023 were prospectively selected as study subjects, and the patients were categorized into <3 ROM(n=81)and ≥3 ROM(n=19)according to whether or not ≥3 ROM occurred. Risk factors for the occurrence of grade ≥3 ROM after radiotherapy in nasopharyngeal cancer patients were analyzed using univariate and multivariate logistic regression, and an associated decision tree prediction model was established. Results The incidence of ROM after radiotherapy in 100 nasopharyngeal cancer patients was 96.0%. Univariate and multifactorial logistic regression analyses showed that smoking, concurrent chemotherapy, albumin level <35 g/L, and oral pH <7.0 were independent risk factors for the occurrence of grade ≥3 ROM after radiotherapy in nasopharyngeal carcinoma patients, whereas the use of oral mucosal protectants was a protective factor(P<0.05). The results of the accuracy validation of the decision tree model constructed using it showed that the area under the working characteristic curve(ROC)(AUC)of its subjects was 0.924(95%CI: 0.901~0.946). Conclusion There are more influencing factors for the occurrence of grade ≥3 ROM after radiotherapy in nasopharyngeal cancer patients, and the decision tree model constructed based on the influencing factors has good predictive ability for the risk of grade ≥3 ROM after radiotherapy in nasopharyngeal cancer patients.

Key words: Nasopharyngeal cancer, Radiotherapy, Radiation oral mucositis, Decision tree

中图分类号:

R739.6

徐飞,朱光熹,王可心. 基于决策树算法构建鼻咽癌患者放疗后发生放射性口腔黏膜炎风险的预测模型[J]. 山东大学耳鼻喉眼学报, 2025, 39(4): 42-48.

XU Fei, ZHU Guangxi, WANG Kexin. Construction of a decision tree algorithm to predict the risk of radiation oral mucositis in nasopharyngeal carcinoma patients after radiotherapy[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2025, 39(4): 42-48.

参考文献 25

[1]	周宇翔. 首诊鼻咽癌内镜手术的治疗进展[J]. 山东大学耳鼻喉眼学报, 2021, 35(6): 108-112. doi:10.6040/j.issn.1673-3770.0.2020.493 ZHOU Yuxiang. Treatment progress of endoscopic surgery for first diagnosed nasopharyngeal carcinoma[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2021, 35(6): 108-112. doi:10.6040/j.issn.1673-3770.0.2020.493
[2]	Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2018, 68(6): 394-424. doi:10.3322/caac.21492
[3]	Cao W, Chen H D, Yu Y W, et al. Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020[J]. Chin Med J(Engl), 2021, 134(7): 783-791. doi:10.1097/cm9.0000000000001474
[4]	朱文鹏, 韩梦琦, 王雨欣, 等. 1990—2019年中国鼻咽癌发病与死亡的趋势及预测研究[J]. 中国全科医学, 2023, 26(34): 4269-4276. doi:10.12114/j.issn.1007-9572.2023.0247 ZHU Wenpeng, HAN Mengqi, WANG Yuxin, et al. Trends and projections of incidence and mortality of nasopharyngeal carcinoma in china from 1990 to 2019[J]. Chin Gen Pract, 2023, 26(34): 4269-4276. doi:10.12114/j.issn.1007-9572.2023.0247
[5]	冯梅, 王卫东, 郎锦义. 鼻咽癌临床诊疗的瓶颈与挑战[J]. 肿瘤预防与治疗, 2022, 35(1): 1-6. doi:10.3969/j.issn.1674-0904.2022.01.001 FENG Mei, WANG Weidong, LANG Jinyi. Bottleneck and challenges in the clinical diagnosis and treatment of nasopharyngeal cancer[J]. Journal of Cancer Control and Treatment, 2022, 35(1): 1-6. doi:10.3969/j.issn.1674-0904.2022.01.001
[6]	Juarez-Vignon Whaley JJ, Afkhami M, Sampath S, et al. Early stage and locally advanced nasopharyngeal carcinoma treatment from present to future: where are we and where are we going?[J]. Current Treatment Options in Oncology, 2023, 24(7): 845-866. doi:10.1007/s11864-023-01083-2
[7]	Liu ZB, Huang LL, Wang HS, et al. Predicting nomogram for severe oral mucositis in patients with nasopharyngeal carcinoma during intensity-modulated radiation therapy: a retrospective cohort study[J]. Curr Oncol, 2022, 30(1): 219-232. doi:10.3390/curroncol30010017
[8]	Luo XD, Wen XH, Zhou MC, et al. Decision-tree-initialized dendritic neuron model for fast and accurate data classification[J]. IEEE Trans Neural Netw Learn Syst, 2022, 33(9): 4173-4183. doi:10.1109/tnnls.2021.3055991
[9]	中国医师协会放射肿瘤治疗医师分会, 中华医学会放射肿瘤治疗学分会. 中国鼻咽癌放射治疗指南(2020版)[J]. 中华肿瘤防治杂志, 2021, 28(3): 167-177. doi:10.16073/j.cnki.cjcpt.2021.03.01
[10]	Sonis ST. Mucositis: The impact, biology and therapeutic opportunities of oral mucositis[J]. Oral Oncol, 2009, 45(12): 1015-1020. doi: 10.1016/j.oraloncology.2009.08.00
[11]	张侍玉, 王玉然, 赵姝姝, 等. 头颈癌放疗患者重度放射性口腔黏膜炎风险预测模型的构建与验证[J]. 护理学报, 2023, 30(10): 68-72. doi:10.16460/j.issn1008-9969.2023.10.068 ZHANG Shiyu, WANG Yuran, ZHAO Shushu, et al. Construction and verification of risk prediction model for severe radiation-induced oral mucositis in patients with head and neck cancer undergoing radiotherapy[J]. Journal of Nursing(China), 2023, 30(10): 68-72. doi:10.16460/j.issn1008-9969.2023.10.068
[12]	Bergamaschi L, Vincini MG, Zaffaroni M, et al. Management of radiation-induced oral mucositis in head and neck cancer patients: a real-life survey among 25 Italian radiation oncology centers[J]. Support Care Cancer, 2023, 32(1):38. doi: 10.1007/s00520-023-08185-5
[13]	李凯新, 辛培玲, 陈媛媛, 等. 局部中晚期鼻咽癌IMRT同步化疗后急性放射性口腔黏膜炎的预测因素分析[J]. 中华放射肿瘤学杂志, 2017, 26(3): 255-260. doi:10.3760/cma.j.issn.1004-4221.2017.03.002 LI Kaixin, XIN Peiling, CHEN Yuanyuan, et al. Dosimetric and clinical factors for predicting acute radiation oral mucositis in locally advanced nasopharyngeal carcinoma patients treated with intensity modulated radiotherapy with concurrent chemotherapy[J]. Chinese Journal of Radiation Oncology, 2017, 26(3): 255-260. doi:10.3760/cma.j.issn.1004-4221.2017.03.002
[14]	王艳丹, 程楠, 史保院, 等. 鼻咽癌患者放疗后发生放射性口腔黏膜炎的影响因素[J]. 实用癌症杂志, 2022, 37(6): 907-909, 916. doi:10.3969/j.issn.1001-5930.2022.06.011 WANG Yandan, CHENG Nan, SHI Baoyuan, et al. Influactors of radiation oral mucositis after radiotherapy in nasopharyngeal patients[J]. The Practical Journal of Cancer, 2022, 37(6): 907-909, 916. doi:10.3969/j.issn.1001-5930.2022.06.011
[15]	Chen GL, Jiang HG, Jiang DZ, et al. Pretreatment serum vitamin level predicts severity of radiation-induced oral mucositis in patients with nasopharyngeal carcinoma[J]. Head Neck, 2021, 43(4): 1153-1160. doi:10.1002/hed.26576
[16]	Tang LL, Guo R, Zhang N, et al. Effect of radiotherapy alone vs radiotherapy with concurrent chemoradiotherapy on survival without disease relapse in patients with low-risk nasopharyngeal carcinoma: a randomized clinical trial[J]. JAMA, 2022, 328(8): 728-736. doi:10.1001/jama.2022.13997
[17]	Zhang Y, chen L, Hu GQ, et al. Final overall survival analysis of gemcitabine and cisplatin induction chemotherapy in nasopharyngeal carcinoma: a multicenter, randomized phase III trial[J]. J Clin Oncol, 2022, 40(22): 2420-2425. doi:10.1200/jco.22.00327
[18]	Chang HP, Huang MC, Lei YP, et al. Phytochemical-rich vegetable and fruit juice alleviates oral mucositis during concurrent chemoradiotherapy in patients with locally advanced head and neck cancer[J]. J Tradit Complement Med, 2022, 12(5): 488-498. doi:10.1016/j.jtcme.2022.03.004
[19]	陈春, 黄佳瑜, 何玉思, 等. 老年恶性血液病化疗患者口腔黏膜炎风险预测模型的构建与验证[J]. 现代医学, 2022, 50(10): 1255-1263. doi:10.3969/j.issn.1671-7562.2022.10.006 CHEN Chun, HUANG Jiayu, HE Yusi, et al. Construction and verification of risk prediction model of oral mucositis in elderly patients with malignant hematological diseases undergoing chemotherapy[J]. Modern Medical Journal, 2022, 50(10): 1255-1263. doi:10.3969/j.issn.1671-7562.2022.10.006
[20]	王鲁, 曹咏梅, 史金晔. 鼻咽癌调强放疗后放射性口腔黏膜炎发生的危险因素分析[J]. 中国中西医结合耳鼻咽喉科杂志, 2017, 25(6): 456-459. doi:10.16542/j.cnki.issn.1007-4856.2017.06.016 WANG Lu, CAO Yongmei, SHI Jinye. Risk factors of radiation induced oral mucositis after intensity-modulated radiotherapy for nasopharyngeal carcinoma[J]. Chinese Journal of Otorhinolaryngology in Integrative Medicine, 2017, 25(6): 456-459. doi:10.16542/j.cnki.issn.1007-4856.2017.06.016
[21]	徐芳, 滕海荣, 王月霞, 等. 鼻咽癌患者放疗后放射性口腔黏膜炎发生的相关因素分析[J]. 实用预防医学, 2019, 26(12): 1476-1479. doi:10.3969/j.issn.1006-3110.2019.12.019 XU Fang, TENG Hairong, WANG Yuexia, et al. Analysis of related factors of radiation-induced oral mucositis in nasopharyngeal carcinoma patients after radiotherapy[J]. Practical Preventive Medicine, 2019, 26(12): 1476-1479. doi:10.3969/j.issn.1006-3110.2019.12.019
[22]	高燕, 杨连平. 急性放射性口腔黏膜炎的防治研究进展[J]. 医学综述, 2020, 26(22): 4494-4498. doi:10.3969/j.issn.1006-2084.2020.22.024 GAO Yan, YANG Lianping. Research progress in prevention and treatment of acute radiation-induced oral mucositis[J] Med Rev, 2020, 26(22): 4494-4498. doi: 10.3969/j.issn.1006-2084.2020.22.024
[23]	Mondal R, Do MD, Ahmed NU, et al. Decision tree learning in Neo4j on homogeneous and unconnected graph nodes from biological and clinical datasets[J]. BMC Medical Informatics and Decision Making, 2023, 22(6): 347. doi:10.1186/s12911-023-02112-8
[24]	Yin J, Xie JR, Lin JW, et al. Evaluation of the efficacy of the anti-ulcer oral mucosal protective agent RADoralex in the prevention and treatment of radiation-induced oral mucosal reactions induced during treatment of nasopharyngeal carcinoma[J]. Cancer Biol Ther, 2022, 23(1): 27-33. doi:10.1080/15384047.2021.2013704
[25]	Wakamori S, Taguchi K, Nakayama Y, et al. Nrf2 protects against radiation-induced oral mucositis via antioxidation and keratin layer thickening[J]. Free Radic Biol Med, 2022, 188: 206-220. doi:10.1016/j.freeradbiomed.2022.06.239

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed