基于决策树与Logistic回归模型的肺癌患者希望水平影响因素判别分析

doi:10.16352/j.issn.1001-6325.2026.03.0402

基础医学与临床 ›› 2026, Vol. 46 ›› Issue (3): 402-410.doi: 10.16352/j.issn.1001-6325.2026.03.0402

基于决策树与Logistic回归模型的肺癌患者希望水平影响因素判别分析

吕娟¹, 吉硕¹, 刘亚¹, 孙雯¹, 潘瑞丽^2*

中国医学科学院北京协和医学院北京协和医院 1.呼吸与危重症医学科;2.护理部,北京 100730

收稿日期:2025-08-26 修回日期:2025-10-30 出版日期:2026-03-05 发布日期:2026-02-25
通讯作者: ^*dabaidexiapu0236@163.com
基金资助:
北京协和医院护理科研课题(XHHLKY202304)

Discriminant analysis on influencing factors of hope level in patients with lung cancer based on decision tree and Logistic regression models

LYU Juan¹, JI Shuo¹, LIU Ya¹, SUN Wen¹, PAN Ruili^2*

1. Department of Respiratory and Critical Care Medicine;2. Department of Nursing, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China

Received:2025-08-26 Revised:2025-10-30 Online:2026-03-05 Published:2026-02-25
Contact: ^*dabaidexiapu0236@163.com

摘要/Abstract

摘要： 目的分析肺癌患者希望水平的影响因素,以便尽早预测和识别较低希望水平的肺癌患者,并为提高肺癌患者希望水平干预措施的制订提供参考依据。方法抽取2024年7月至2024年12月在北京协和医院就诊的266例肺癌患者作为研究对象,使用Herth 希望指数(HHI)对纳入患者展开希望水平的调查。比较不同特征肺癌患者希望水平情况,采用决策树(DT)模型与Logistic 回归模型分析影响肺癌患者希望水平的影响因素。结果剔除9例作答了无效问卷的患者后,本研究共纳入患者共257例。Logistic 回归模型结果显示,确诊天数(B=-0.001)、肺癌分型[腺癌(B=0.177)、鳞癌(B=1.949)、其他(B=1.458)]、文化程度[高中、中专或技校(B=-1.182)、大专(B=0.392)、本科及以上(B=1.040)]、免疫治疗(B=-0.682)、体力状态(PS)评分[1级(B=1.657)、2级(B=2.102)、3级(B=0.171)]、心理弹性总分(CD-RISC)(B=-0.060)这6项是肺癌患者中等希望水平发生的独立影响因素;决策树分析结果显示,心理弹性总分是影响肺癌患者希望水平的主要因素,其次是文化程度和确诊天数。两个模型的ROC曲线下面积(AUC)分别为0.853(0.806,0.900)、0.850(0.801,0.898),其差异无统计学意义(Z=0.144,P=0.885)。结论 Logistic回归模型和决策树模型在预测肺癌患者的希望水平时均有一定的应用价值,建议在临床中将二者结合使用,以便更好提高肺癌患者的希望水平。

关键词: 希望水平, 心理弹性, Logistic回归, 决策树

Abstract: Objective To identify influencing factors of hope level in patients with lung cancer, so as to find and identify patients with lower hope level as early as possible, and to provide reference for the formulation of intervention measures to improve hope level in patients with lung cancer. Methods Total of 266 patients with lung cancer who were treated in Peking Union Medical College Hospital from July 2024 to December 2024 were selected as the research objects. Herth Hope Index (HHI) was used to investigate the hope level of the included patients.The hope level of lung cancer patients with different characteristics was compared, and the decision tree(DT) and Logistic regression model were used to analyze the influencing factors of the hope level of lung cancer patients. Results After excluding 9 patients who answered invalid questionnaires, 257 patients were included in this study. Logistic regression model showed that the days since diagnosis (B=-0.001), lung cancer classification[adenocarcinoma(B=0.177), squamous cell carcinoma (B=1.949), others (B=1.458)], education level [high school, vocational school or technical school (B=-1.182), junior college (B=0.392), bachelor′s degree or above (B=1.040)], immunotherapy(B=-0.682), the score of Eastern Cooperative Oncology Group (ECOG) performance status (PS) [grade 1 (B=1.657), grade 2 (B=2.102) , grade 3 (B=0.171)]and the score of Connor-Davidson Resilience Scale (CD-RISC) (B=-0.060) were independent factors influencing the occurrence of the medium hope level in lung cancer patients.The results of decision tree showed that the total score of CD-RISC was the main factor affecting the hope level of lung cancer patients, followed by education level and the days of diagnosis. The area under the curve(AUC) of the two models was 0.853(0.806,0.900) and 0.850 (0.801, 0.898) respectively with no statistically significant difference (Z=0.144, P=0.885). Conclusions Both Logistic regression model and decision tree have certain application value in predicting the hope level of lung cancer patients. It is suggested to combine the two models in clinical practice in order to improve the hope level of lung cancer patients.

Key words: hope level, psychological resilience, Logistic regression, decision tree

中图分类号:

R734.2

吕娟, 吉硕, 刘亚, 孙雯, 潘瑞丽. 基于决策树与Logistic回归模型的肺癌患者希望水平影响因素判别分析[J]. 基础医学与临床, 2026, 46(3): 402-410.

LYU Juan, JI Shuo, LIU Ya, SUN Wen, PAN Ruili. Discriminant analysis on influencing factors of hope level in patients with lung cancer based on decision tree and Logistic regression models[J]. Basic & Clinical Medicine, 2026, 46(3): 402-410.

参考文献

[1] Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. Ca-Cancer J Clin, 2021,71:209-249.doi:10.3322/caac.21660.
[2] Liu X, Yu Y, Wang M, et al. The mortality of lung cancer attributable to smoking among adults in China and the United States during 1990–2017[J]. Cancer Commun, 2020,40:611-619.doi:10.1002/cac2.12099.
[3] Osowiecka K, Kieszkowska-Grudny A, Środa R, et al. Identification of cognitive strategies used by cancer patients as a basis for psychological self-support during oncological therapy[J]. Int J Env Res Pub He, 2022,19:9243.doi:10.3390/ijerph19159243.
[4] McLouth LE, Shelton B , Bursac V, et al. “Pathways”: a hope-enhancing intervention for patients undergoing treatment for advanced lung cancer[J]. Psycho-Oncology, 2024,33:e6316.doi:10.1002/pon.6316.
[5] Huang M, Hung Y, Lee W, et al. Usage of case-based reasoning, neural network and adaptive neuro-fuzzy inference system classification techniques in breast cancer dataset classification diagnosis[J]. J Med Syst, 2012,36:407-414.doi:10.1007/s10916-010-9485-0.
[6] Herth K. Abbreviated instrument to measure hope: development and psychometric evaluation[J]. J Adv Nurs, 1992,17:1251-1259.doi:10.1111/j.1365-2648.1992.tb01843.x.
[7] Xu R, Chen J, Chen D, et al. CT-guided percutaneous microwave ablation combined with local radiotherapy or chemotherapy of malignant pulmonary tumors[J]. Curr Radiopharm, 2024,17:184-199.doi:10.2174/0118744710261655231214105406.
[8] Yu X, Zhang J, Yu XN, et al. Factor analysis and psychometric evaluation of the Connor-Davidson resilience scale (CD-RISC) with Chinese people[J]. Soc Behav Personal, 2007,35:19-30.doi:10.2224/SBP.2007.35.1.19.
[9] Cheng L, Gao W, Xu Y, et al. Anxiety and depression in rheumatoid arthritis patients: prevalence, risk factors and consistency between the hospital anxiety and depression scale and Zung′s self-rating anxiety scale/depression scale[J]. Rheumatol Adv Pract, 2023,7:rkad100.doi:10.1093/rap/rkad100.
[10] Bando T, Onishi C, Imai Y. Treatment-associated symptoms and coping of postoperative patients with lung cancer in Japan: development of a model of factors influencing hope[J]. Jpn J Nurs Sci, 2018,15:237-248.doi:10.1111/jjns.12193.
[11] Gao Y, Yuan L, Pan B, et al. Resilience and associated factors among Chinese patients diagnosed with oral cancer[J]. Bmc Cancer, 2019,19:447.doi:10.1186/s12885-019-5679-0.
[12] 霍艳飞. 肺癌化疗患者希望水平现状及影响因素研究[J]. 齐齐哈尔医学院学报, 2018,39:2462-2464.doi:10.3969/j.issn.1002-1256.2018.20.044.
[13] 朱文曦. 胃肠道癌症患者希望水平与心理弹性的相关性研究[J]. 当代护士, 2021,28:44-47.doi:10.19791/j.cnki.1006-6411.2021.28.015.
[14] 王艳华, 阎成美, 黄丽婷, 等. 乳腺癌住院患者疾病不确定感与希望的相关性研究[J]. 护理学报, 2007,14:15-17.doi:10.3969/j.issn.1008-9969.2007.01.007.
[15] Yang Y, Liu L, Wang X, et al. Prevalence and associated positive psychological variables of depression and anxiety among Chinese cervical cancer patients: a cross-sectional study[J]. PLoS One, 2014,9:e94804.doi:10.1371/journal.pone.0094804.

基于决策树与Logistic回归模型的肺癌患者希望水平影响因素判别分析

Discriminant analysis on influencing factors of hope level in patients with lung cancer based on decision tree and Logistic regression models

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	潘瑞丽, 马千惠, 徐燕, 王孟昭, 王素娥, 关玉霞. 希望水平在晚期肺癌患者抑郁状态与心理韧性中的中介效应[J]. 基础医学与临床, 2022, 42(2): 291-295.
[2]	胡泊李卫刘冰陈涛孙毅. 北京市城乡中年人高血压流行情况及危险因素分析[J]. 基础医学与临床, 2010, 30(7): 759-762.