消化道早癌高危患者内镜复查依从性的影响因素分析^*

Analysis of Factors Affecting Endoscopic Follow-up Compliance in High-Risk Patients With Early Gastrointestinal Cancer

摘要

目的 应用随机森林分析疾病感知、医患沟通、认知负荷与消化道早癌高危患者内镜复查依从性的关系。方法 选取2022年1月–2022年12月303例消化道早癌高危患者为研究对象，采用一般资料调查表、简化版疾病感知问卷、医患沟通评价量表、不同认知负荷量表进行问卷调查。Spearman分析疾病感知、医患沟通、认知负荷、消化道早癌高危患者内镜复查依从性之间的关系，多因素logistic分析患者内镜复查依从性的影响因素，随机森林模型对患者内镜复查依从性特征变量进行重要性排序，通过受试者工作特征（receiver operating characteristic, ROC）曲线下面积（area under the curve, AUC）评估模型效能，并应用五折法验证。结果 Spearman分析显示：消化道早癌高危患者内镜复查依从性差与疾病感知、医患沟通呈负相关（r_s=-0.788、-0.815，P<0.05），与认知负荷呈正相关（r_s=0.619，P<0.05）；经多因素logistic分析得出，年龄〔比值比（odds ratio, OR）=1.159，95%置信区间（confidence interval, CI）：1.052～1.276〕、消化道肿瘤家族史（OR=0.081，95%CI：0.008～0.865）、家庭人均月收入（OR=0.994，95%CI：0.991～0.997）、疾病感知（OR=0.745，95%CI：0.639～0.870）、医患沟通（OR=0.694，95%CI：0.602～0.801）、认知负荷（OR=1.351，95%CI：1.136～1.608）是消化道早癌高危患者内镜复查依从性的影响因素（P<0.05）；随机森林模型变量重要性排序为医患沟通>疾病感知>认知负荷>家庭人均月收入>年龄>消化道肿瘤家族史，其预测AUC为0.899（95%CI：0.843～0.921），经五折交叉验证随机森林模型平均准确率为0.893。结论 疾病感知、医患沟通、认知负荷、家庭人均月收入、年龄、消化道肿瘤家族史是消化道早癌高危患者内镜复查依从性的关键因素。

Abstract

Objective The random forest method was used to analyze the relationship between disease perception, doctor-patient communication, cognitive load, and the compliance of high-risk patients with early digestive tract cancer regarding endoscopic re-examination. Methods A total of 303 patients at high risk for early digestive tract cancer from January 2022 to December 2022 were selected as research subjects. Questionnaire surveys were conducted using general information questionnaires, a simplified disease perception questionnaire, a doctor-patient communication evaluation scale, and various cognitive load scales. Spearman analysis was used to examine the relationships among disease perception, doctor-patient communication, cognitive load, and compliance with endoscopic reexamination in patients at high risk for early digestive tract cancer. Multivariate logistic analysis was performed to identify factors influencing patients' compliance with endoscopic reexamination. A random forest model was used to rank the importance of characteristic variables for compliance. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate model efficacy, and five-fold cross-validation was applied for validation. Results Spearman analysis showed that poor compliance with endoscopic re-examination among patients at high risk for early digestive tract cancer was negatively correlated with disease perception and doctor-patient communication (r _s = -0.788, -0.815, P < 0.05), and positively correlated with cognitive load ( r _s = 0.619, P < 0.05). Multivariate logistic analysis identified age (odds ratio [OR] = 1.159, 95% confidence interval [CI]: 1.052-1.276), family history of digestive tract tumors (OR = 0.081, 95% CI: 0.008-0.865), average monthly family income (OR = 0.994, 95% CI: 0.991-0.997), disease perception (OR = 0.745, 95% CI: 0.639-0.870), doctor-patient communication (OR = 0.694, 95% CI: 0.602-0.801), and cognitive load (OR = 1.351, 95% CI: 1.136-1.608) as factors influencing compliance with endoscopic re-examination in these patients ( P < 0.05). The variable importance ranking in the random forest model was doctor-patient communication > disease perception > cognitive load > average monthly family income > age > family history of digestive tract tumors. The model's prediction AUC was 0.899 (95% CI: 0.843-0.921), and the average accuracy after five-fold cross-validation was 0.893. Conclusion Disease perception, doctor-patient communication, cognitive load, average monthly household income, age, and family history of digestive tract tumors are key factors influencing compliance with endoscopic re-examination in patients with early digestive tract cancer.

关键词

消化道 / 内镜 / 随机森林 / 医患沟通

Key words

Gastrointestinal tract / Endoscope / Random forest / Doctor-patient communication

参考文献

[1] BEN-AHARON I, Van LAARHOVEN H W M, FONTANA E, et al. Early-Onset Cancer in the Gastrointestinal Tract Is on the Rise-Evidence and Implications. Cancer Discov, 2023, 13(3): 538-551. doi: 10.1158/2159-8290.CD-22-1038.

[2] WANG J, LI D, YE F, et al. Global Epidemiology of Early-Onset Digestive System Malignancy: A Systematic Analysis for the Global Burden of Disease Study 2021. J Gastroenterol Hepatol, 2025, 40(6): 1525-1535. doi: 10.1111/jgh.17012.

[3] GOETZ N, LAMBA M, RYAN K, et al. Post-Endoscopy Upper Gastrointestinal Cancer Rate in a Tertiary Referral Centre: An Australian Data Linkage Analysis. J Gastrointest Cancer, 2023, 54(3): 837-845. doi: 10.1007/s12029-022-00874-4.

[4] ZHANG M, ZHONG J, SONG Z, et al. Regulatory mechanisms and potential therapeutic targets in precancerous lesions of gastric cancer: A comprehensive review. Biomed Pharmacother, 2024, 177: 117068. doi: 10.1016/j.biopha.2024.117068.

[5] 余炜燕, 李雪, 朱娟, 等. 消化道肿瘤联合筛查项目胃肠镜依从性影响因素分析. 中国肿瘤, 2024, 33(11): 937-951. doi: 10.11735/j.issn.1004-0242.2024.11.A009.

[6] YU W Y, LI X, ZHU J, et al. Influencing Factors for Compliance of Gastroscopy and Colonoscopy in Gastrointestinal Cancer Screening Program. China Cancer, 2024, 33(11): 937-951. doi: 10.11735/j.issn.1004-0242.2024.11.A009.

[7] VICENTE R S, FREITAS A R, FERREIRA R M A, et al. Communication preferences and perceptions of cancer patient during their first medical oncology appointment. Psychooncology, 2023, 32(11): 1702-1709. doi: 10.1002/pon.6220.

[8] BATTILORO C, DOMINICI F. Long Live Random Forest - The Quiet, Long-Lasting Power of Statistical Learning for Molecular Diagnostics in the AI Era. NEJM Evid, 2025, 4(11): EVIDe2500248. doi: 10.1056/EVIDe2500248.

[9] 朱祥, 喻舜, 刘星雨, 等. 基于随机森林生存模型的AMI患者PCI术后的不良事件风险分析. 重庆医科大学学报, 2024, 49(3): 295-302. doi: 10.13406/j.cnki.cyxb.003455.

[10] ZHU X, YU S, LIU X Y, et al. Risk factors for adverse events after percutaneous coronary intervention in patients with acute myocardial infarction: an analysis based on a random forest survival model. Journal of Chongqing Medical University, 2024, 49(3): 295-302. doi: 10.13406/j.cnki.cyxb.003455.

[11] KIM D J, ROCKHILL B, COLDITZ G A. Validation of the Harvard Cancer Risk Index: a prediction tool for individual cancer risk. J Clin Epidemiol, 2004, 57(4): 332-340. doi: 10.1016/j.jclinepi.2003.08.013.

[12] XIAO H F, YAN S P, LI J G, et al. Development and external validation of a nomogram to predict the risk of Upper gastrointestinal precancerous lesions in a non-high-incidence area. Cancer Med, 2020, 9(22): 8722-8732. doi: 10.1002/cam4.3462.

[13] AHMED F E. Colon cancer: prevalence, screening, gene expression and mutation, and risk factors and assessment. J Environ Sci Health C Environ Carcinog Ecotoxicol Rev, 2003, 21(2): 65-131. doi: 10.1081/GNC-120026233.

[14] WATANABE H. Applications of statistics to medical science, Ⅲ. Correlation and regression. J Nippon Med Sch, 2012, 79(2): 115-120. doi: 10.1272/jnms.79.115.

[15] BROADBENT E, PETRIE K J, MAIN J, et al. The brief illness perception questionnaire. J Psychosom Res, 2006, 60(6): 631-637. doi: 10.1016/j.jpsychores.2005.10.020.

[16] MAKOUL G. The SEGUE Framework for teaching and assessing communication skills. Patient Educ Couns, 2001, 45(1): 23-34. doi: 10.1016/s0738-3991(01)00136-7.

[17] LEPPINK J. Cognitive load theory: Practical implications and an important challenge. J Taibah Univ Med Sci, 2017, 12(5): 385-391. doi: 10.1016/j.jtumed.2017.05.003.

[18] CHEN Z Y, BIAN T Z, ZHAO Z Y, et al. Patient Involvement and Methodological Considerations in the UGIC Endoscopy Screening Cluster Trial. Gastroenterology, 2025, 169(4): 745-746. doi: 10.1053/j.gastro.2025.04.029.

[19] 杜佳, 于智凯, 张艳, 等. 重庆市上消化道癌高危人群内镜筛查依从性及影响因素分析. 中国肿瘤, 2024, 33(12): 1019-1026. doi: 10.11735/j.issn.1004-0242.2024.12.A009.

[20] DU J, YU Z K, ZHANG Y, et al. Compliance and Influencing Factors of Endoscopic Screening in High-Risk Population of Upper Gastrointestinal Cancer in Chongqing. China Cancer, 2024, 33(12): 1019-1026. doi: 10.11735/j.issn.1004-0242.2024.12.A009.

[21] ZHANG M, ZHANG Y, GUO L, et al. Trends in colorectal cancer screening compliance and incidence among 60- to 74-year-olds in China. Cancer Med, 2024, 13(8): e7133. doi: 10.1002/cam4.7133.

[22] 刘畅, 戴静毅, 赵军, 等. 2018-2019年云南省某医院肝癌高危人群肝癌监测依从性变化及影响因素分析. 中国预防医学杂志, 2023, 24(2): 122-128. doi: 10.16506/j.1009-6639.2023.02.006.

[23] LIU C, DAI J Y, ZHAO J, et al. Changes in adherence to hepatocellular carcinoma surveillance among high-risk population in a hospital in Yunnan and the related influencing factors. Chinese Preventive Medicine, 2023, 24(2): 122-128. doi: 10.16506/j.1009-6639.2023.02.006.

[24] ZENG J, GAO Y, HOU C, et al. The impact of doctor-patient communication on medication adherence and blood pressure control in patients with hypertension: a systematic review. PeerJ, 2024, 12: e18527. doi: 10.7717/peerj.18527.

[25] ZHAN Y, MAO P, GAO F, et al. Content and Duration of Doctor-Patient Communication in Outpatient Oncology Follow-Up Consultations in China. Cureus, 2024, 16(3): e55597. doi: 10.7759/cureus.55597.

[26] LIU X, ZENG J, LI L, et al. The Influence of Doctor-Patient Communication on Patients' Trust: The Role of Patient-Physician Consistency and Perceived Threat of Disease. Psychol Res Behav Manag, 2024, 17: 2727-2737. doi: 10.2147/PRBM.S460689.

[27] LIU T, LIU X, ZENG J, et al. The effect of doctor-patient communication on blood pressure control in hypertensive patients: Mediating role of medication adherence. Heart Lung, 2025, 73: 197-206. doi: 10.1016/j.hrtlng.2025.05.005.

[28] 王侨蓝, 谢林伸, 杜文, 等. 尘肺合并细菌性肺炎的危险因素与预后: 随机森林模型的应用. 四川大学学报(医学版), 2025, 56(4): 1076-1082. doi: 10.12182/20250760102.

[29] WANG Q L, XIE L S, TU W, et al. Risk Factors and Prognosis of Pneumoconiosis Combined With Bacterial Pneumonia: Application of a Random Forest Model. Journal of Sichuan University (Medical Sciences), 2025, 56(4): 1076-1082. doi: 10.12182/20250760102.

基金资助

*国家重点专科建设项目(ZDZKKF01)