结直肠息肉发病风险预测模型构建及其临床价值

目的探讨行结肠镜检查者罹患结直肠息肉的相关危险因素并构建预测模型。 方法回顾性分析2019年1月至2021年10月于南京中医药大学第二附属医院行结肠镜检查者共1 671例的临床资料。根据结肠镜结果将968例结直肠息肉患者纳入息肉组,703名无息肉病变的患者纳入无息肉组。收集患者年龄、性别、身高、体重、吸烟史、饮酒史、实验室检查结果和既往肠镜检查结果等多种因素,分析影响结直肠息肉发生的相关危险因素。应用R语言建立预测结直肠息肉发生风险的列线图模型,用Bootstrap法进行模型内部验证,采用列线图验证曲线及ROC曲线评价列线图的预测性能。 结果息肉组患者年龄（t=151.531,P＜0.001）、男性比例（χ²=50.843,P＜0.001）、长期吸烟史比例（χ²=5.034,P=0.013）、BMI（t=0.813,P＜0.001）、既往息肉史（χ²=8.323,P=0.004）高于无息肉组,差异有统计学意义。多因素Logistic回归模型分析结果显示：年龄,性别,BMI,长期吸烟,既往息肉大小、病理类型及生长位置为结直肠息肉发病的独立危险因素（均P＜0.05）。ROC曲线显示AUC为0.908,敏感性和特异性分别为76.9%和83.2%。 结论年龄,性别,长期吸烟史,BMI,既往息肉大小、病理类型及生长位置为结直肠息肉发病的独立危险因素。该研究所建立的列线图模型具有良好的区分度和准确度,可为直观、个体化地分析结直肠息肉发生风险,甄别高危人群,为临床制订筛查方案提供参考依据。

Construction of a risk prediction model for colorectal polyps and its clinical value

ObjectiveTo investigate the risk factors of colorectal polyps in patients undergoing colonoscopy and to construct a predictive model. MethodsA total of 1 671 patients who underwent colonoscopy in the Second Affiliated Hospital of Nanjing University of Traditional Chinese Medicine from January 2019 to October 2021 were analyzed retrospectively. According to the endoscopic results, 968 patients with colorectal polyps were included in the polyp group, and 703 patients without polyp lesions were included in the polyp-free group. Various factors such as age, gender, height, weight, history of smoking and drinking, laboratory examination and previous colonoscopy results were collected, and the related risk factors affecting the occurrence of colorectal polyps were analyzed. R software was used to establish a nomogram model for predicting the risk of colorectal polyps, and the Bootstrap method was used for internal validation of the model, and the C-index and ROC curve were used to evaluate the predictive performance of the nomogram. ResultsThe age (t=151.531, P＜0.001) , male ratio (χ²=50.843, P＜0.001), the proportion of patients with long-term smoking (χ²=5.034, P=0.013), BMI (t=0.813, P＜0.001), past polyps historical proportions in the polyp group (χ²=8.323, P=0.004) were higher than those in the control group, and the difference was statistically significant (P＜0.05). Multivariate logistic regression model analysis showed that age, gender, BMI, the proportion of patients with long-term smoking, previous polyp size, pathological type and growth location were independent risk factors for colorectal polyps (P＜0.05). The ROC curve showed that the AUC was 0.908, and the sensitivity and specificity were 76.9% and 83.2%, respectively. ConclusionAge, gender, BMI, the proportion of patients with long-term smoking, previous polyp size, pathological type and growth location are independent risk factors for colorectal polyps. The nomogram model established in this study has good discrimination and accuracy, which can intuitively and individually analyze the risk of colorectal polyps, identify high-risk groups, and provide a reference for clinical screening programs.