目的 探讨结肠镜下息肉切除术后复发的危险因素，并基于机器学习算法构建复发风险预警模型，为防治对策提供依据。方法 回顾性收集2018年9月—2023年9月六安市人民医院1 058例初次行无痛结肠镜下息肉切除术患者的临床资料，使用单因素和多因素Logistic回归分析筛选复发危险因素。采用7∶3随机抽样分为训练集和验证集，分别通过决策树、贝叶斯及Logistic回归算法构建预测模型，并以受试者工作特征曲线（ROC）曲线下面积（AUC）、灵敏度、特异度等指标来评估模型效能。结果 单因素分析显示，性别、吸烟、代谢综合征、息肉数量、息肉位置、山田分型、组织病理学类型、切除方式、复查时间、肠息肉直径、手术时间是复发的危险因素（P＜0.05）。多因素分析显示，性别、代谢综合征、息肉数量、息肉直径、肠息肉位置、山田分型、组织学病理类型、切除方式、手术时间均是结肠息肉内镜下切除术后复发的危险因素。模型评估显示，决策树算法、贝叶斯算法、Logistic回归算法的ROC曲线下面积（AUC）分别为0.849、0.818、0.811；灵敏度分别为85.14%、81.62%、79.43%；特异度分别为81.69%、79.45%、74.18%；约登指数分别为0.534、0.551、0.573；95%CI分别为0.810~0.876、0.794~0.860、0.782~0.850；决策树算法模型效能最佳，Logistic回归算法的性能最差。结论 性别、代谢综合征、肠息肉特征（数量、直径、位置等）是术后复发的关键危险因素。决策树模型在风险预测中表现最优，可为临床制定个体化随访策略提供参考。
Objective To explore the risk factors for recurrence after painless colonoscopic polypectomy and construct a recurrence risk warning model based on machine learning algorithms to provide evidence for prevention and treatment strategies．Methods A retrospective analysis was conducted on clinical data from 1 058 patients who underwent their first painless colonoscopy-guided polypectomy at our hospital between September 2018 and September 2023．Univariate and multivariate Logistic regression analyses were performed to identify recurrence risk factors．The dataset was randomly divided into training and validation sets using a 7∶3 ratio．Prediction models were constructed using decision tree，Bayesian，and Logistic regression algorithms，and their performance was evaluated using metrics such as the area under the receiver operating characteristic curve（AUC），sensitivity，specificity，and others．Results Univariate analysis revealed that gender，smoking，metabolic syndrome，number of polyps，polyp location，Yamada classification，histopathological type，resection method，follow-up time，polyp diameter，and operation duration were risk factors for recurrence（P＜0.05）．Multivariate analysis identified gender，metabolic syndrome，number of polyps，polyp diameter，polyp location，Yamada classification，histopathological type，resection method，and operation duration as independent risk factors for recurrence after endoscopic polypectomy．Model evaluation showed AUC values of 0.849，0.818，and 0.811 for the decision tree，Bayesian，and Logistic regression algorithms，respectively．Sensitivity values were 85.14%，81.62%，and 79.43%；specificity values were 81.69%，79.45%，and 74.18%；Youden’s indices were 0.534，0.551，and 0.573；and 95% confidence intervals（CIs）were 0.810–0.876，0.794–0.860，and 0.782–0.850，respectively．The decision tree algorithm demonstrated the best predictive performance，while the Logistic regression algorithm performed the least favorably．Conclusions Gender，metabolic syndrome，and polyp characteristics（number，diameter，location，etc．）are key risk factors for recurrence after polypectomy．The decision tree algorithm exhibited optimal predictive efficacy，offering valuable insights for developing individualized follow-up strategies in clinical practice．
目的 研究结肠黑变病(melanosis coli,MC)对结肠息肉的影响。方法 从2014年1月—2017年1月在石河子大学医学院第一附属医院行电子结肠镜的21 708例患者中选取符合条件的522例结肠黑变病患者组成MC组,随机选取569例患者组成非MC组,分析比较2组的一般情况及与结肠息肉的关系,非正态分布的计量资料以中位数表示,采用秩和检验,两组计数资料采用χ2检验。结果 结肠黑变病组年龄中位数为64岁(51～73岁),非结肠黑变病组年龄中位数为54岁(47～64岁),2组性别无统计学差异;MC组、非MC组结肠息肉检出率分别为47.8%和40.2%,P=0.013,差异有统计学意义;在病理类型上2组均为炎性息肉检出率最低,腺瘤性息肉检出率最高分别达 58.0%和51.5%,病理类型无统计学差异;在盲肠及降结肠检出率均很低,多发部位、直肠、乙状结肠检出率相对较高,但差异均无统计学意义;结肠息肉大小集中在0~9 mm范围内,2组所占百分比分别高达92.0%和91.3%,≥20 mm息肉检出率均很低,分别为0.40%,0.44%,息肉大小无统计学差异。结论 MC组息肉检出率高于非MC组,差异有统计学意义;2组结肠息肉病理类型、发病部位、息肉大小差异均无统计学意义。
Objective Studying the effect of melanosis coli (MC) on colonic polyps.Methods This is a reospectively review of patients with electronic colonoscopy in our hospital from January 2014 to January 2017. A total of 522 cases of colorectal melanosis (MC) were composed of MC group, and 569 patients were randomly selected to form a non-mc group. The comparison of basic information between the two groups and the relationship of colon polyp and colon cancer was analyzed.Results The median age of the colon melanosis group was 64 years (51~73 years old), and the median age of the non-colonic melanosis group was 54 years (47 to 64 years old), with no statistically significant differences between the two groups.The detection rate of colon polyps in MC group was 47.8%. The detection rate of colon polyps in non-mc group was 40.2%, P= 0.013, and the difference was statistically significant.The two groups of polyps had the lowest detection rate of inflammatory polyps in pathological types, and the detection rate of adenomatous polyps was up to 58.0% and 51.5% respectively, but there was no statistically significant difference between the two groups. In the cecum, the detection rate of the descending colon was low, and the detection rate of multiple sites, rectum and sigmoid colon was relatively high, but the difference was not statistically significant.The size of colon polyps was concentrated in the range of 0~9 mm, and the percentages of the two groups were as high as 92.0% and 91.3% respectively, while the detection rate of the size being more than 20mm was low, that is 0.40% and 0.44%. But there was no statistical difference between the two groups.Conclusion The detection rate of polyps in MC group was higher than that in non-mc group, and the difference was statistically significant.There was no statistically significant difference between the two groups of colon polyps pathology, pathogenesis, and polyp size.
