【摘要】 目的 探讨预防性回肠造口周围潮湿相关性皮肤损伤(PMASD)的发生机制及主要影响因素，构建风险预测模型。方法 选取2024年1～6月上海市同济医院收治的570例预防性回肠造口患者作为研究对象，按照便利抽样法将所有患者分为建模组(310例)和验证组(260例),依据建模组患者是否发生PMASD分为损伤组和无损伤组，并构建预测模型。利用受试者工作特征曲线(ROC)、霍斯默-莱梅肖(Hosmer-Lemeshow)检验及外部验证组数据评估模型的预测效果。结果 经分析，患者的个体属性、手术情况、造口特征、护理、饮食和排便状况等均为显著影响因素(P均<0.05)。预测模型ROC下面积为0.858,Hosmer-Lemeshow检验P值为0.767,准确率达90.51%。验证组分析显示预测模型具有良好的灵敏度和特异度，总体准确率为77.33%。结论 构建回肠造口患者PMASD的风险预测模型，主要影响因素为患者的个体属性、手术情况、造口特征、护理、饮食和排便情况，模型具有较高的准确性。更多还原

【Abstract】 Objective To explore the mechanism and main influencing factors of peristomal moisture-associated skin damage(PMASD) around preventive ileostomy, and to construct a risk prediction model. Methods A total of 570 patients with an intestinal stoma admitted to Tongji Hospital of Tongji University from January to June 2024 were selected as the study subjects. The patients were divided into a modeling group(310 cases) and a validation group(260 cases) using a convenience sampling method. Based on whether the patients in the modeling group developed PMASD, they were divided into a damage group and a non-damage group, and a prediction model was constructed. The receiver operating characteristic(ROC) curve, the Hosmer-Lemeshow test, and the data of validation group were adopted to evaluate the predictive effect of the model. Results Upon the analysis, the individual attributes, operative details, stoma features, nursing practices, dietary habits, and defecation conditions of patients were identified as significant influencing factors(P < 0.05). The predictive model achieved an area under the ROC curve of 0.858, a Hosmer-Lemeshow test P-value of 0.767, and an overall accuracy of 90.51%. The analysis of the validation group showed that the prediction model had good sensitivity and specificity, with an overall accuracy of 77.33%. Conclusion A risk prediction model for PMASD in patients with an intestinal stoma was developed. The main influencing factors are individual attributes, operative details, stoma features, nursing practices, dietary habits, and defecation conditions. The model demonstrated a relatively high predictive accuracy.更多还原