老年住院患者皮肤撕裂伤风险预测模型的构建及验证 [中文引用][英文引用]

目的  构建并验证老年住院患者皮肤撕裂伤风险预测模型，为临床早期识别高风险患者及实施针对性预防提供参考。方法  采用前瞻性观察性研究设计，选取 2024 年 1 月至 2025 年 6 月 1 016 例老年住院患者作为研究对象。按 7：3 比例将患者分为训练集（n=700）与验证集（n=300）。通过单因素及多因素 Logistic 回归分析筛选危险因素并构建列线图预测模型。采用受试者工作特征（receiver operating characteristic，ROC）曲线下面积、Hosmer-Lemeshow 检验及校准曲线评价模型的区分度与校准度，并采用 Bootstrap 法（重复抽样 1 000 次）进行内部验证，最后在验证集中进行外部验证。结果  老年住院患者皮肤撕裂伤发生率为 12.4%。年龄增长、活动 / 移动能力重度障碍、皮肤状况明显异常、失禁相关性皮炎、认知功能中重度障碍及皮肤撕裂伤史是老年住院患者发生皮肤撕裂伤的危险因素（均 P<0.05）。列线图预测模型的 ROC 曲线下面积为 0.814，灵敏度为0.791，特异度为 0.687，Hosmer-Lemeshow 检验 χ 2=3.153，P=0.924；经 Bootstrap 内部验证校正后的一致性指数（C-index）为 0.802。模型在验证集测试的 ROC 曲线下面积为 0.791，灵敏度为 0.774，特异度为 0.685，Hosmer-Lemeshow 检验 χ 2=4.672，P=0.792。结论  本研究构建的老年住院患者皮肤撕裂伤风险预测列线图模型具有良好的预测效能、校准度与稳健性，有助于临床护理人员量化评估个体风险，实现早期识别与精准预防。

Objective To develop and validate a model for risk prediction of skin tears in elderly inpatients，aiming to provide a reference for early identification of high-risk patients and implementation of targeted preventive measures. Methods A prospective observational study was conducted. From January 2024 to June 2025，a total of 1，016 elderly inpatients were recruited and divided into a development set（n=700）and a validation set（n=300）in a 7：3 ratio. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors and develop a nomogram prediction model. Discrimination and calibration of the model were evaluated using the area under the receiver operating characteristic（ROC）curve，the Hosmer-Lemeshow test，and calibration curves. Internal validation was conducted using the Bootstrap method（1，000 resamples），followed by external validation on an independent validation set. Results The incidence of skin tear among elderly inpatients was 12.4%. Logistic regression showed that advanced age，severe mobility impairment，significant skin abnormalities，incontinence-associated dermatitis，moderate-to-severe cognitive impairment，and a history of skin tear were the independent risk factors（all P<0.05）. The area under the ROC curve of the nomogram prediction model was 0.814，with a sensitivity of 0.791 and a specificity of 0.687. The Hosmer-Lemeshow test yielded χ 2 =3.153， P=0.924. After Bootstrap internal validation，the corrected concordance index（C-index）was 0.802. In the independent validation set， the area under the ROC curve was 0.791，with a sensitivity of 0.774 and specificity of 0.685. The Hosmer-Lemeshow test yielded χ 2 = 4.672，P=0.792. Conclusion The nomogram developed for predicting the risk of skin tear in elderly inpatients shows good predictive performance，calibration and robustness. It can assist clinical nurses in quantifying individual risk，enabling early identification and precise prevention of a skin tear.