Department of Neurosurgery, College of Medicine, Pusan National University, Busan, South Korea.
Department of Nursing, Pukyong National University, Busan, South Korea.
J Tissue Viability. 2020 Nov;29(4):252-257. doi: 10.1016/j.jtv.2020.06.002. Epub 2020 Jul 29.
Oral-mucosal pressure injury (PI) is the most commonly encountered medical device-related PIs. This study was performed to identify risk factors and construct a risk prediction model for oral-mucosal PI development in intubated patients in the intensive care unit.
The study design was prospective, observational with medical record review. The inclusion criteria stipulated that 1) participants should be > 18 years of age, 2) there should be ETT use with holding methods including adhesive tape, gauze tying, and commercial devices. Data of 194 patient-days were analysed. The identification and validation of risk model development was performed using SPSS and the SciKit learn platform.
The risk prediction logistic models were composed of three factors (bite-block/airway, commercial ETT holder, and corticosteroid use) for lower oral-mucosal PI development and four factors (commercial ETT holder, vasopressor use, haematocrit, and serum albumin level) for upper oral-mucosal PI development among 10 significant input variables. The sensitivity and specificity for lower oral-mucosal PI development were 85.2% and 76.0%, respectively, and those for upper oral-mucosal PI development were 60.0% and 89.1%, respectively. Based on the results of the machine learning, the upper oral-mucosal PI development model had an accuracy of 79%, F1 score of 88%, precision of 86%, and recall of 91%.
The development of lower oral-mucosal PIs is affected by immobility-related factors and corticosteroid use, and that of upper oral-mucosal PIs by undernutrition-related factors and ETT holder use. The high sensitivities of the two logit models comprise important minimum data for positively predicting oral-mucosal PIs.
口腔黏膜压力性损伤（PI）是最常见的与医疗器械相关的 PI。本研究旨在确定 ICU 插管患者口腔黏膜 PI 发生的危险因素，并构建风险预测模型。
研究设计为前瞻性、观察性病历回顾。纳入标准规定：1）参与者年龄应大于 18 岁，2）应使用 ETT 并采用胶带、纱布捆绑和商业设备等固定方法。共分析了 194 个患者日的数据。使用 SPSS 和 SciKit learn 平台对风险模型的识别和验证进行了分析。
低口腔黏膜 PI 发展的风险预测逻辑模型由三个因素（咬块/气道、商业 ETT 固定器和皮质类固醇使用）组成，而上口腔黏膜 PI 发展的风险预测逻辑模型由 10 个重要输入变量中的四个因素（商业 ETT 固定器、血管加压素使用、红细胞压积和血清白蛋白水平）组成。低口腔黏膜 PI 发展的敏感性和特异性分别为 85.2%和 76.0%，而上口腔黏膜 PI 发展的敏感性和特异性分别为 60.0%和 89.1%。基于机器学习的结果，上口腔黏膜 PI 发展模型的准确性为 79%，F1 得分为 88%，精度为 86%，召回率为 91%。
低口腔黏膜 PI 的发生与固定相关因素和皮质类固醇使用有关，而上口腔黏膜 PI 的发生与营养不良相关因素和 ETT 固定器使用有关。两种逻辑模型的高敏感性包含了对口腔黏膜 PI 进行阳性预测的重要最小数据。
