UNASSIGNED: The participants were hospitalized patients 65 years and older from two branches of a tertiary hospital in China, one for model training set and the other for validation set. This study was a case-control study based on hospital electronic medical records. According to the presence of pressure injury at admission, patients were divided into a case group and a control group. In the model training set, LASSO regression was used to select the best predictors, and then logistic regression was used to construct a nomogram. The performance of the model was evaluated by drawing the receiver operating characteristic curve (ROC) and calculating the area under the curve (AUC), calibration analysis, and decision curve analysis. The model used a 10-fold crossover for internal and external validation.
UNASSIGNED: The study included a total of 20,235 subjects, including 11,567 in the training set and 8668 in the validation set. The prevalence of CAPI in the training and validation sets was 2.5% and 1.8%, respectively. A nomogram was constructed including eight variables: age ≥ 80, malnutrition status, cerebrovascular accidents, hypoproteinemia, respiratory failure, malignant tumor, paraplegia/hemiplegia, and dementia. The AUC of the prediction model in the original model, internal validation, and external validation were 0.868 (95% CI: 0.847, 0.890), mean 0.867, and 0.840 (95% CI: 0.807,03.873), respectively. The nomogram showed acceptable calibration and clinical benefit.
UNASSIGNED: We constructed a nomogram to predict CAPI from the perspective of comorbidity that is suitable for use by non-specialists. This nomogram will help family caregivers and community workers with the early identification of PI risks.
UNASSIGNED:参与者是来自中国三级医院两个分院的65岁及以上的住院患者,
未经评估:该研究共包括20,235名受试者,
UNASSIGNED:我们构建了一个列线图,以从合并症的角度预测CAPI,该合并症适合非专业人士使用。