Construction and validation of a risk prediction model for critically ill patients with stress injury / 中国实用护理杂志

ABSTRACT

Objective:To construct a pressure injury risk prediction model for critical patients and verify its prediction effect.Methods:A cohort study was conducted to collect relevant data of critical patients hospitalized in the Intensive Care Unit from February 2019 to September 2019. The occurrence of pressure injuries was used as a dependent variable to conduct a single factor and multiple factor analyses of relevant data and establish predictive models. The risk stratification and predictive effect tests were also performed.Results:There were 329 critical patients and 48 cases of pressure injuries. The single factor analysis of 11 factors showed that blood lactate, body temperature, ICU hospitalization days, Braden score, consciousness state, age and booster drug treatment were the suspicious factors of stress injury, and the difference was statistically significant ( Z value was 2.575-3.694, χ 2 values were 6.800, 30.510, 6.344, P<0.05 or 0.01); The results of the binary Logistic regression analysis showed that the independent influencing factors for the occurrence of pressure injuries included the patient′s body temperature within 24 hours after entering the ICU, the Braden score, state of consciousness, age and ICU hospitalization duration ( P<0.05 or 0.01). A prediction model was established. The likelihood ratio chi-square proved that the model was statistically significant and fitted well. The sensitivity was 66.7% and the specificity was 72.2%. The risk stratification of the model was performed. The difference between the high-risk group and the low-risk group was statistically significant ( t value was -33.371, P<0.01); the validation set was used to test the prediction effect, and the area under the ROC curve was 0.758. Conclusions:The constructed prediction model is a scientific combination of objective indicators of the clinical characteristics of critical patients, which is statistically significant; the model can predict critical patients’ risks of pressure injuries; it also has a good degree of discrimination, which can provide a theoretical basis for the risk management of critical patients with great clinical application value.