Objective To investigate the influencing factors of facial pressure injury related to ventilation in prone positioning in children with severe pneumonia and to construct a nomogram prediction model.

Methods A total of 158 children with severe pneumonia who underwent prone positioning ventilation were selected as research subjects. Clinical data were collected, and the children were divided into injury group (31 cases) and non-injury group (127 cases) based on whether facial pressure injury occurred. Univariate and multivariate Logistic regression analysis were used to explore the influencing factors of facial pressure injury related to prone positioning ventilation in children with severe pneumonia; the receiver operating characteristic (ROC) curve, consistency index, and Hosmer-Lemeshow goodness-of-fit test were used to evaluate the predictive efficiency of the nomogram model for facial pressure injury related to prone positioning ventilation in children with severe pneumonia.

Results Univariate analysis showed that the proportion of children aged < 3 years, the proportion of those with complications, ventilation time in prone positioning, the proportions of children with sedative drugs and poor nutritional status, no decompression dressings, and the proportions of children without prone positioning ventilation training for medical staff in the injury group were higher or longer than that in the non-injury group (P < 0.05). Multivariate Logistic regression analysis showed that age < 3 years, presence of complications, longer prone positioning ventilation time, no decompression dressings, and lack of prone positioning ventilation training for medical staff were independent risk factors for facial pressure injury related to prone positioning ventilation in children with severe pneumonia (P < 0.05), and a nomogram prediction model was constructed based on these factors. The consistency index of the nomogram model was 0.940, and the area under the ROC curve was 0.978 (95%CI, 0.958 to 0.999). The calibration curve of predicting facial pressure injury related to prone positioning ventilation in children with severe pneumonia approached the ideal curve, and the Hosmer-Lemeshow goodness-of-fit test showed good fitting (χ²=12.416, P < 0.05).

Conclusion The nomogram prediction model constructed based on 5 independent risk factors in this study has high risk identification ability and can early identify high-risk children with facial pressure injury related to prone positioning ventilation in severe pneumonia.