IDDF2024-ABS-0010 Development and validation of a risk-stratification prediction model for acute bowel injury in critically ill patients

<h3>Background</h3> To establish a risk stratification model that accurately predicts the occurrence of acute bowel injury in adult patients requiring critical care. By identifying high-risk individuals using this model, timely interventions can be implemented, leading to improved prognosis and increased success rates in managing severe cases. <h3>Methods</h3> This study utilized clinical data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) to analyze and identify factors associated with acute bowel injury (ABI). Thirteen factors, including age, gender, hypertension, diabetes, coronary heart disease, chronic kidney disease, total bilirubin, emergency surgery, mechanical ventilation, sepsis, heart failure, tumors, and hypoalbuminemia, were carefully examined by conducting an extensive literature review. Univariate and multivariate analyses were employed to determine the key factors that contribute to the predictive model. Binary logistic regression was subsequently employed to construct the ABI prediction model. The discriminatory capacity of the model, in terms of distinguishing between patients with and without ABI, was evaluated using the area under the receiver operating characteristics curve (AUROC). <h3>Results</h3> Our study included a cohort of 499 patients, among whom 149 patients (29.86%) experienced acute bowel injury (ABI). The average age of the patients was 56±12 years, and 53.76% were male. The ABI prediction model demonstrated a favorable prognostic ability, as indicated by an AUROC of 0.87, sensitivity of 73.8%, and specificity of 85.4%. <h3>Conclusions</h3> We have constructed an acute bowel injury (ABI) prediction model for critically ill patients, which incorporates five variables, namely heart failure, chronic kidney disease, emergency surgery, sepsis, and total bilirubin. Additionally, we assessed the prognostic performance of this model.