Prediction model for severe complications in patients with failed conservative treatment of acute intestinal obstruction based on clinical and imaging features: development and validation

Abstract Objective To develop and validate a prediction model based on clinical and imaging features for identifying high-risk patients who develop Clavien–Dindo grade ≥ IIIa severe complications (including intestinal necrosis, perforation, sepsis, and reoperation) after failed non-operative management (NOM) of acute intestinal obstruction. Methods This study was conducted and reported according to the TRIPOD guidelines. Clinical data were collected, including age, sex, BMI, history of abdominal surgery, history of chronic disease, vital signs, laboratory parameters (NLR, CRP), obstruction characteristics, and CT findings (degree of bowel dilation, bowel wall thickening, fecal sign, mesenteric vascular sign, ascites). Missing data were handled using multiple imputation. Univariate and multivariate logistic regression analyses were used to identify independent predictors, based on which a nomogram prediction model was constructed. Model discrimination and calibration were assessed, and internal validation was performed using 10-fold cross-validation. Results Multivariate logistic regression showed that history of abdominal surgery, development of peritonitis signs during NOM, increased heart rate, elevated 24‑h NLR increase after admission, and CT findings of fecal sign and mesenteric vascular sign were independent predictors of severe complications. The prediction model showed good discrimination, with an AUC of 0.894 (95% CI 0.851–0.936). The internally validated C‑index was 0.872 (95% CI 0.825–0.920). Calibration statistics showed a Brier score of 0.105. Conclusion A prediction model combining clinical and CT features was successfully developed and internally validated. This model effectively predicts the risk of severe complications in patients with acute intestinal obstruction who fail NOM, facilitating early identification of high‑risk patients and timely intervention.