ABSTRACT
Objective:To explore the value of a nomogram model based on the CT enterography (CTE) signs for prediction of intestinal penetrating lesions in patients with Crohn disease (CD).Methods:The clinical and CTE data of CD patients who underwent at least two CTE examinations from January 2010 to June 2020 in the First Affiliated Hospital of Sun Yat-sen University were retrospectively collected. A total of 112 patients were enrolled, and according to whether there was intestinal wall penetration in the last CTE observation were divided into non-penetration group (84 cases) and penetration group (28 cases). First, the clinical and CTE data for the first examination was analyzed by using univariate and multivariate Cox proportional hazards regression to screen out high-risk factors that could effectively predict intestinal wall penetrating lesions in CD patients and established a nomogram model. Then the change trend of CTE data (ΔCTE) between the first and last clinical and CTE signs was analyzed by using univariate and multivariate Cox proportional hazards regression, and built a nomogram model to sort out ΔCTE that may accompany the development of penetrating lesions in CD patients. The Harrell concordance index was used to evaluate the discriminative ability of the nomogram model.Results:In the first time clinical and CTE signs, multivariate Cox proportional hazards regression results showed that numbers of diseased bowel segments (HR=0.686, 95%CI 0.475-0.991, P=0.045) and the shortest diameter of the largest lymph node (HR=0.751, 95%CI 0.593-0.949, P=0.017) were independent protection factors for penetrating lesions, and rough bowel wall surface (HR=5.626, 95%CI 2.466-12.839, P<0.001) was an independent risk factor for penetrating lesions. The specificity and sensitivity of the nomogram model to predict non-penetration lesions were 82.1% and 59.5% respectively, and the Harrell concordance index was 0.810 (95%CI 0.732-0.888). In the ΔCTE signs, multivariate Cox proportional hazards regression showed that Δrough bowel wall surface (always rough bowel wall surface HR=12.344, 95%CI 2.042-74.625, P=0.006; slide bowel wall surface becomes rough bowel wall surface HR=28.720, 95%CI 4.580-180.112, P<0.001) and Δthe shortest diameter of the largest lymph node (HR=1.534, 95%CI 1.091-2.157, P=0.014) were independent risk factors for penetrating lesions. The specificity and sensitivity of the nomogram model were 89.3% and 79.2% respectively, and the Harrell concordance index was 0.876 (95%CI 0.818-0.934). Conclusion:The nomogram based on CTE signs of numbers of diseased bowel segments, the shortest diameter of the largest lymph node and rough bowel wall surface and ΔCTE can effectively predict the intestinal wall penetrating lesions of CD patients.