New score models for assessing disease activity in Crohn's disease based on bowel ultrasound and biomarkers: Ideal surrogates for endoscopy or imaging

Abstract

Disease activity evaluation is important in Crohn's disease (CD). We aimed to establish new disease activity indices for CD based on noninvasive parameters. The data of 110 patients with CD were retrospectively analyzed. Parameters from bowel ultrasound and biomarkers were measured to select the variables included in the models by univariate analysis. Logistic regression analysis was performed to predict mucosal and transmural activities defined by ileocolonoscopy or computed tomography enterography, respectively. The models' performance was measured by the area under the receiver operating characteristic (ROC) curve (AUC). Leave-one-out cross validation (LOOCV) was applied to adjust for overconfidence in the newly established score models. To predict mucosal activity, erythrocyte sedimentation rate (ESR) and (LimG × BWT)-SUM (the sum of the product of Limberg grade [LimG] and bowel wall thickness [BWT] of each bowel segment) were selected for model A, and the equation was A = 2 × ESR + 9.3 × (LimG × BWT)-SUM. The AUC of ROC, sensitivity, and specificity were 0.927%, 89.8%, and 86.4%, respectively. The AUC of the ROC curve verified by LOOCV was 0.913. To predict transmural activity, albumin (ALB) and LimG-SUM (the sum of the LimG of all the bowel segments) were selected for model B, which was established as B = -1.3 × ALB +1.7 × LimG-SUM. The AUC of ROC, sensitivity, and specificity were 0.851%, 78.0%, and 84.2%, respectively. The AUC of the ROC curve verified by LOOCV was 0.833. Nomograms were developed for two score models. New score models based on noninvasive parameters established in this study showed good abilities in detecting active disease and performed well in the validation phase.

FIGURE 1

(a) Nomogram of the score model (model A) for predicting mucosal activity in patients with CD based on ESR and BUS parameters. ESR, unit: mm/h; BUS, represents for (LimG × BWT)‐SUM, the sum of the product of LimG and BWT of each bowel segment, unit: cm. (b) Receiver operating characteristic curves for the score model (model A) for predicting mucosal activity in patients with CD. (c) Calibration curves of actual versus predicted probability of mucosal activity in patients with CD using the score (model A). The ideal perfect prediction is shown by the dotted diagonal (ideal). The performance of model A is shown by the dotted line surrounding the diagonal (apparent). The score model performance as assessed by bootstrap validation with 1000 replications is shown by the continuous line surrounding the ideal diagonal (bias‐corrected). The closeness between the apparent line, the bias‐corrected lines, and the diagonal suggests good agreement between the prediction and actual observation. AUC, area under the receiver operating characteristic curve; BUS, bowel ultrasound; BWT, bowel wall thickness; CD, Crohn's disease; ESR, erythrocyte sedimentation rate; LimG, Limberg grade.

FIGURE 2

Receiver operating characteristic curves for the score model (model A) for predicting mucosal activity in patients with Crohn's disease with leave‐one‐out cross validation. AUC, area under the receiver operating characteristic curve.

FIGURE 3

(a) Nomogram of the score model (model B) for predicting transmural activity in patients with CD based on albumin and bowel ultrasound parameters. ALB, unit: g/L; BUS, represents for LimG‐SUM, the sum of the LimG of all the bowel segments. (b) Receiver operating characteristic curves for the score model (model B) for predicting transmural activity in patients with CD. (c) Calibration curves of actual versus predicted probability of transmural activity in patients with CD using the score (model B). The ideal perfect prediction is shown by the dotted diagonal (ideal). The performance of model B is shown by the dotted line surrounding the diagonal (apparent). The score model performance as assessed by bootstrap validation with 1000 replications is shown by the continuous line surrounding the ideal diagonal (bias‐corrected). The closeness between the apparent line, the bias‐corrected line and the diagonal suggests good agreement between the prediction and actual observation. AUC, area under the receiver operating characteristic curve; BUS, bowel ultrasound; CD, Crohn's disease; LimG, Limberg grade.

FIGURE 4

Receiver operating characteristic curves for the score model (model B) for predicting transmural activity in patients with Crohn's disease with leave‐one‐out cross validation. AUC, area under the receiver operating characteristic curve.