Prediction of early mucosal healing of Crohn’s disease after treatment with biologics- a novel nomogram based on radiomics and clinical risk factors
BackgroundPredicting endoscopic remission is crucial for optimizing clinical treatment strategies and switching biologics in Crohn’s disease (CD). Mucosal healing (MH) is a key therapeutic target. This study aimed to develop a clinically applicable prediction model for early MH in CD patients receiv...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2025.1586300/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | BackgroundPredicting endoscopic remission is crucial for optimizing clinical treatment strategies and switching biologics in Crohn’s disease (CD). Mucosal healing (MH) is a key therapeutic target. This study aimed to develop a clinically applicable prediction model for early MH in CD patients receiving biological therapy.MethodsThis study retrospectively analyzed 120 CD patients diagnosed between 2018 and 2023, randomly divided into a training cohort and an internal validation cohort 1. Additionally, 34 prospectively enrolled CD patients diagnosed between 2024 and 2025 formed an internal validation cohort 2. Clinical indicators and conventional imaging features were evaluated to establish a clinical model. Radiomics features were extracted from computed tomography enterography (CTE) images, with regions of interest (ROIs) manually delineated to align with ulcerated intestinal segments identified through colonoscopy. A radiomics model was constructed, and a radiomics score (Rad-score) was derived. A clinical-radiomics nomogram was then developed by integrating Rad-score with clinical risk factors. Model performance was assessed using discrimination, calibration, decision curve analysis (DCA), and clinical impact curves.ResultsThe clinical-radiomics nomogram demonstrated strong predictive performance, with AUC values of 0.948 (95% CI: 0.902–0.995) in the training cohort, 0.925 (95% CI: 0.805–1.0) in the internal validation cohort 1, and 0.940 (95% CI: 0.802–0.993) in the internal validation cohort 2. The nomogram outperformed standalone clinical and radiomics models, with DCA confirming its clinical utility.ConclusionThe developed nomogram effectively predicts early MH in CD patients undergoing biological therapy, providing a practical tool for clinicians to optimize treatment strategies and improve outcomes. |
|---|---|
| ISSN: | 1663-9812 |