Lili Huang,1,* Jixin Meng,1,2,* Shaochun Lin,1,* Zhenpeng Peng,1,* Ruonan Zhang,1 Xiaodi Shen,1 Weikai Zheng,1 Qingzhu Zheng,1 Luyao Wu,1 Xinyue Wang,1 Yangdi Wang,1 Ren Mao,3 Canhui Sun,1 Xuehua Li,1 Shi-Ting Feng1 

1Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, People’s Republic of China; 2Department of Radiology, Henan Provincial People’s Hospital & Zhengzhou University People’s Hospital, Zhengzhou, People’s Republic of China; 3Department of Gastroenterology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Xuehua Li, Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, People’s Republic of China, Tel +86-20-87755766-8471, Email lxueh@mail.sysu.edu.cn Shi-Ting Feng, Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, People’s Republic of China, Fax +86-20-87615805, Email fengsht@mail.sysu.edu.cn

Purpose: Cumulative bowel damage (BD) critically influences the progression and prognosis of Crohn’s disease (CD). Although the Lémann Index (LI) remains the standard for BD assessment, its clinical utility is limited by heavy reliance on extensive clinical data. Multiparametric magnetic resonance enterography (MRE) provides noninvasive macroscopic evaluation of BD severity, however, it fails to characterize microscopic alterations. We therefore integrated MRE with gut microbiome and metabolomic data to uncover mechanistic insights and develop a comprehensive model for better prediction of BD.
Methods and Results: In this prospective two-center study, 309 CD patients were stratified into BD and non-BD groups using LI. Patients underwent MRE, fecal 16S rRNA gene sequencing, and fecal/serum metabolomic analysis. Thirty healthy controls were included for comparison. The relationships between microbial/metabolic factors and MRE features were explored using correlation and mediation analyses. Seven machine learning algorithms, each paired with seven distinct combinations of multi-omics features, were evaluated using nested 5-fold cross-validation to construct an optimal prediction model. BD patients exhibited reduced gut microbial diversity (P< 0.05), with Erysipelatoclostridium and [Ruminococcus]_gnavus_group as key discriminators. Metabolomics revealed elevated fecal aromatic amino acids and depleted serum glycerophospholipids/sphingolipids (P< 0.05) linked to MRE-quantified features through mediation by microbial pathways (eg, 22.8% mediation effect of Prevotella_9 on penetration, PACME=0.022). The optimal Xtreme Gradient Boosting Classifier (XGBC) model integrating three microbial genera, six fecal metabolites, three serum metabolites, and three MRE features achieved superior performance (AUC 0.857 and 0.829 in the derivation and external validation cohorts, respectively). SHapley Additive exPlanations (SHAP) analysis prioritized perianal diseases, Erysipelatoclostridium, and fecal alanine as key contributors.
Conclusion: Our study underscores the interplay between gut microbial dysbiosis, metabolic alterations, and MRE-quantified structural changes in BD patients. The integrated multi-omics model provides a promising tool for BD prediction, enabling precise CD severity stratification and personalized clinical decision-making.
Plain Language Summary: Crohn’s disease is a long-term condition that causes inflammation of the digestive tract and can lead to significant bowel damage over time. Although tools such as the Lémann Index help assess this damage, they mainly rely on clinical records and do not reveal the biological processes behind the damage. In this study, we aimed to develop a more accurate method for predicting bowel damage. We combined the three methods into a single comprehensive test.Imaging: Magnetic resonance enterography (MRE), a noninvasive scan, was used to capture clear images of the bowel. This allowed us to observe signs of inflammation, such as thickened bowel walls, swelling in the surrounding tissues, abnormal blood vessel patterns, as well as other structural damage.Gut Bacteria Analysis: We examined stool samples to understand the variety and balance of the gut bacteria.Metabolite Testing: We analyzed both stool and blood samples to measure metabolic markers.
We studied 309 individuals with Crohn’s disease and compared them with 30 healthy volunteers. Our findings revealed that the changes seen on MRE were closely linked to shifts in gut bacteria and metabolic markers. For instance, individuals with bowel damage had less diverse gut bacteria, higher levels of certain amino acids in their stool, and lower levels of important lipids in their blood.
These results suggest that integrating these tests into a single diagnostic tool could help doctors quickly and accurately identify bowel damage. This, in turn, may lead to more personalized treatment and better outcomes for individuals with Crohn’s disease.

Keywords: Crohn’s disease, gut microbial dysbiosis, metabolomic signatures, magnetic resonance enterography, machine learning modelling