Artificial Intelligence-Based Classification and Prognostic Prediction in Small Bowel Crohn's Disease

NCT07757217 | Completed

• 1 other identifier: SHSY-IEC-6.0/25KY58/P01
• Study Type: observational
• Target: 437
• Locations: 1 country
• Sites: 1

Brief Summary

This retrospective observational study aims to develop an artificial intelligence-based system for the precise classification and prognostic prediction of small bowel Crohn's disease. The study includes 437 patients with Crohn's disease who were hospitalized at Shanghai Tenth People's Hospital between January 1, 2020, and January 31, 2025. Clinical information, laboratory results, endoscopic findings, computed tomography enterography or magnetic resonance enterography images, and available pathological and molecular data will be collected from existing medical records. Artificial intelligence-based image segmentation and multimodal analysis will be used to identify and quantify intestinal lesions, strictures, mesenteric changes, fistulas, abscesses, and other disease characteristics. The study will examine whether these features can classify patients more accurately and predict clinical outcomes, including response to medical treatment, treatment failure or switching, and the need for surgery. The resulting system may support individualized assessment and clinical decision-making for patients with small bowel Crohn's disease.

Conditions

Crohn's Disease

Keywords

Small Bowel Crohn Disease; Artificial Intelligence; Machine Learning; Prognostic Prediction; Radiomics

Outcome Measures

Primary Outcomes (1)

• Discriminative Performance of the Artificial Intelligence-Based Multimodal Model for Predicting 12-Month Clinical Outcomes

  The area under the receiver operating characteristic curve will be used to evaluate the ability of the artificial intelligence-based multimodal model to predict the patient's clinical outcome. Clinical outcomes will be classified as effective medical treatment, treatment failure or recurrence requiring treatment switching, or Crohn's disease-related intestinal surgery.

  Within 12 months after the index CTE or MRE examination

Secondary Outcomes (2)

• Sensitivity and Specificity of the Multimodal Prediction Model

  Within 12 months after the index CTE or MRE examination

• Proportion of Patients Requiring Treatment Switching

  Within 12 months after the index CTE or MRE examination

Study Arms (3)

Effective Medical Treatment

Patients with small bowel Crohn's disease who achieved and maintained an effective clinical response to medical treatment without treatment switching or Crohn's disease-related surgery during the prespecified follow-up period.

Other: Artificial Intelligence-Based Multimodal Analysis

Treatment Failure or Switching

Patients with small bowel Crohn's disease who experienced an inadequate response, loss of response, or disease recurrence requiring a switch in medical treatment during the prespecified follow-up period.

Other: Artificial Intelligence-Based Multimodal Analysis

Crohn's Disease-Related Surgery

Patients with small bowel Crohn's disease who underwent Crohn's disease-related intestinal surgery because of disease activity, intestinal stricture or obstruction, penetrating complications, or other Crohn's disease-related indications during the prespecified follow-up period.

Other: Artificial Intelligence-Based Multimodal Analysis

Interventions

Artificial Intelligence-Based Multimodal Analysis OTHER

Existing CTE or MRE images will be analyzed using interactive artificial intelligence-based image segmentation. Imaging features will be integrated with available clinical, laboratory, endoscopic, pathological, and molecular data to classify small bowel Crohn's disease and predict subsequent clinical outcomes. This retrospective observational study does not assign any treatment or alter routine clinical care.

Crohn's Disease-Related Surgery; Effective Medical Treatment; Treatment Failure or Switching

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of patients with small bowel Crohn's disease who were hospitalized in the Department of Gastroenterology at Shanghai Tenth People's Hospital between January 1, 2020, and January 31, 2025. Eligible patients will be identified retrospectively from existing medical records. Patients must have adequate CTE or MRE images and sufficient clinical and follow-up information for multimodal feature extraction and assessment of subsequent treatment response, treatment switching, or Crohn's disease-related intestinal surgery.

You may qualify if:

• Diagnosis of Crohn's disease established according to the European Crohn's and Colitis Organisation criteria based on clinical, endoscopic, radiological, and/or histopathological findings.
• Small bowel involvement confirmed by computed tomography enterography, magnetic resonance enterography, endoscopy, surgery, and/or histopathology.
• Availability of CTE or MRE images obtained before treatment and during follow-up. Follow-up imaging was performed within 6 months after treatment for patients with active disease or within 1 to 2 years for patients in remission.
• Availability of sufficient clinical and follow-up information to determine treatment response, treatment switching, or Crohn's disease-related surgery.

You may not qualify if:

• Failure to receive regular medical treatment or follow-up.
• Incomplete clinical or laboratory data that prevent assessment of the prespecified variables or clinical outcomes.
• Poor-quality or incomplete CTE or MRE images that prevent reliable image segmentation or evaluation.
• Presence of a malignant tumor.
• Presence of severe comorbidities, including heart failure or other severe organ dysfunction, that may substantially affect clinical outcomes.

Sponsors & Collaborators

• Shanghai 10th People's Hospital: lead

Study Sites (1)

The Tenth People's Hospital of Shanghai

Shanghai, Shanghai Municipality, 201505, China

Location

MeSH Terms

Conditions

Crohn Disease

Condition Hierarchy (Ancestors)

Inflammatory Bowel Diseases; Gastroenteritis; Gastrointestinal Diseases; Digestive System Diseases; Intestinal Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Director

Study Record Dates

• First Submitted: August 6, 2026
• First Posted: August 11, 2026
• Study Start: January 1, 2020
• Primary Completion: October 31, 2025
• Study Completion: April 30, 2026
• Last Updated: August 11, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)