Incremental Value of Traditional Chinese Medicine Features in Two-Stage Pre-Endoscopic Prediction

NCT07784114 | Completed

• 1 other identifier: 82374298
• Study Type: observational
• Target: 1,500
• Locations: 0 countries
• Sites: N/A

Brief Summary

This observational study evaluates whether adding Traditional Chinese Medicine (TCM)-related clinical features improves the performance of machine-learning models that estimate disease risk before colonoscopy. We compare two modeling strategies that use the same sequential (two-stage) framework: Western-only models, based on demographic, clinical, and laboratory information commonly used in Western medicine. TCM-integrated models, which use the same types of Western information plus structured TCM features. Stage 1 aims to distinguish people more likely to have functional bowel problems from those more likely to have inflammatory or neoplastic colorectal disease. Stage 2 focuses on people in the higher-risk pathway and aims to distinguish ulcerative colitis from other inflammatory or neoplastic conditions. Models are developed in one dataset and tested in independent external data from other centers. We assess discrimination (including AUC), clinical usefulness with decision-curve analysis, and which TCM features contribute most in the integrated models. This study does not assign treatments. It analyzes existing clinical information to support future pre-endoscopic triage research. Results will not replace colonoscopy or clinician judgment.

Conditions

Ulcerative Colitis (Disorder); Crohn Disease (CD); Inflammatory Bowel Diseases; Colorectal Neoplasms

Keywords

Traditional Chinese Medicine; TCM-integrated model; Western medicine model; Machine learning; Decision curve analysis

Outcome Measures

Primary Outcomes (1)

• Difference in External-Validation AUC (ΔAUC) Between TCM-Integrated and Western-Only Two-Stage Pre-Endoscopic Prediction Models

  The primary outcome is the difference in area under the receiver operating characteristic curve (ΔAUC = AUC\_TCM-integrated - AUC\_Western-only) for matched machine-learning algorithms assessed in independent external validation. ΔAUC is reported for the two sequential prediction stages: Stage 1 (functional-predominant versus inflammatory-neoplastic pathway) and Stage 2 (ulcerative colitis versus other inflammatory or neoplastic conditions). Higher ΔAUC indicates greater incremental discriminative value of the TCM-integrated strategy.

  Baseline (index visit; all pre-endoscopic assessments within 1 day)

Eligibility Criteria

• Age: 18 Years - 85 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study includes adults from multiple participating centers in China who underwent clinical evaluation and colonoscopy-related diagnostic work-up for suspected functional bowel disorders or colorectal inflammatory / neoplastic disease. A development cohort is used to train two-stage machine-learning prediction models under Western-only and TCM-integrated strategies. Independent external-validation cohorts from other centers are used to assess generalizability. No study treatment is assigned; analyses use existing clinical data collected under institutional approvals.

You may qualify if:

• Adults aged 18 years or older Patients evaluated in participating centers with clinical records suitable for pre-endoscopic risk assessment related to colorectal inflammatory or functional bowel conditions Underwent colonoscopy (or had a colonoscopy-confirmed final diagnosis) allowing assignment to the study diagnostic labels used in the two-stage framework Stage 1-eligible diagnoses classifiable as either a functional-predominant pathway (e.g., irritable bowel syndrome / related functional presentations as defined in the protocol) or an inflammatory-neoplastic pathway (ulcerative colitis, Crohn disease, indeterminate colitis, or colorectal neoplasia as defined in the protocol) For Stage 2 analyses: patients within the inflammatory-neoplastic pathway classifiable as ulcerative colitis versus other inflammatory or neoplastic conditions (Crohn disease, indeterminate colitis, or colorectal neoplasia) Availability of required Western clinical and laboratory predictors for model development or validation For TCM-integrated analyses: availability of protocol-defined structured Traditional Chinese Medicine (TCM) features Ability to assign the record to the development cohort or an independent external-validation cohort according to the protocol center rules

You may not qualify if:

• Age younger than 18 years Missing or unverifiable final diagnostic label required for Stage 1 and/or Stage 2 Missing key predictors required by the Western-only and/or TCM-integrated modeling pipelines (per protocol variable lists) Diagnosis outside the predefined Stage 1 / Stage 2 label sets and not mappable under protocol rules Duplicate or overlapping records for the same patient encounter after de-duplication Records excluded by pre-specified data-quality or center-specific protocol rules (e.g., incomplete critical clinical documentation)

Sponsors & Collaborators

• Beijing University of Chinese Medicine: lead

MeSH Terms

Conditions

Colitis, Ulcerative; Crohn Disease; Inflammatory Bowel Diseases; Colorectal Neoplasms

Condition Hierarchy (Ancestors)

Colitis; Gastroenteritis; Gastrointestinal Diseases; Digestive System Diseases; Colonic Diseases; Intestinal Diseases; Intestinal Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Rectal Diseases

Study Design

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

Study Record Dates

• First Submitted: August 15, 2026
• First Posted: August 25, 2026
• Study Start: January 1, 2015
• Primary Completion: June 1, 2025
• Study Completion: June 1, 2025
• Last Updated: August 25, 2026

Record last verified: 2026-08