Ancient wisdom meets AI: could TCM features sharpen colorectal screening?

Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.

Inclusion Criteria: 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 Exclusion Criteria: 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)