Cure8 trial brief
Researchers are exploring ways to prioritize who needs colonoscopy sooner; adding TCM features to prediction models might change triage performance. Patients and clinicians interested in pre-endoscopic risk tools or integrative medicine approaches may find the study relevant.
Researchers and data scientists working on IBD diagnostic models, clinicians involved in pre-endoscopic triage, and patients or centers interested in integrative (TCM + Western) approaches to diagnostic prediction.
The trial record describes a multicenter, retrospective diagnostic modeling study (TCM-PREDICT) that developed and externally validated two parallel two-stage prediction strategies: a Western-only model using routine demographic, clinical, and laboratory data, and a TCM-integrated model that adds structured TCM clinical features.
The main outcome is the difference in external-validation AUC between the two strategies for both stages of the sequential framework. Models are intended to inform research on pre-endoscopic triage and are not a replacement for colonoscopy or clinician judgment.
The registry lists planned enrollment (about 1,500), eligibility (adults 18–85 with colonoscopy-confirmed diagnoses), and that results will include discrimination metrics (AUC), decision-curve analysis, and feature-importance explanations (e.g., SHAP) for TCM variables. No treatments were assigned because this is a retrospective diagnostic modeling study.
This is a completed multicenter retrospective modeling study registered on ClinicalTrials.gov. The registry text describes methods and planned analyses but does not present numeric results in the supplied extraction. Models are explicitly framed as research tools and not substitutes for colonoscopy or clinical care.
Review the original publication for the complete reporting, methods, and context.
This Cure8 brief is based on source text from the linked article. Cure8 is informational only and is not a substitute for professional medical advice, diagnosis, or treatment.
AI tools could make objective disease assessment faster and more consistent, help detect inflammation beyond what symptoms suggest, and ultimately support more personalized treatment choices for people with Crohn’s...
This study suggests machine learning of stool microbiome data could eventually help distinguish IBD (especially Crohn’s) from healthy people and some other bowel or systemic conditions.
A long-term study that profiles immune cells, genes, diet, and the microbiome could help identify biomarkers that predict flares or response to therapy, which matters to people living with Crohn’s or ulcerative colitis.
