External, Multicentre Validation of a Machine-Learning Model to Predict Colonic Adenoma in Indian Adults

External, Multicentre Validation of a Machine-Learning Model to Predict Colonic Adenoma in Indian Adults-A Prospective, Observational, Multicentre Study

Colorectal adenomas are precursors to colorectal cancer (CRC). Accurate pre-procedure risk stratification could optimize colonoscopy yield and resource allocation in India, where adenoma prevalence varies by age, sex, and lifestyle/metabolic factors. ML models can integrate multiple predictors to estimate individualized risk.

Existing risk scores are largely Western; performance and calibration may not be appropriate in Indian populations with different socio-demographic and metabolic profiles. External, prospective, multicentre validation is essential before clinical implementation.

Study Overview

• Status: Not yet recruiting
• Conditions: Colonoscopy
• Intervention / Treatment: Procedure: Not Applicable / Observational study

• Study Type: Observational
• Enrollment (Estimated): 1000

Contacts and Locations

• Study Contact: Name: DR. NITIN JAGTAP, MD,DM; Phone Number: 8712015028; Email: docsnitin13@gmail.com
• Study Contact Backup: Name: DR NITIN JAGTAP, MD,DM; Phone Number: 8712015028; Email: docsnitin13@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

1000

Description

Inclusion Criteria:

• Adults ≥18 years undergoing diagnostic colonoscopy.
• Adequate bowel preparation (Boston Bowel Preparation Scale total ≥6 with each segment ≥2).
• Complete examination (cecal intubation; withdrawal time ≥6 min when no therapy).
• Availability of all model predictors per CRF.

Exclusion Criteria:

• • Known CRC or polyp, prior colectomy, polyposis syndromes, known IBD, or strong hereditary CRC syndromes (e.g., Lynch) if excluded in derivation.

  • Inadequate prep, incomplete colonoscopy, obstructing lesions preventing optical diagnosis beyond obstruction.
  • Emergency colonoscopies, therapeutic-only procedures without diagnostic intent.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Single prospective observational cohort; Participants undergo standard-of-care colonoscopy No allocation into treatment or comparison arms	Procedure: Not Applicable / Observational study; No study-specific intervention is administered. Participants undergo standard-of-care diagnostic colonoscopy and histopathological evaluation. A locked machine-learning model is applied to routinely collected baseline clinical and demographic data for risk prediction only, without influencing clinical management.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Receiver Operating Characteristic Curve (AUROC) of the Machine Learning Model	Area under the receiver operating characteristic curve (AUROC) of the machine learning-based prediction model for identifying the presence of histologically proven colonic adenoma	1 YEAR

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Validation Performance of the Machine Learning Prediction Model	Validation performance of the machine learning model for predicting colonic adenoma, assessed using AUROC, calibration metrics (Brier score), and calibration plots in an independent validation cohort.	1 YEAR

Collaborators and Investigators

• Sponsor: Asian Institute of Gastroenterology, India

Study record dates

Study Major Dates

• Study Start (Estimated): February 1, 2026
• Primary Completion (Estimated): March 30, 2027
• Study Completion (Estimated): March 30, 2027

Study Registration Dates

• First Submitted: December 26, 2025
• First Submitted That Met QC Criteria: December 27, 2025
• First Posted (Estimated): January 9, 2026

Study Record Updates

• Last Update Posted (Estimated): January 12, 2026
• Last Update Submitted That Met QC Criteria: January 9, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Investigative Techniques; Methods; Observation
• Other Study ID Numbers: VALID-ADENOMA-IN

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No