NCT07351708

Development and Validation of a Post-operative Risk Of Local Recurrence Model Integrating Serology and Evalution (PROMISE) in Local Advanced Rectal Cancer Receiving Neoadjuvant Therapy: a Multicenter Study

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 2,315 (actual)
• Sponsor: Cai Zerong · Academic / Other
• Sex: All
• Age: 20 Years – 90 Years
• Healthy volunteers: Not accepted

Summary

Local recurrence (LR) in locally advanced rectal cancer (LARC) correlated with poor survival and impaired quality of life. The aim of this study was to develop and validate machine learning (ML) models integrating clinicopathological features and inflammatory signature to predict LR in LARC patients undergoing neoadjuvant therapy followed by total mesorectal excision.

Detailed description

To address the gap in accessible and integrative risk prediction, this study aimed to develop and validate an interpretable machine learning model for the early prediction of postoperative local recurrence in LARC patients using a multicenter cohort. We employed SHapley Additive exPlanations (SHAP) analysis to elucidate feature importance and provide clear interpretations for individual predictions, with the ultimate goal of evaluating the model's clinical utility in guiding personalized patient management-particularly by identifying high-risk patients in clinical practice and informing tailored follow-up and treatment strategies to improve patient outcomes.

Conditions

• Locally Advanced Rectal Cancer (LARC)

Timeline

• Start date: 2010-01-06
• Primary completion: 2022-12-30
• Completion: 2025-11-30
• First posted: 2026-01-20
• Last updated: 2026-01-20