NCT07267767

Comparison of Six Different Machine Learning Methods With Traditional Model for Low Anterior Resection Syndrome After Minimally Invasive Surgery for Rectal Cancer -- Development and External Validation of a Nomogram : A Dual-center Cohort Study

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 3,500 (actual)
• Sponsor: Northern Jiangsu People's Hospital · Academic / Other
• Sex: All
• Age: —
• Healthy volunteers: —

Summary

Following thorough screening based on inclusion and exclusion criteria, patients from the two sizable medical centers were split up into two cohorts for this study. Cohort 1 served primarily as the training and internal validation set, while Cohort 2 was used for external validation of the predictive model constructed from Cohort 1. We used six distinct machine learning methodss, including DT, RF, XGBOOST, SVM, lightGBM, and SHLNN, in addition to conventional logistic regression to create the predictive model. We chose the approach with the best sensitivity and specificity by comparing the concordance index(C-index) akin to the area under the ROC curve (AUC) of these seven distinct model-building methods. The predictive model for Cohort 1 was then built using this method, and internal validation was finished. Lastly, Cohort 2 underwent external validation of the predictive model

Conditions

• Rectal Cancer
• LARS - Low Anterior Resection Syndrome

Interventions

Type	Name	Description
PROCEDURE	nCRT	neoadjuvant chemoradiotherapy
BEHAVIORAL	BMI	Body Mass Index
DIAGNOSTIC_TEST	Distance from AV	Distance from AV
PROCEDURE	Surgical type	laparoscopic and robotic surgery
PROCEDURE	Surgical approach	tatme + isr
PROCEDURE	LCA Preserving	LCA Preserving
PROCEDURE	Prophylactic stoma	Prophylactic stoma
PROCEDURE	Anastomotic leakage	Anastomotic leakage

Timeline

• Start date: 2015-04-10
• Primary completion: 2023-10-07
• Completion: 2024-06-20
• First posted: 2025-12-05
• Last updated: 2025-12-05