Tokyo, May 2 -- UMIN Clinical Trials Registry (UMIN-CTR) received information related to the study (UMIN000061288) titled 'Development and External Validation of Machine Learning Models for Predicting Postoperative Recurrence in Gastric Cancer: A TRIPOD+AI-Compliant Single-Center Cohort Study' on May 1.
Study Type:
Observational
Primary Sponsor:
Institute - Kameda Medical Center
Condition:
Condition - Gastric cancer
Classification by malignancy - Malignancy
Genomic information - NO
Objective:
Narrative objectives1 - The aims of this study were to: (1) develop ML models for postoperative gastric cancer recurrence in a Japanese single-center curative resection cohort using multivariate iterative imputation; (2) evaluate external generalizability in an independent holdout cohort; (3) improve probability calibration via post-hoc sigmoid calibration; (4) quantify clinical utility using bootstrap-corrected DCA; and (5) assess model interpretability using SHAP values.
Basic objectives2 - Efficacy
Eligibility:
Age-lower limit - 20
years-old
=
Gender - Male and Female
Key inclusion criteria - Age is greater than or equal to 20 years
Histologically confirmed gastric adenocarcinoma
Underwent curative (R0) gastrectomy (total, distal, or proximal gastrectomy with lymph node dissection)
Surgery performed between April 2008 and March 2020 at the study institution
Follow-up duration of at least 3 months
Key exclusion criteria - Presence of concurrent non-gastric malignancies
Receipt of neoadjuvant chemotherapy or chemoradiotherapy
Emergency surgery or reduced-function procedures
Follow-up duration of less than 3 months
Target Size - 1162
Recruitment Status:
Recruitment status - Preinitiation
Date of protocol fixation - 2025 Year 04 Month 24 Day
Anticipated trial start date - 2025 Year 04 Month 25 Day
Last follow-up date - 2026 Year 03 Month 31 Day
To know more, visit https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000070124
Disclaimer: Curated by HT Syndication.
