Explainable Machine Learning for Predicting Early Gastric Cancer

NCT07047937 | Enrolling By Invitation DMC

• 1 other identifier: 202506031607000064611
• Study Type: observational
• Target: 10
• Locations: 1 country
• Sites: 1

Brief Summary

Abstract Background: Early detection of gastric cancer is crucial for improving patient survival rates. Currently, the primary method for diagnosing early-stage gastric cancer is endoscopy, which has various limitations. Additionally, single laboratory tests continue to fall short of the requirements for early screening. This study aims to develop a machine learning (ML) model using clinical data to predict early-stage gastric cancer and apply SHapley Additive exPlanation (SHAP) values to explain the ML model. Methods: This study involved patients who provided gastric tissue samples at Wenzhou Central Hospital from 2019 to 2023. The investigators gathered various laboratory test results from these patients. The investigators constructed and evaluated nine ML models to predict early-stage gastric cancer, using the area under the curve (AUC), accuracy, and sensitivity to assess their performance. For the most effective prediction model, The investigators utilized the SHAP method to determine the features' importance and explain the ML model.

Conditions

Early Gastric Cancer

Keywords

early detection of cancer; early gastric cancer; machine learning; prediction model; SHapley Additive exPlanation (SHAP)

Outcome Measures

Primary Outcomes (1)

• Explainable machine learning for predicting early gastric cancer

  The area under the ROC curve (AUC) was used as the primary outcome measure

  From June 2025 to July 2025

Secondary Outcomes (1)

• Explainable machine learning for predicting early gastric cancer

  From June 2025 to July 2025

Other Outcomes (1)

• Explainable machine learning for predicting early gastric cancer

  From June 2025 to July 2025

Eligibility Criteria

• Sex: all
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

all patients with a gastric tissue pathology result are included,1,085 patients were included in the study

You may qualify if:

• all patients with a gastric tissue pathology result are included

You may not qualify if:

• unclear or incomplete pathology results
• significant missing laboratory data
• progressive and advanced gastric cancer

Sponsors & Collaborators

• Wenzhou Central Hospital: lead

Study Sites (1)

Wenzhou Central Hospital

Wenzhou, Zhejiang, China

Location

MeSH Terms

Conditions

Stomach Neoplasms

Condition Hierarchy (Ancestors)

Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Stomach Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 10 Days
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Resident in gastrointestinal surgery

Study Record Dates

• First Submitted: June 4, 2025
• First Posted: July 2, 2025
• Study Start: June 28, 2025
• Primary Completion: July 1, 2025
• Study Completion: July 1, 2025
• Last Updated: July 2, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL
• Time Frame: Approximately from August 1, 2025 to November 1, 2025.
• Access Criteria: Log in to the clinical trial public management platform, and researchers can query the original research records and data of the research plan on this platform.

Locations

CN (1)