Explainable Machine Learning for Predicting Early Gastric Cancer

Explainable Machine Learning for Predicting Early Gastric Cancer: a Retrospective Cohort Study

Status

Enrolling by invitation

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT07047937

Enrollment

Registered

2025-07-02

Start date

2025-06-28

Completion date

2025-07-01

Last updated

2025-07-02

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Early Gastric Cancer

Keywords

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

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.

Interventions

None listed

Study design

Observational model

COHORT

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Inclusion criteria

* all patients with a gastric tissue pathology result are included

Exclusion criteria

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

Design outcomes

Primary

Measure	Time frame	Description
Explainable machine learning for predicting early gastric cancer	From June 2025 to July 2025	The area under the ROC curve (AUC) was used as the primary outcome measure

Secondary

Measure	Time frame	Description
Explainable machine learning for predicting early gastric cancer	From June 2025 to July 2025	We considered the sensitivity of the model as a secondary outcome measure.

Other

Measure	Time frame	Description
Explainable machine learning for predicting early gastric cancer	From June 2025 to July 2025	We included model accuracy as other outcome measures.

Countries

China

Outcome results