Endoscopic Grading of Gastric Intestinal Metaplasia for Cancer Risk Assessment

144 patients were enrolled in a prospective study validating endoscopic scoring for gastric cancer risk. The modified EGGIM model incorporating microvascular pattern achieved an AUC of 0.921 for identifying high-risk OLGIM stages. Authored by Xueling Zhang and shared under CC-BY-4.0, this dataset supports research on non-invasive endoscopic risk stratification.

Use Cases

• Validate endoscopic scoring systems for gastric intestinal metaplasia based on the described EGGIM and modified EGGIM models.
• Assess the diagnostic performance of microvascular pattern evaluation for predicting high-risk gastric cancer development.
• Develop machine learning models for risk stratification using the reported sensitivity, specificity, and predictive values.
• Compare the diagnostic accuracy of different endoscopic grading criteria for OLGIM III-IV stages.

Strengths

• Dataset is based on a prospective study design involving 144 patients.
• Provides specific diagnostic performance metrics, including an AUC of 0.921 for the modified model.
• Includes validated statistical results such as odds ratios (OR=4.696) and confidence intervals.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is stored in a DOCX file format (32.0 KB), which may require extraction and structuring for analysis.

Provenance

Source

figshare

Collection Method

Prospective clinical study where patients underwent endoscopic scoring and biopsy.

Freshness

Last updated 2026-05-10 19:00:03; freshness should be verified.