Single-factor COX Proportional Risk Model: Early Gastric Cancer Patient Data

290 patients with early gastric cancer from Fujian Provincial Hospital, monitored for a median of 32 months after non-radical endoscopic submucosal dissection. Author Yangyang Chen published this dataset on figshare under a CC-BY-4.0 license. The study compares the predictive accuracy of the w-eCura and eCura systems for salvage surgery necessity.

Use Cases

• Validate the w-eCura risk stratification model based on clinicopathological characteristics described in the study.
• Train survival prediction models based on Kaplan-Meier survival analysis results.
• Compare model performance using ROC curve analysis metrics like AUC.
• Identify factors influencing positive cancer residue status based on Cox proportional hazard model findings.

Strengths

• Includes data from 290 patients, providing a substantial cohort for analysis.
• Contains a median follow-up duration of 32 months with a range of 15-54 months, offering longitudinal insight.
• Model performance is quantified with specific AUC values (0.82 for w-eCura, 0.79 for eCura).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is from a single hospital (Fujian Provincial Hospital), which may limit generalizability.

Provenance

Source

Fujian Provincial Hospital.

Collection Method

Retrospective case-control study.

Time Range

Patients treated between January 2011 and July 2024.

Freshness

Last updated 2026-05-19 17:25:31; freshness should be verified.

Geography

China (Fujian Provincial Hospital).