Young Women with Localized Breast Cancer: Survival Risk Stratification, 2000-2023

1,060 women aged ≤40 years diagnosed with stage I–III breast cancer were studied in a single-center retrospective cohort. The data includes clinicopathological variables and treatment details used to build a Random Survival Forest model for risk stratification, achieving a C-index of 0.723. Author Bin Xu published the dataset under a CC-BY-4.0 license on figshare.

Use Cases

• Training survival prediction models based on clinicopathological features like pathological subtype and T stage.
• Analyzing the impact of specific treatments like radiotherapy and endocrine therapy on overall survival.
• Investigating the unexpected association between high Ki67 expression and improved survival in this population.
• Benchmarking machine learning models for risk stratification in oncology using a dataset with 79.8 months median follow-up.

Strengths

• Includes data from 1,060 patients with a median follow-up of 79.8 months.
• Model performance is quantified with a C-index of 0.723.
• Specific hazard ratios for key prognostic factors like nipple invasion (HR=3.95) are provided.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data table is unknown, which may limit suitability assessment.
• Data is from a single-center retrospective study, which may limit generalizability.

Provenance

Source

figshare, author Bin Xu.

Collection Method

Single-center retrospective cohort study.

Time Range

Patients diagnosed between 2000 and 2023.

Freshness

Last updated 2026-05-05 05:24:43; freshness should be verified.