Clinical Predictors of BRCA1/2 Variants in High-Risk Breast Cancer Patients in China

From 2017 to 2021, this dataset includes 1,204 high-risk breast cancer patients from Zhejiang Cancer Hospital in eastern China. It contains clinical data used to develop a model predicting BRCA1/2 pathogenic variant carrier status, with 102 (8.5%) patients testing positive. The dataset was authored by Wei Gu and published under a CC-BY-4.0 license.

Use Cases

• Training a logistic regression model to predict BRCA1/2 carrier status based on clinical features like histology and family history.
• Benchmarking new predictive models against the reported AUC of 0.758 and Brier score of 0.071.
• Analyzing the association between triple-negative breast cancer (TNBC) and BRCA1/2 variant prevalence, noted as 55.9% in carriers.
• Conducting sensitivity and bootstrap validation studies on clinical prediction models, as described with 500 resamples.

Strengths

• Dataset is derived from a cohort of 1,204 high-risk patients, described as a large high-risk clinical cohort for mainland China.
• Model performance is quantitatively reported with an AUC of 0.758, a Brier score of 0.071, and bootstrap validation across 500 resamples.
• Clinical predictors are clearly named, including histology, molecular subtype, age, and family history.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying clinical data is unknown, which may limit suitability assessment.
• Data is specific to a single hospital in eastern China (Zhejiang Cancer Hospital), which may limit generalizability.

Provenance

Source

Zhejiang Cancer Hospital, eastern China.

Collection Method

Clinical data collection and targeted NGS for BRCA1/2 on blood samples, with variants classified by ClinVar and ACMG-AMP guidelines.

Time Range

2017–2021

Freshness

Last updated 2026-06-02 04:21:27; freshness should be verified.

Geography

Eastern China