Breast Cancer-Related Lymphedema Risk Prediction Model

A retrospective cohort study of 234 patients undergoing breast cancer surgery, of whom 27 (11.5%) developed lymphedema. The dataset was used to develop and internally validate a predictive nomogram using Firth penalized logistic regression. Authored by Yufei Fan and last updated on June 3, 2026.

Use Cases

• Predicting risk of ipsilateral upper-limb lymphedema based on surgery type and nodal factors.
• Validating clinical prediction models using bootstrap optimism correction and decision curve analysis.
• Identifying high-risk patients for targeted preventive interventions based on the four-variable nomogram.

Strengths

• Model demonstrated excellent discriminative ability with an apparent AUC of 0.964.
• Dataset includes 234 patient records with a defined outcome prevalence of 11.5%.
• Analysis employed advanced statistical methods (LASSO, Firth penalized regression) to handle limited outcome events.

Limitations

• Dataset is very small at 15.2 KB; row count and column-level documentation are unknown.
• Model shows residual overfitting indicated by an optimism-corrected calibration slope of 0.711.
• Data is limited to internal validation; external validation is pending.

Provenance

Source

figshare

Collection Method

Retrospective cohort study of patients undergoing breast cancer surgery.

Freshness

Last updated 2026-06-03 04:47:19