Clinical Data for Predicting Lymphocele in Cervical Cancer Patients, 221 Records

19.9% of the 221 cervical cancer patients studied developed symptomatic pelvic lymphocele after surgery. The dataset contains clinical characteristics and laboratory data from a retrospective analysis at the Affiliated Hospital of North Sichuan Medical College, collected between January 2023 and September 2024. It was used to develop and validate interpretable machine learning models for predicting this surgical complication.

Use Cases

• Training a predictive model for surgical complications based on clinical characteristics and laboratory data.
• Identifying key risk factors for symptomatic pelvic lymphocele based on features like diabetes and tumor size.
• Benchmarking machine learning models (e.g., KNN, XGBoost) on a clinical tabular dataset.
• Applying model interpretability techniques (e.g., SHAP) to understand feature importance in a medical context.

Strengths

• Includes data from 221 patients with a clear outcome incidence of 19.9%.
• Model performance metrics are provided, including an AUC of 0.952 for the KNN model in the training set.
• Key predictive features identified via SHAP analysis are listed in the description.

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, which may reflect geographic or institutional bias.

Provenance

Source

Affiliated Hospital of North Sichuan Medical College

Collection Method

Retrospective analysis of clinical records.

Time Range

January 2023 to September 2024

Freshness

Last updated 2026-04-15 05:44:13; freshness should be verified.

Geography

Likely China (based on hospital name).