Table 1_An interpretable machine learning model for predicting symptomatic pelvic lymphoce

Table 1_An interpretable machine learning model for predicting symptomatic pelvic lymphocele after pelvic lymphadenectomy in cervical cancer.xls contains clinical and laboratory data from 221 patients with cervical cancer. The data was collected at the Affiliated Hospital of North Sichuan Medical College between January 2023 and September 2024. Author Yiyue Wang published the dataset on figshare under a CC-BY-4.0 license.

Use Cases

• Training a predictive model for symptomatic pelvic lymphocele based on clinical characteristics and laboratory data.
• Validating machine learning models (e.g., KNN, XGBoost) for medical risk prediction using AUC and Brier Score metrics.
• Conducting feature importance analysis for surgical outcomes using methods like SHAP.
• Performing univariate analysis to identify risk factors for post-operative complications.

Strengths

• Dataset includes 221 patient records with a clear outcome variable (44 cases of symptomatic pelvic lymphocele).
• Model performance metrics are provided, including a test set AUC of 0.832 for the KNN model.
• Key predictive features identified via SHAP analysis are listed: diabetes, surgical approach, preoperative monocyte-to-lymphocyte ratio, preoperative fibrinogen level, and tumor size.

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 in China, which may reflect geographic and institutional biases.

Provenance

Source

Affiliated Hospital of North Sichuan Medical College, collected by author Yiyue Wang.

Collection Method

Retrospective analysis of clinical characteristics and laboratory data from patient records.

Time Range

January 2023 to September 2024.

Freshness

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

Geography

China (hospital location implied).