Survival Data for Elderly Esophageal Cancer Patients Treated with Radiotherapy

308 elderly patients with locally advanced esophageal squamous cell carcinoma were enrolled in a retrospective study. The dataset includes clinicopathological and nutritional-inflammatory variables used to construct nine survival models for predicting overall and progression-free survival. The research was authored by Jie Zou and last updated on 2026-05-11.

Use Cases

• Compare the performance of conventional and machine learning-based survival models based on the nine models constructed.
• Identify key nutritional-inflammatory biomarkers for prognosis based on features like GNRI and PNI highlighted in the SHAP analysis.
• Refine risk assessment for elderly cancer patients based on the Ridge-based predicted-risk thresholds described.
• Explore survival heterogeneity across elderly subgroups based on the exploratory age-stratified analyses mentioned.

Strengths

• Dataset includes 308 patient records, with a 7:3 split for training and testing cohorts.
• Model performance was evaluated using multiple metrics: concordance index, time-dependent AUC, and integrated Brier score.
• Analysis includes SHAP to clarify predictor contributions over follow-up time.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single retrospective study; external validation is noted as necessary.

Provenance

Source

Retrospective study by Jie Zou, platform figshare.

Collection Method

Retrospective study of patients treated with definitive radiotherapy.

Freshness

Last updated 2026-05-11 05:28:55; freshness should be verified.