Radiation Pneumonitis NTCP Model Validation Data for Lung Cancer Patients

A clinical dataset of 580 lung cancer patients treated with thoracic IMRT between 2018 and 2023, used to validate and update NTCP models for radiation pneumonitis. The dataset was created by Zhi Chen and includes an external validation cohort of 100 patients from an independent center. It was last updated in April 2026.

Use Cases

• Validating NTCP models for radiation pneumonitis based on clinical and DVH variables.
• Developing simplified predictive models based on features like age, tumor stage, and smoking status.
• Assessing model calibration and discrimination using metrics like AUC and Brier score.
• Performing decision curve analysis to evaluate the clinical utility of risk prediction models.

Strengths

• Includes a development cohort of 580 patients and an external validation cohort of 100 patients.
• Model performance is quantified with specific metrics (e.g., AUC 0.708, Brier 0.215).
• Dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the primary data is unknown, which may limit suitability assessment.
• Data may reflect temporal and treatment modality bias inherent to the specific patient cohorts studied.

Provenance

Source

figshare

Collection Method

Retrospective analysis of patient records from a clinical trial (ChiCTR2500102055).

Time Range

2018-2023 for the primary development cohort.

Freshness

Last updated 2026-04-28 04:29:08; freshness should be verified.