CT Radiomics Model for Predicting Pain Relief After Radiotherapy in Bone Metastases

A dual-center study from Xuzhou, China, developed a CT-based radiomics model to predict pain relief after palliative radiotherapy for bone metastases. The dataset includes 134 patients from two hospitals, with clinical variables and radiomic features used to train 11 machine learning classifiers. The optimal k-nearest neighbors model achieved an AUC of 0.818 on an external test set.

Use Cases

• Predicting pain relief outcomes after radiotherapy based on CT radiomic features and clinical variables.
• Comparing the performance of 11 machine learning classifiers for a binary medical classification task.
• Validating a radiomics model on an external test set from a different hospital center.

Strengths

• Model was validated on an external test set of 17 patients from a second hospital center.
• The study compared 11 different machine learning algorithms for model selection.
• The final model was based on 7 selected radiomic features after feature selection.

Limitations

• Row count for the underlying data is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data may reflect geographic bias inherent to the two hospitals in Xuzhou, China.

Provenance

Source

Zhiling Wan via figshare

Collection Method

Retrospective collection of patient data and CT images from two hospitals.

Time Range

January 2022 to December 2024

Freshness

Last updated 2026-04-21 04:20:14; freshness should be verified.

Geography

Xuzhou, China (Xuzhou Central Hospital and Xuzhou First People's Hospital)