Objective:

To develop and validate a CT-based radiomics model for predicting pain relief after palliative radiotherapy in patients with bone metastases.

Approach:

Key Findings:

• 134 patients included: 53 in the pain relief group and 81 in the non-relief group.
• K-nearest neighbors (KNN) model showed the best performance with AUCs of 0.823, 0.812, and 0.818 across training, internal validation, and external test sets, respectively.
• Seven radiomic features were selected for modeling after feature screening.

Interpretation:

The KNN model effectively predicts pain relief outcomes post-radiotherapy, indicating its potential for clinical application in identifying patients likely to benefit from treatment.

Limitations:

• Retrospective design may introduce bias.
• Sample size, while adequate, may limit generalizability.
• External validation was performed on a relatively small cohort.

Conclusion:

The CT radiomics-based KNN model can serve as a valuable tool for predicting pain relief in bone metastasis patients undergoing palliative radiotherapy.

Source

Based on findings from:

A Radiomics Model Utilizing CT Imaging to Forecast Pain Relief Following Radiotherapy in Bone Metastasis Patients: Findings from a Dual-Center Investigation

Zhiling Wan, Kangning Liu, Heyao Xu, Fei Zhao, Xiaohan Qin, Zexian Wang, Weijia Li, Yuhang Wu, Bowen Hu, Chong Zhou, Xiaojin Wu. Frontiers In Oncology, 2026.

https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2026.1813913/full

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.