A Radiomics Model Utilizing CT Imaging to Forecast Pain Relief Following Radiotherapy in Bone Metastasis Patients: Findings from a Dual-Center Investigation - Summary - MDSpire
Advertisement
A Radiomics Model Utilizing CT Imaging to Forecast Pain Relief Following Radiotherapy in Bone Metastasis Patients: Findings from a Dual-Center Investigation
To develop and validate a CT-based radiomics model for predicting pain relief after palliative radiotherapy in patients with bone metastases.
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.
