Gulta, DawitChen, StephenKlein, GeoffRoss, Tayler DRezkalla, MatthewPalhares, Daniel MBurgess, LauraDetsky, JaySahgal, ArjunWhyne, Cari MHardisty, Michael2026-01-152026-01-152025-08-22D. Gulta et al., "Vertebral compression Fracture Risk in Spinal Metastases Patients Following Stereotactic Body Radiotherapy Using Quantitative Imaging Data and Machine Learning," 2025 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Tainan, Taiwan, 2025, pp. 1-8, doi: 10.1109/CIBCB66090.2025.11177109979-8-3315-0266-92994-9408https://doi.org/10.1109/cibcb66090.2025.11177109https://hdl.handle.net/10315/43490This author accepted manuscript for a conference paper is published in its final form as D. Gulta et al., "Vertebral compression Fracture Risk in Spinal Metastases Patients Following Stereotactic Body Radiotherapy Using Quantitative Imaging Data and Machine Learning," 2025 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Tainan, Taiwan, 2025, pp. 1-8, doi: 10.1109/CIBCB66090.2025.11177109.Vertebral compression fractures (VCFs) occur in approximately 14% of patients with spinal metastases following treatment with Stereotactic Body Radiotherapy (SBRT). The Spinal Instability Neoplastic Score (SINS) is the current clinical standard for assessing potential mechanical instability in these patients; however, it has several limitations such as it is manually assessed, has an inconsistent relationship with fracture risk and is only semi-quantitative. This study used quantitative CT imaging biomarkers derived from SBRT treatment planning imaging and machine learning models (Logistic Regression, Random Forest, XGBoost, SVM, Gradient Boosting, AdaBoost, Neural Network) to predict vertebral compression fractures (VCF) following SBRT in spinal metastases patients (in 300 thoraco-lumbar vertebrae from 179 patients). The Random Forest model achieved the best performance (sensitivity: 0.64, specificity: 0.76, F1-score: 0.47), showing a 36% improvement in balanced accuracy over SINS. Feature importance analysis identified the quantitative imaging biomarkers, spinal alignment and bone lesion composition (lytic or blastic disease) as the strongest predictors. ML models demonstrated meaningful improvements over existing SINS assessment.enBiomedical and clinical sciencesClinical sciencesBiomedical imagingBioengineeringPhysical injury - accidents and adverse effectsMachine learning and artificial intelligenceRadiation oncologyCancerDiscovery and preclinical testing of markers and technologiesMachine learningVertebral compresion fracturesSpinal instability neoplastic score (SINS)Stereotactic body radiotherapy (SBRT)Medical imagingFracture risk predictionConference Paper