Clinical guidelines are a useful adjunct to select patients with spinal metastases for prophylactic intervention. The objective of this study is to determine the ability of biomechanically based models to accurately predict metastatic burst fracture risk. Ninety-two vertebrae with osteolytic spinal metastases were examined retrospectively. Vertebrae were categorized as burst fractured, wedge fractured, or intact and analyzed using three predictive models: vertebral bulge (maximum radial displacement under load), vertebral axial displacement (maximum axial displacement under load), and a volumetric estimate of tumor size. The load-bearing capacity parameter (tumor volume, bone mineral density, disc quality, pedicle involvement) was determined from computed tomography while the load-bearing requirement parameter (pressure load, loading rate) was determined using computed tomography and patient records (retrieved for 37 patients [52%]). Fracture prediction was optimized using the vertebral bulge model considering only load-bearing capacity with a specificity, sensitivity, and confidence interval of 1 to yield a clear threshold for burst fracture risk. Fracture prediction in the other two models, vertebral axial displacement considering only load-bearing capacity and tumor size, also was strong with receiver-operator curve values of 0.992 and 0.988, respectively. The predictive power of these models can provide useful clinical information for prophylactic decision-making.