Prognostication of Patients with Spinal Bone Metastases (SBM): External Validation Study Comparing the Utility of Two Current Prediction Models

Purpose: A majority of developed prediction models for SBM are not used in clinical practice, where there is lack of external validation studies describing their performance on independent patient data. Methods: Primary aim was to externally validate two prediction models and to demonstrate whether these can be generalized for patients treated in different centers. Secondary aim was to identify additional prognostic factors predicting survival in patients with SBM. Results: Our results show modest predictive capacity for patients with symptomatic SBM in daily clinical practice by use of the existing two prediction models Van der Linden and Bollen. A slightly better performance in discrimination and calibration is found for the Bollen model with a C-statistic of 0.67 (95% CI: 0.63 –0.71) based on the validation dataset (95% CI: 0.65 –0.73) in contrast to Van der Linden with a C-statistic of 0.65 (95% CI: 0.60–0.71). Impact of brain or visceral metastases was significantly associated with survival, with a Hazard Ratio (HR) of 3.8 and 1.34 respectively. For breast cancer patients with SBM, hormone receptor status was of importance for prognostication (C-statistic of 0.67). Conclusion: With this first external validation study, we found modest predictive capacity for the prediction models by van der Linden and Bollen, with a slightly better performance for the Bollen model. Predictive impact of overall visceral and brainmetastases should not be underestimated. Breast tumor subtypes based on immunohistochemistry markers, seem to be of importance for the prognostication of breast cancer patients with SBM.