Study design: Retrospective observational study.
Objective: To evaluate the accuracy of eight scoring systems, including the Tomita, modified Tokuhashi, modified Bauer, Rades, Oswestry Spinal Risk index (OSRI), Lei, New England Spinal Metastasis Score, and Skeletal Oncology Research Group (SORG) nomogram, for predicting long-term survival of patients with spinal metastasis.
Summary of background data: Predicting the prognosis of spinal metastasis is vital for surgical decisions, yet the effectiveness of existing scoring systems in identifying long-term survival remains unclear.
Methods: 456 cases were finally included. Prognostic scores were compared with survival outcomes. Receiver operating characteristic (ROC) curves were analyzed for the entire cohort and across three distinct time periods to evaluate the area under the curve (AUC) for 1-year and 2-year survival, alongside Harrell's C-statistic.
Results: The mean patient age was 58.9 years, and the median survival time was 8.6 months. For the entire cohort, the SORG nomogram, OSRI, and modified Tokuhashi scores yielded Harrell's C-index values of 0.64, 0.63, and 0.62, respectively. For 1-year survival prediction, the SORG nomogram, OSRI, and modified Tokuhashi score demonstrated moderate discriminative power, with AUC values of 0.72, 0.71, and 0.70, respectively. Similarly, for 2-year survival prediction, the modified Tokuhashi score, SORG nomogram, and OSRI also revealed moderate discriminative power, with AUC values of 0.73, 0.72, and 0.70, respectively. For patients who underwent surgery in the most recent period, OSRI demonstrated the highest predictive accuracy for 1-year survival, with a Harrell's C-index of 0.63 and an AUC of 0.68, and 2-year survival, with a Harrell's C-index of 0.63 and an AUC of 0.64.
Conclusion: Most scoring systems exhibited low discriminative power, with only the SORG nomogram, OSRI, and modified Tokuhashi scores demonstrating moderate power for predicting long-term survival. In the most recent period, the OSRI demonstrated the highest predictive accuracy for both 1-year and 2-year survival.
Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.