SRS33 - Human <i>versus</i> machine in survival prediction for metastatic spinal cord compression: a retrospective cohort study

Abstract Background Accurate survival prediction in metastatic spinal cord compression (MSCC) is critical for guiding treatment decisions, yet remains challenging, particularly for intermediate survival durations. We compared the accuracy of oncologist judgment, surgeon-calculated Tokuhashi scores, and ChatGPT-assisted predictions in estimating survival outcomes in MSCC patients. Methods This retrospective study included 99 consecutive patients referred to a tertiary spinal oncology center with radiologically confirmed MSCC. Anonymized clinical data were used to calculate surgeon Tokuhashi scores, document oncologist-estimated life expectancy, and generate ChatGPT-assisted survival predictions based on both literature review and Tokuhashi calculation. Predictions were compared against actual survival outcomes (&amp;lt;6 months, 6–12 months, &amp;gt;12 months). Machine learning analyses identified key predictors of survival. Results Overall prediction accuracies were 54% for ChatGPT Tokuhashi-based predictions, 50% for surgeon Tokuhashi scores, 48% for oncologist judgment, and 37% for ChatGPT literature-based estimates. Recall for short survival (&amp;lt;6 months) was highest with surgeon (71%) and ChatGPT Tokuhashi (69%) methods, whereas intermediate survival (6–12 months) remained difficult to predict across all modalities. Functional status (Karnofsky score) and patient age emerged as the strongest survival predictors across logistic regression, random forest, decision tree, and XGBoost models, surpassing primary tumor type and metastasis burden. Conclusions Structured prognostic tools and AI-assisted scoring can complement clinical judgment in predicting short-term survival in MSCC. However, intermediate-term survival prediction remains a critical unmet need. Future prognostic strategies should prioritize dynamic functional metrics over static tumor classifications to improve personalized decision-making.