Evaluating the Real-World Predictive Utility of Karnofsky and ECOG Performance Status for 90-Day Survival After Oncologic Surgery for Metastatic Spinal Tumors

BACKGROUND: Performance status is often cited as an independent predictor of survival after metastatic spine tumor surgery (MSTS), but its standalone predictive value for short-term outcomes remains unclear. We aimed to evaluate how well Karnofsky (KPS) and Eastern Cooperative Oncology Group performance status (ECOG-PS) predict 90-day survival, a common surgical candidacy threshold, in patients managed with MSTS. METHODS: We conducted a retrospective study of 175 adult patients who underwent MSTS at a single institution (2012-2025). All patients had documented preoperative KPS and ECOG-PS scores. Univariable logistic regression was used to assess associations with 90-day survival. Predictive performance was assessed by discrimination (AUC), diagnostic accuracy, calibration (Brier score), and clinical utility (decision curve analysis). RESULTS: < 0.001) were statistically associated with survival. However, discrimination was modest (AUC 0.65 for KPS, 0.68 for ECOG-PS), with the most balanced diagnostic accuracy achieved at KPS ≥ 70 (sensitivity 0.66, specificity 0.62) and ECOG-PS ≤ 2 (sensitivity 0.76, specificity 0.5). Calibration was fair (Brier scores 0.185 and 0.182, respectively). Decision curve analysis showed minimal net benefit across most threshold probabilities, with ECOG-PS performing slightly better at intermediate thresholds (30-60%), the zone of greatest clinical uncertainty. CONCLUSIONS: Despite being widely cited as an independent predictor of postoperative survival in patients with metastatic spine disease, performance status assessed via the KPS and ECOG-PS demonstrated only modest overall discriminatory ability, diagnostic accuracy, calibration, and clinical utility when used alone to predict 90-day survival after MSTS. While both scores retained meaningful value at the extremes (i.e., patients with very poor or very good performance status had more predictable outcomes), caution is warranted in intermediate cases, where performance status alone may be insufficient to guide treatment decisions. These findings highlight the critical difference between statistical association and the real-world clinical utility of a single metric to predict outcome in this patient population.