In Journal of neurosurgery. Spine
Accurate prediction of patient survival is an essential component of the preoperative evaluation of patients with spinal metastases. Over the past quarter of a century, a number of predictors have been developed, although none have been accurate enough to be instituted as a staple of clinical practice. However, recently more comprehensive survival calculators have been published that make use of larger data sets and machine learning to predict postoperative survival among patients with spine metastases. Given the glut of calculators that have been published, the authors sought to perform a narrative review of the current literature, highlighting existing calculators along with the strengths and weaknesses of each. In doing so, they identify two "generations" of scoring systems-a first generation based on a priori factor weighting and a second generation comprising predictive tools that are developed using advanced statistical modeling and are focused on clinical deployment. In spite of recent advances, the authors found that most predictors have only a moderate ability to explain variation in patient survival. Second-generation models have a greater prognostic accuracy relative to first-generation scoring systems, but most still require external validation. Given this, it seems that there are two outstanding goals for these survival predictors, foremost being external validation of current calculators in multicenter prospective cohorts, as the majority have been developed from, and internally validated within, the same single-institution data sets. Lastly, current predictors should be modified to incorporate advances in targeted systemic therapy and radiotherapy, which have been heretofore largely ignored.
Pennington Zach, Ehresman Jeff, Cottrill Ethan, Lubelski Daniel, Lehner Kurt, Feghali James, Ahmed A Karim, Schilling Andrew, Sciubba Daniel M
AUC = area under the curve, ECOG = Eastern Cooperative Oncology Group, ESCC = epidural spinal cord compression, GSTSG = Global Spine Tumour Study Group, KPS = Karnofsky Performance Status, NESMS = New England Spinal Metastasis Score, NSQIP = National Surgical Quality Improvement Program, PPV = positive predictive value, QOL = quality of life, SORG = Skeletal Oncology Research Group, minimally invasive surgery, oncology, patient selection, predictive analytics, quality of life, spinal metastases, survival prediction