Optimizing predictive model performance in adult spinal deformity surgery: a comparative head-to-head analysis of learning models for perioperative complications.

Journal: Neurosurgical focus
Published Date: Jun 1, 2025

Abstract

OBJECTIVE: The aim of this study was to develop and compare 4 predictive algorithms, including logistic regression (LR), random forest (RF), gradient boosting machine (GBM), and neural network (NN), for perioperative outcomes in adult spinal deformity (ASD) surgery. By evaluating these models, the authors sought to explore how linear and nonlinear interactions unique to each outcome influence predictive accuracy, emphasizing the need for outcome-specific model selection.

Authors

  • Shane Shahrestani
    Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, California, USA; Department of Medical Engineering, California Institute of Technology, Pasadena, California, USA.
  • Catherine Garcia
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Andrew M Miller
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Robin Babadjouni
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Andre E Boyke
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Miguel Quintero-Consuegra
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Rohin Singh
    Department of Neurosurgery, University of Rochester Medical Center, Rochester, NY, USA.
  • Alexander Tuchman
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.
  • Corey T Walker
    1Department of Neurosurgery, Cedars-Sinai Medical Center, Los Angeles, California; and.

Keywords

External Resources

Popular Topics
Recent Journals