July 2025

ORTHOPAEDICS

PREDICTING FAILED BACK SURGERY SYNDROME AFTER LUMBAR SPINE SURGERY USING MACHINE LEARNING TECHNIQUES

In a recent study published in Spine, Northwestern Medicine Orthopaedics researchers— including  Alpesh A. Patel, MD, Srikanth N. Divi, MD, and Wellington Hsu, MD— built a predictive model for failed back surgery syndrome (FBSS) using machine learning techniques. 
​
The goal of this retrospective cohort study was to identify risk factors associated with FBSS within one year of lumbar spine surgery.

The study analyzed a substantial dataset comprising 10,128 lumbar decompression surgeries and 2,890 lumbar fusion surgeries performed between 2002 and 2022. The team used multiple machine-learning algorithms, with the Random Forest model emerging as the most effective, achieving an area under the receiver operating characteristic curve of 0.715 for lumbar decompression and 0.701 for lumbar fusion. 

Top Predictors of FBBS
For lumbar decompression, the team found that the top three predictors of FBSS were:
  • Absence of microdiscectomy
  • Lack of preoperative immunosuppressant usage
  • Preoperative benzodiazepine usage
For lumbar fusion, the most important predictors included:
  • Prior FBSS diagnosis
  • Lack of preoperative immunosuppressant usage
  • OR duration
The findings indicate that this Random Forest model has the potential to enhance preoperative risk assessment in spine surgery, aiding surgeons in identifying patients who may face complications post-surgery.
Read More on This Research
Alpesh A. Patel, MD, professor of Orthopaedic Surgery
Srikanth N. Divi, MD, assistant professor of Orthopaedic Surgery and Neurological Surgery
Wellington K. Hsu, MD, Professor of Orthopaedic Surgery and Neurological Surgery

Refer a Patient

Northwestern Medicine welcomes the opportunity to collaborate with you in caring for your patients. ​

You May Also Like