Machine learning accurately predicted 1-year prognoses for lumbar disc herniation surgery
Click Here to Manage Email Alerts
Key takeaways:
- A machine learning model accurately predicted disability and pain up to 1 year after lumbar disc herniation surgery.
- The algorithm may inform about individual prognoses and aid in surgical decision-making.
A machine learning model accurately predicted disability and pain up to 1 year after lumbar disc herniation surgery and may aid decision-making for patients and surgeons, according to published results.
Researchers used the Norwegian Registry for Spine Surgery to perform a prospective, multicenter prognostic study of 21,161 patients (mean age of 47 years) who underwent 22,707 lumbar disc herniation surgeries from Jan. 1, 2007, to May 31, 2021.
According to the study, researchers used a validated machine learning model to predict treatment success in disability and pain for 1 year after surgery. Treatment success was defined as improvements in the Oswestry Disability Index (ODI) of 22 points or more, numeric rating scale (NRS) for back pain of two points or more and NRS for leg pain of four points or more.
Overall, 33% of cases were deemed unsuccessful according to ODI; 27% were deemed unsuccessful according to NRS for back pain; and 31% were deemed unsuccessful according to NRS for leg pain. Researchers noted the machine learning model showed consistent discrimination and calibration after internal-external cross-validation.
“The findings of this study suggest that algorithms can inform about individual prognosis and aid in surgical decision-making to ultimately reduce ineffective and costly spine care,” the researchers wrote in the study.
Collapse
Read more about
Click Here to Manage Email Alerts