Related Experiment Video
Updated: Jul 12, 2026
14:56
An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP
Published on: January 27, 2010
21.4K
Machine Learning Models for Predicting Disability and Pain Following Lumbar Disc Herniation Surgery
Bjørnar Berg1,2, Martin A Gorosito1,3, Olaf Fjeld1,4
1Centre for Intelligent Musculoskeletal Health, Faculty of Health Sciences, Oslo Metropolitan University, Oslo, Norway.
JAMA Network Open
|February 7, 2024
Summary
Machine learning models predict outcomes for lumbar disc herniation surgery, identifying patients unlikely to benefit. These models aid surgical decision-making by providing individual prognoses for pain and disability.
Area of Science:
- Neurosurgery
- Orthopedic Surgery
- Medical Informatics
Background:
- Lumbar disc herniation surgery offers pain and disability relief for many.
- A significant portion of patients experience limited benefits from surgery.
- Accurate prediction models are crucial for optimizing surgical outcomes.
Purpose of the Study:
- To develop and validate machine learning models for predicting disability and pain 12 months post-lumbar disc herniation surgery.
- To assess the models' performance using internal-external cross-validation across different regions.
Main Methods:
- Prospective, multicenter, registry-based prognostic study of 22,707 surgical cases (21,161 patients).
- Machine learning models trained to predict treatment success based on Oswestry Disability Index (ODI) and Numeric Rating Scale (NRS) pain scores.
- Internal-external cross-validation performed across 5 geographic regions to validate model performance (C statistic, calibration slope, and intercept).
Main Results:
- Machine learning models demonstrated consistent discrimination and calibration across all validation regions.
- The Oswestry Disability Index (ODI) model achieved a C statistic ranging from 0.81 to 0.84 (pooled estimate 0.82).
- Models for back and leg pain also showed good predictive performance, with C statistics of 0.77 and 0.75, respectively.
Conclusions:
- Developed machine learning models accurately predict disability and pain outcomes after lumbar disc herniation surgery.
- These validated models can inform patient-clinician discussions regarding surgical decision-making.
- Prognostic models enhance personalized treatment strategies for lumbar disc herniation.
Related Concept Videos
01:29Herniated Intervertebral Disc l: Introduction
Intervertebral disc herniation refers to the displacement of the nucleus pulposus (the gel-like inner core of the disc) through a tear or weakened area in the annulus fibrosus (the outer fibrous ring). The displaced disc material extends beyond the normal boundaries of the disc space and may compress or irritate nearby spinal nerve roots or, less commonly, the spinal cord.Etiology and Risk FactorsHerniation commonly results from degeneration, in which aging reduces disc hydration and...
01:23Degenerative Disc Disease ll: Pathophysiology
The symptoms of degenerative disc disease arise from a combination of mechanical compression, vascular compromise, and biochemical inflammation, which together disrupt nerve function and produce pain.Mechanical CompressionDisc degeneration reduces height and elasticity, predisposing to herniation of the nucleus pulposus, a major cause of radicular pain. Herniations may be protrusion (bulging with intact annulus), extrusion (nucleus extends beyond disc but remains connected), or sequestration...