Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 7:96:512-520.
doi: 10.2340/17453674.2025.44251.

External validation of a prediction model for disability and pain after lumbar disc herniation surgery: a prospective international registry-based cohort study

Allan Abbott  1 , Casper Friis Pedersen  2 , Henrik Hedevik  3 , Catharina Parai  4 , Martin A Gorosito  5 , Mikkel Andersen  6 , Tor Ingebrigtsen  7 , Tore K Solberg  7 , Margreth Grotle  8 , Bjørnar Berg  9
Affiliations

External validation of a prediction model for disability and pain after lumbar disc herniation surgery: a prospective international registry-based cohort study

Allan Abbott et al. Acta Orthop. .

Abstract

Background and purpose: We aimed to externally validate machine learning models developed in Norway by evaluating their predictive outcome of disability and pain 12 months after lumbar disc herniation surgery in a Swedish and Danish cohort.

Methods: Data was extracted for patients undergoing microdiscectomy or open discectomy for lumbar disc herniation in the NORspine, SweSpine and DaneSpine national registries. Outcome of interest was changes in Oswestry disability index (ODI) (≥ 22 points), Numeric Rating Scale (NRS) for back pain (≥ 2 points), and NRS for leg pain (≥ 4 points). Model performance was evaluated by discrimination (C-statistic), calibration, overall fit, and net benefit.

Results: For the ODI model, the NORspine cohort included 22,529 patients, the SweSpine cohort included 10,129 patients, and DaneSpine 5,670 patients. The ODI model's C-statistic varied between 0.76 and 0.81 and calibration slope point estimates varied between 0.84 and 0.99. The C-statistic for NRS back pain varied between 0.70 and 0.76, and calibration slopes varied between 0.79 and 1.03. The C-statistic for NRS leg pain varied between 0.71 and 0.74, and calibration slopes varied between 0.90 and 1.02. There was acceptable overall fit and calibration metrics with minor-modest but explainable heterogeneity observed in the calibration plots. Decision curve analyses displayed clear potential net benefit in treatment in accordance with the prediction models compared with treating all patients or none.

Conclusion: Predictive performance of machine learning models for treatment success/non-success in disability and pain at 12 months post-surgery for lumbar disc herniation showed acceptable discrimination ability, calibration, overall fit, and net benefit reproducible in similar international contexts. Future clinical impact studies are required.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Flow diagram of surgical cases included in the analyses.
Figure 2
Figure 2
Calibration plots for prediction models in the development and validation cohorts. The dashed diagonal line represents perfect calibration. The solid line is a LOESS-smoothed calibration curve. Points below the dashed line indicate that the model’s successful outcome event estimates are too high compared with observed events; points above the dashed line indicate that the model’s successful outcome estimates are too low compared with observed events.
Figure 3
Figure 3
Decision curve analyses for the Oswestry Disability Index, NRS back pain, and NRS leg pain models. Net benefit (y-axis) for binary outcome prediction models across a range of threshold probabilities along the x-axis that define when surgery is warranted. Each line represents 1 prediction result, with red line = treat all, blue line = treat none, and green cline = treat per prediction model.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Wynne-Jones G, Cowen J, Jordan J L, Uthman O, Main C J, Glozier N, et al. Absence from work and return to work in people with back paIn: a systematic review and meta-analysis. Occup Environ Med 2014; 71(6): 448-56. doi: 10.1136/oemed-2013-101571. - DOI - PMC - PubMed
    1. Olafsson G, Jonsson E, Fritzell P, Hägg O, Borgström F. Cost of low back paIn: results from a national register study in Sweden. Eur Spine J 2018; 27(11): 2875-81. doi: 10.1007/s00586-018-5742-6. - DOI - PubMed
    1. Foster N E, Anema J R, Cherkin D, Chou R, Cohen S P, Gross D P, et al. ; Lancet Low Back Pain Series Working Group . Prevention and treatment of low back paIn: evidence, challenges, and promising directions. Lancet 2018; 391(10137): 2368-83. doi: 10.1016/S0140-6736(18)30489-6. - DOI - PubMed
    1. Gibson J N, Waddell G. Surgical interventions for lumbar disc prolapse: updated Cochrane Review. Spine (Phila Pa 1976) 2007; 32(16): 1735-47. doi: 10.1097/BRS.0b013e3180bc2431. - DOI - PubMed
    1. Lagerbäck T, Fritzell P, Hägg O, Nordvall D, Lønne G, Solberg T K, et al. Effectiveness of surgery for sciatica with disc herniation is not substantially affected by differences in surgical incidences among three countries: results from the Danish, Swedish and Norwegian spine registries. Eur Spine J 2019; 28(11): 2562-71. doi: 10.1007/s00586-018-5768-9. - DOI - PubMed

Publication types

LinkOut - more resources