Performance of DeepSeek-R1 and ChatGPT-5 in the Generation of North American Spine Society Clinical Guidelines for Adult Vertebral Compression Fractures: Comparative Study - Report - MDSpire

Performance of DeepSeek-R1 and ChatGPT-5 in the Generation of North American Spine Society Clinical Guidelines for Adult Vertebral Compression Fractures: Comparative Study

  • By

  • Ruiyuan Chen

  • Yue Pan

  • Minghui Liang

  • Aobo Wang

  • Ziqian Ma

  • Yu Xi

  • Ning Fan

  • Shuo Yuan

  • Peng Du

  • Tianyi Wang

  • Lei Zang

  • July 10, 2026

  • 0 min

Share

Clinical Report: Evaluation of DeepSeek-R1 and ChatGPT-5 for VCF Guidelines

Background

Vertebral compression fractures (VCFs) are a significant public health concern, particularly among the aging population, with approximately 1.5 million cases annually in the U.S. and substantial healthcare costs. Effective management of VCFs requires adherence to clinical guidelines.

Data Highlights

No numerical or trial data was provided in the source material.

Key Findings

  • VCFs are associated with pain, spinal deformity, and increased mortality risk.
  • Large language models have shown potential in generating clinical recommendations across various medical domains.
  • Performance of LLMs varies significantly when addressing spinal surgery topics.
  • No prior studies have specifically evaluated LLM performance on VCFs.
  • Timeliness of clinical guidelines is crucial for the accuracy of LLM-generated recommendations.

Clinical Implications

The variability in accuracy of LLMs necessitates careful evaluation of the recommendations provided by these models.

Conclusion

Further research is needed to enhance the accuracy and reliability of LLMs in clinical settings.

Related Resources & Content

  1. North American Spine Society, JMIR, 2024 -- Evaluation of DeepSeek-R1 and ChatGPT-5 in Formulating Clinical Guidelines for Adult Vertebral Compression Fractures
  2. Frontiers in Surgery — Comparative analysis of two modified TLICS systems in guiding surgical decision-making for thoracolumbar fractures
  3. Comparative Outcomes of Anterior Cervical Discectomy and Fusion with Plate Versus Posterior Screw Fixation in Octogenarians Following Traumatic Subaxial Fractures: A Two-Year Follow-Up on Complications and Results
  4. Does achieving vertebral body height restoration following fractures and minimally-invasive dorsal stabilization with polyaxial pedicle screws represent a mere illusion?
  5. NASS Evidence-Based Clinical Guidelines for VCFs
  6. ACR Appropriateness Criteria for Management of VCFs
  7. Radiological diagnosis of prevalent osteoporotic vertebral fracture on radiographs: an interim consensus from a group of experts of the ESSR osteoporosis and metabolism subcommittee | Skeletal Radiology | Springer Nature Link
  8. https://www.nogg.org.uk/sites/nogg/download/NOGG-Guideline-2024.pdf?v4%253D=
  9. Recommendation: Osteoporosis to Prevent Fractures: Screening | United States Preventive Services Taskforce
  10. https://josr-online.biomedcentral.com/counter/pdf/10.1186/s13018-025-05621-6.pdf
  11. Vertebroplasty, Kyphoplasty, Sacroplasty – Rereview: Final Report
  12. Risk of adjacent level fracture after percutaneous vertebroplasty and kyphoplasty vs natural history for the management of osteoporotic vertebral compression fractures: a network meta-analysis of randomized controlled trials - PubMed

Original Source(s)

Related Content