Performance of DeepSeek V3.2 and ChatGPT 5.1 in Musculoskeletal Triage and Differential Diagnosis of Outpatients With Low Back Pain: Multidimensional Comparative Study - Report - MDSpire

Performance of DeepSeek V3.2 and ChatGPT 5.1 in Musculoskeletal Triage and Differential Diagnosis of Outpatients With Low Back Pain: Multidimensional Comparative Study

  • By

  • Ziqian Ma

  • Ruiyuan Chen

  • Aobo Wang

  • Yu Xi

  • Minghui Liang

  • Shuo Yuan

  • Ning Fan

  • Jianwei Zang

  • Tianyi Wang

  • Lei Zang

  • July 3, 2026

  • 0 min

Share

Clinical Report: Evaluation of DeepSeek V3.2 and ChatGPT 5.1 in Triage of LBP

Overview

This study evaluates the diagnostic capabilities of two AI chatbots, DeepSeek V3.2 and ChatGPT 5.1, in the triage and differential diagnosis of outpatients with low back pain (LBP).

Background

Musculoskeletal disorders (MSDs) are prevalent and contribute significantly to healthcare burdens, with a notable increase in incidence over the past two decades. Effective triage and diagnosis of conditions like low back pain are essential for optimizing patient care and resource allocation. The integration of artificial intelligence, particularly large language models, is being explored for enhancing diagnostic accuracy in outpatient settings.

Data Highlights

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

Key Findings

  • DeepSeek V3.2 and ChatGPT 5.1 were assessed for their ability to classify MSDs based on patient complaints.
  • The study utilized standardized questionnaires derived from real outpatient records for evaluation.
  • Both AI models were evaluated for their performance in the clinical diagnosis and triage of low back pain.
  • The complexity of MSDs necessitates advanced diagnostic tools.
  • LLMs like DeepSeek and ChatGPT are being investigated for their roles in the medical field.

Clinical Implications

AI chatbots may support outpatient physicians in the triage and diagnosis of low back pain.

Conclusion

The study evaluates AI chatbots in the triage and diagnostic processes for low back pain, addressing challenges posed by musculoskeletal disorders.

Related Resources & Content

  1. Frontiers in Medicine, 2026 -- Preliminary evaluation of DeepSeek-R1 and GPT-5.3 in selected PET/CT clinical scenarios: patient preparation, report interpretation, and diagnostic reasoning
  2. Frontiers in Medicine, 2026 -- Utility of large language models as information tools for nursing care in gout: a comparative study of DeepSeek and ChatGPT
  3. Frontiers in Medicine, 2026 -- Performance stability despite iteration: evaluating DeepSeek and ChatGPT on Chinese medical licensing examinations
  4. Frontiers in Digital Health, 2026 -- Performance of deepseek-R1 and ChatGPT-5.4 thinking in the medical laboratory professional title examination: accuracy, stability, and comparison with interns
  5. Low Back Pain: A Review | Pain Medicine | JAMA | JAMA Network, 2026
  6. Low Back Pain: A Review | Pain Medicine | JAMA | JAMA Network
  7. Spinal Manipulation and Clinician-Supported Self-Management for Preventing Chronic Low Back Pain Impact: The PACBACK Randomized Clinical Trial | Trials | JAMA Internal Medicine | JAMA Network

Original Source(s)

Related Content