The Accuracy of ChatGPT in Classifying Lumbar Spondylolisthesis and Compression Fractures
Journal of the American Osteopathic Academy of Orthopedics · 29.05.2026 · X (1)
DOI: 10.70709/qbghijluqge3j8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Osteopathic Academy of Orthopedics, online erschienen am 29.05.2026. Verfasst von Justin Chung und 7 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben.
Abstract (Originalsprache)
Background
Chat Generative Pre-Trained Transformer (ChatGPT), released in the fall of 2022, made large language models accessible worldwide. Since then, ChatGPT’s capabilities have expanded to areas including imaging and analysis across multiple models, such as the recent advanced reasoning o-models. The aim of this study was to determine whether ChatGPT and its three other models can identify and classify two distinct lumbar spinal pathologies: L5-S1 spondylolisthesis and vertebral compression fractures (VCFs).
Methods
This study utilized 54 images from the VinDr-SpineXR database: 30 labeled as spondylolisthesis and 24 labeled as vertebral collapse. These images were uploaded into ChatGPT 5.2 Thinking, 4o, o4-mini, and o4-mini-high, all in temporary mode. Three standardized questions were asked: 1) Can you identify the pathology in this image? 2) Can you identify where the spondylolisthesis/compression fracture is in this image? 3) Can you grade the level of L5-S1 spondylolisthesis/percentage of compression in the image?
Results
Across both pathologies, ChatGPT 5.2 Thinking displayed the highest accuracy in initial pathology identification at a rate of 86.7% (p
Zitieren
APA
Chung, J., Lin, R., Dunn, E., Kim, G., Choi, C., Mo, K., Fang, W., & Lee, D. (2026). The Accuracy of ChatGPT in Classifying Lumbar Spondylolisthesis and Compression Fractures. Journal of the American Osteopathic Academy of Orthopedics, X(1). https://doi.org/10.70709/qbghijluqge3j8
Vancouver
Chung J, Lin R, Dunn E, Kim G, Choi C, Mo K, et al. The Accuracy of ChatGPT in Classifying Lumbar Spondylolisthesis and Compression Fractures. Journal of the American Osteopathic Academy of Orthopedics. 2026;X(1). doi:10.70709/qbghijluqge3j8
BibTeX
@article{Chung2026,
author = {Chung, Justin and Lin, Rowen and Dunn, Evan and Kim, Grace and Choi, Caleb and Mo, Kevin and Fang, William and Lee, Daniel},
title = {The Accuracy of ChatGPT in Classifying Lumbar Spondylolisthesis and Compression Fractures},
journal = {Journal of the American Osteopathic Academy of Orthopedics},
year = {2026},
volume = {X},
number = {1},
doi = {10.70709/qbghijluqge3j8}
}
EUVIMED