Performance of ChatGPT versus spine surgeons as an emergency department spine call consultant.

Abstract

Background

Large language models (LLMs) like ChatGPT are increasingly being recognized as credible tools for use across diverse healthcare settings. While artificial intelligence (AI) use has previously been evaluated in emergency medicine, its use in subspecialty care - particularly spine surgery - remains underexplored. This study evaluates the clinical accuracy, management appropriateness, completeness, helpfulness, and overall quality of ChatGPT responses compared to those of board-certified, spine surgeons in response to common emergency department (ED) consultations.

Methods

A 7-part questionnaire was developed based on common ED spine consultations (eg, Cauda Equina Syndrome, compression fracture in elderly patients, purulent drainage from surgical wound, acute lumbar disc herniation, incomplete spinal cord injury, epidural abscess, and metastatic spine disease). Each case included 3-4 questions pertaining to examination, diagnosis, management, and counseling. Responses from ChatGPT and 7 board-certified spine surgeons were restricted to 3-4 sentences per question. Three emergency medicine physicians rated each de-identified questionnaire response using a 5-point Likert scale. Statistical analysis was conducted using a 2-sample T-test with unequal variance. Inter-rater reliability was assessed using pairwise weighted Cohen's kappa coefficient (κ).

Results

When comparing AI responses versus spine surgeon responses to proposed ED consultations, AI responses were rated to be superior across all 5 metrics of clinical accuracy, management appropriateness, completeness, helpfulness, and overall quality (p<.05). Inter-rater reliability was assessed using the average pairwise weighted Cohen's kappa coefficient which showed substantial agreement (κ=0.76).

Conclusions

ChatGPT responses to emergency department spine consultations were rated as significantly higher compared to board-certified spine surgeons by emergency medicine providers. Though further improvement and validation is warranted, these findings suggest that ChatGPT can be a useful clinical adjunct for spine-related emergency department consultations.

Department

Description

Provenance

Subjects

Artificial Intelligence, Chatgpt, Consult, Emergency, Spine

Citation

Published Version (Please cite this version)

10.1016/j.xnsj.2025.100836

Publication Info

Taka, Taha M, Seena Sebt, Sarah Meng, Andrew Cabrera, David Shin, Vahe Yacoubian, Weyjuin Chao, Daniel Rossie, et al. (2026). Performance of ChatGPT versus spine surgeons as an emergency department spine call consultant. North American Spine Society journal, 25. p. 100836. 10.1016/j.xnsj.2025.100836 Retrieved from https://hdl.handle.net/10161/33965.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.

Scholars@Duke

Erickson

Melissa Maria Erickson

Associate Professor of Orthopaedic Surgery

I am a spine surgeon who provides surgical management of cervical, thoracic  and lumbar spine conditions, including cervical myelopathy, herniated discs, deformity, stenosis, tumor and trauma.  I provide both minimally invasive procedures as well as traditional surgical techniques.

Rocos

Brett Rocos

Assistant Professor of Orthopaedic Surgery

I joined the team at Duke University Health from London, UK, where I was a Consultant Adult and Paediatric Spine Surgeon at Barts Health NHS Trust and Honorary Consultant Senior Lecturer at Queen Mary University of London. I completed my surgical training in in the South West of the UK and at the University of Toronto, and am fellowship trained in adult spine surgery, paediatric spine surgery, orthopaedic trauma surgery, research and healthcare management.

I am driven to support patients at every stage of their care, from clinic assessment, through surgery to discharge. Making sure that every person, adult, child, family or friend understands what’s wrong, helping them to choose the right treatment for them, and what the recovery will be like is an important priority.

My research activity focusses on finding effective new treatments for spinal disorders and bringing them to patients. Focusing on spinal deformity, I have led investigations in the UK, Canada and the USA, and I sit on the Global AO Knowledge Forum for Deformity and the Research Grants Committee at the Scoliosis Research Society. I have lectured in North America and Europe about the treatment of spine disorders for the Scoliosis Research Society, Global Spine Congress, AO Spine and Eurospine, and I have worked hard to produce research that improves the care for spine patients wherever they live. Lastly, I review for several orthopaedic journals and I am Deputy Editor of the Bone and Joint 360, a leading publication with a global readership.

Than

Khoi Duc Than

Professor of Neurosurgery

I chose to pursue neurosurgery as a career because of my fascination with the human nervous system. In medical school, I developed a keen interest in the diseases that afflict the brain and spine and gravitated towards the only field where I could help treat these diseases with my own hands. I focus on disorders of the spine where my first goal is to help patients avoid surgery if at all possible. If surgery is needed, I treat patients using the most advanced minimally invasive techniques available in order to minimize pain, blood loss, and hospital stay, while maximizing recovery, neurologic function, and quality of life. In my free time, I enjoy spending time with my family and friends. I am an avid sports fan and love to eat. I try to stay physically fit by going to the gym and playing ice hockey.

Danisa

Olumide Ayodele Danisa

Instructor in the Department of Orthopaedic Surgery

I am an academic board-certified spine surgeon with more than 25 years of experience treating spine disease. I address a variety of spinal conditions, including upper cervical instability; cervical degenerative and traumatic disease; thoracic disease and deformity; lumbar degeneration and instability; spinal trauma (cervical, thoracic, and lumbosacral); metastatic spine disease; spinal infections; and complex spine conditions. In surgery, I use traditional open techniques, minimally invasive spine surgery, and endoscopic spine surgery.


Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.