Performance of ChatGPT on NASS Clinical Guidelines for the Diagnosis and Treatment of Low Back Pain

Author:

Shrestha Nancy1,Shen Zekun2,Zaidat Bashar3,Duey Akiro H.3,Tang Justin E.3,Ahmed Wasil3,Hoang Timothy3,Restrepo Mejia Mateo3,Rajjoub Rami3,Markowitz Jonathan S.4,Kim Jun S.4,Cho Samuel K.4

Affiliation:

1. Chicago Medical School at Rosalind Franklin University, North Chicago, IL

2. Independent Scholar, New York, NY

3. Icahn School of Medicine at Mount Sinai, New York, NY

4. Department of Orthopedics, Mount Sinai Health System, New York, NY

Abstract

Study Design. Comparative analysis. Objective. To evaluate ChatGPT’s ability to predict appropriate clinical recommendations based on the most recent clinical guidelines for the diagnosis and treatment of low back pain. Background. Low back pain is a very common and often debilitating condition that affects many people globally. Chat Generative Pre-trained Transformer (ChatGPT) is an artificial intelligence model that may be able to generate recommendations for low back pain. Methods. Using the North American Spine Society Evidence-Based Clinical Guidelines as the gold standard, 82 clinical questions relating to low back pain were entered into ChatGPT (GPT-3.5) independently. For each question, we recorded ChatGPT’s answer, then used a point-answer system— the point being the guideline recommendation and the answer being ChatGPT’s response— and asked ChatGPT if the point was mentioned in the answer to assess for accuracy. This response accuracy was repeated with one caveat— a prior prompt is given in ChatGPT to answer as an experienced orthopedic surgeon— for each question by guideline category. A two-sample proportion z-test was used to assess any differences between the pre- and post-prompt scenarios with alpha=0.05. Results. ChatGPT’s response was accurate 65% (72% post-prompt, P=0.41) for guidelines with clinical recommendations, 46% (58% post-prompt, P=0.11) for guidelines with insufficient or conflicting data, and 49% (16% post-prompt, P=0.003*) for guidelines with no adequate study to address the clinical question. For guidelines with insufficient or conflicting data, 44% (25% post-prompt, P=0.01*) of ChatGPT responses wrongly suggested that sufficient evidence existed. Conclusion. ChatGPT was able to produce a sufficient clinical guideline recommendation for low back pain, with overall improvements if initially prompted. However, it tended to wrongly suggest evidence and often failed to mention, especially post-prompt, when there is not enough evidence to adequately give an accurate recommendation.

Publisher

Ovid Technologies (Wolters Kluwer Health)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3