Exploring the Clinical Translation of Generative Models Like ChatGPT: Promise and Pitfalls in Radiology, From Patients to Population Health

被引：14

作者：

Doo, Florence X. ^{[1
,2
,15
]}

Cook, Tessa S. ^{[3
,4
,5
,6
]}

Siegel, Eliot L. ^{[7
,8
]}

Joshi, Anupam ^{[9
,10
]}

Parekh, Vishwa ^{[11
]}

Elahi, Ameena ^{[12
,13
]}

Yi, Paul H. ^{[14
]}

机构：

[1] Univ Maryland, Med Intelligent Imaging Ctr UM2ii, Innovat, Baltimore, MD USA

[2] ACR Commiss Econ, Comm Econ Acad Radiol, Baltimore, MD USA

[3] Emory Univ, Perelman Sch Med, Dept Radiol, Practice Informat, Atlanta, GA USA

[4] Penn Med, Dept Radiol, Imaging Informat, Philadelphia, PA USA

[5] Penn Med, Dept Radiol, 3D & Advanced Imaging, Philadelphia, PA USA

[6] ACR Commiss Patient and Family Ctr Care, RAHSR Affin Grp, Philadelphia, PA USA

[7] Univ Maryland, Res Informat Syst, Baltimore, MD USA

[8] US Dept Vet Affairs Maryland Healthcare Syst, USDepartment Vet Affairs Vet Integrated Serv Netwo, Radiol & Nucl Med Diagnost, Baltimore, MD USA

[9] Univ Maryland, Comp Sci & Elect Engn, Baltimore, MD USA

[10] Univ Maryland Baltimore Cty, Ctr Cybersecur, Baltimore, MD USA

[11] Univ Maryland, Med Intelligent Imaging UM2ii Ctr, Baltimore, MD USA

[12] Univ Penn, Philadelphia, PA USA

[13] Penn Med, Informat Serv, Philadelphia, PA USA

[14] RAD AID Int, Philadelphia, PA USA

[15] Stanford Univ, 500 Pasteur Dr, Palo Alto, CA 94304 USA

来源：

JOURNAL OF THE AMERICAN COLLEGE OF RADIOLOGY | 2023年 / 20卷 / 09期

关键词：

generative artificial intelligence; radiology; limitations; large language models; ChatGPT; ARTIFICIAL-INTELLIGENCE; CLIMATE;

D O I：

10.1016/j.jacr.2023.07.007

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Generative artificial intelligence (AI) tools such as GPT-4, and the chatbot interface ChatGPT, show promise for a variety of applications in radiology and health care. However, like other AI tools, ChatGPT has limitations and potential pitfalls that must be considered before adopting it for teaching, clinical practice, and beyond. We summarize five major emerging use cases for ChatGPT and generative AI in radiology across the levels of increasing data complexity, along with pitfalls associated with each. As the use of AI in health care continues to grow, it is crucial for radiologists (and all physicians) to stay informed and ensure the safe translation of these new technologies.

引用

页码：877 / 885

页数：9

共 64 条

[1] Persistent Anti-Muslim Bias in Large Language Models [J].