Attitudes of Radiologists and Interns Toward the Adoption of GPT-like Technologies: a National Survey Study in China

Overview

Journal Insights Imaging

Publisher Springer

Date 2025 Jan 31

PMID 39890713

Authors

Tianyi Xia

Shijun Zhang

Ben Zhao

Ying Lei

Zebin Xiao

Bingwei Chen

Junhao Zha

Yaoyao Yu

Zhijun Wu

Chunqiang Lu

Tianyu Tang

Yang Song

Yuancheng Wang

Shenghong Ju

Affiliations

Soon will be listed here.

Abstract

Objectives: To investigate the attitudes of Chinese radiologists or interns towards generative pre-trained (GPT)-like technologies.

Methods: A prospective survey was distributed to 1339 Chinese radiologists or interns via an online platform from October 2023 to May 2024. The questionnaire covered respondent characteristics, opinions on using GPT-like technologies (in clinical practice, training and education, environment and regulation, and development trends), and their attitudes toward these technologies. Logistic regression was conducted to identify underlying factors associated with the attitude.

Results: After quality control, 1289 respondents (median age, 37.0 years [IQR, 31.0-44.0 years]; 813 males) were surveyed. Most of the respondents (n = 1223, 94.9%) supported adoption of GPT-like technologies. Based on the acceptance level of GPT-like technologies, the respondents were 3 (0.2%), 29 (2.2%), 352 (27.3%), 677 (52.5%), and 228 (17.7%) from low to high acceptance degrees. Multivariable analysis revealed significant associations between positive attitudes towards GPT-like technologies and their acceptance: writing papers and language polishing (odds ratio [OR] = 1.99; p < 0.001), influence of colleagues using such technologies (OR = 1.77; p = 0.007), government regulation introduction (OR = 2.25; p < 0.001), and enhancement of decision support capabilities (OR = 2.67; p < 0.001). Sensitivity analyses confirmed these results for different acceptance thresholds (all p < 0.001).

Conclusions: Chinese radiologists or interns generally support GPT-like technologies due to their potential capabilities in clinical practice, medical education, and scientific research. They also emphasize the need for regulatory oversight and remain optimistic about their future medical applications.

Critical Relevance Statement: This study highlights the broad support among Chinese radiologists for GPT-like technologies, emphasizing their potential to enhance clinical decision-making, streamline medical education, and improve research efficiency, while underscoring the need for regulatory oversight.

Key Points: The impact of GPT-like technologies on the radiology field is unclear. Most Chinese radiologists express the supportive adoption of GPT-like technologies. GPT-like technologies' capabilities at research and clinic prompt the attitude.

References

Pinto Dos Santos D, Giese D, Brodehl S, Chon S, Staab W, Kleinert R . Medical students' attitude towards artificial intelligence: a multicentre survey. Eur Radiol. 2018; 29(4):1640-1646. DOI: 10.1007/s00330-018-5601-1. View

Lecler A, Duron L, Soyer P . Revolutionizing radiology with GPT-based models: Current applications, future possibilities and limitations of ChatGPT. Diagn Interv Imaging. 2023; 104(6):269-274. DOI: 10.1016/j.diii.2023.02.003. View

Lehnen N, Dorn F, Wiest I, Zimmermann H, Radbruch A, Kather J . Data Extraction from Free-Text Reports on Mechanical Thrombectomy in Acute Ischemic Stroke Using ChatGPT: A Retrospective Analysis. Radiology. 2024; 311(1):e232741. DOI: 10.1148/radiol.232741. View

Hayden N, Gilbert S, Poisson L, Griffith B, Klochko C . Performance of GPT-4 with Vision on Text- and Image-based ACR Diagnostic Radiology In-Training Examination Questions. Radiology. 2024; 312(3):e240153. DOI: 10.1148/radiol.240153. View

Huisman M, Ranschaert E, Parker W, Mastrodicasa D, Koci M, Pinto de Santos D . An international survey on AI in radiology in 1,041 radiologists and radiology residents part 1: fear of replacement, knowledge, and attitude. Eur Radiol. 2021; 31(9):7058-7066. PMC: 8379099. DOI: 10.1007/s00330-021-07781-5. View

Gertz R, Dratsch T, Bunck A, Lennartz S, Iuga A, Hellmich M . Potential of GPT-4 for Detecting Errors in Radiology Reports: Implications for Reporting Accuracy. Radiology. 2024; 311(1):e232714. DOI: 10.1148/radiol.232714. View

Schwartz L, Panicek D, Berk A, Li Y, Hricak H . Improving communication of diagnostic radiology findings through structured reporting. Radiology. 2011; 260(1):174-81. PMC: 3121011. DOI: 10.1148/radiol.11101913. View

Thirunavukarasu A, Ting D, Elangovan K, Gutierrez L, Tan T, Ting D . Large language models in medicine. Nat Med. 2023; 29(8):1930-1940. DOI: 10.1038/s41591-023-02448-8. View

Bhayana R, Nanda B, Dehkharghanian T, Deng Y, Bhambra N, Elias G . Large Language Models for Automated Synoptic Reports and Resectability Categorization in Pancreatic Cancer. Radiology. 2024; 311(3):e233117. DOI: 10.1148/radiol.233117. View

10.

Williams C, Zack T, Miao B, Sushil M, Wang M, Kornblith A . Use of a Large Language Model to Assess Clinical Acuity of Adults in the Emergency Department. JAMA Netw Open. 2024; 7(5):e248895. PMC: 11077390. DOI: 10.1001/jamanetworkopen.2024.8895. View

11.

Sun S, Huynh K, Cortes G, Hill R, Tran J, Yeh L . Testing the Ability and Limitations of ChatGPT to Generate Differential Diagnoses from Transcribed Radiologic Findings. Radiology. 2024; 313(1):e232346. DOI: 10.1148/radiol.232346. View

12.

Kataoka Y, So R . Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine. N Engl J Med. 2023; 388(25):2399. DOI: 10.1056/NEJMc2305286. View

13.

Alexander R, Waite S, Bruno M, Krupinski E, Berlin L, Macknik S . Mandating Limits on Workload, Duty, and Speed in Radiology. Radiology. 2022; 304(2):274-282. PMC: 9340237. DOI: 10.1148/radiol.212631. View

14.

Lai H, Ge L, Sun M, Pan B, Huang J, Hou L . Assessing the Risk of Bias in Randomized Clinical Trials With Large Language Models. JAMA Netw Open. 2024; 7(5):e2412687. PMC: 11112444. DOI: 10.1001/jamanetworkopen.2024.12687. View

15.

Bhayana R, Krishna S, Bleakney R . Performance of ChatGPT on a Radiology Board-style Examination: Insights into Current Strengths and Limitations. Radiology. 2023; 307(5):e230582. DOI: 10.1148/radiol.230582. View

16.

Zhou Y, Ong H, Kennedy P, Wu C, Kazam J, Hentel K . Evaluating GPT-V4 (GPT-4 with Vision) on Detection of Radiologic Findings on Chest Radiographs. Radiology. 2024; 311(2):e233270. DOI: 10.1148/radiol.233270. View

17.

Mesko B, Topol E . The imperative for regulatory oversight of large language models (or generative AI) in healthcare. NPJ Digit Med. 2023; 6(1):120. PMC: 10326069. DOI: 10.1038/s41746-023-00873-0. View

18.

Adams L, Truhn D, Busch F, Kader A, Niehues S, Makowski M . Leveraging GPT-4 for Post Hoc Transformation of Free-text Radiology Reports into Structured Reporting: A Multilingual Feasibility Study. Radiology. 2023; 307(4):e230725. DOI: 10.1148/radiol.230725. View

19.

Bhayana R . Chatbots and Large Language Models in Radiology: A Practical Primer for Clinical and Research Applications. Radiology. 2024; 310(1):e232756. DOI: 10.1148/radiol.232756. View

20.

Cozzi A, Pinker K, Hidber A, Zhang T, Bonomo L, Gullo R . BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study. Radiology. 2024; 311(1):e232133. PMC: 11070611. DOI: 10.1148/radiol.232133. View