BACKGROUND
Since November 2022, with the debut of OpenAI’s ChatGPT, there has been growing interest in the use of generative artificial intelligence (AI), including in healthcare. However, there is only limited research into doctors’ adoption of these tools and their opinions about their application in clinical practice.
OBJECTIVE
This study aimed to explore the opinions of general practitioners (GPs) in the United Kingdom (UK) about the use of generative AI tools (ChatGPT/Bard/Bing AI) in primary care.
METHODS
Between February 2nd-24th 2024, using a convenience sample, we administered a web-based mixed methods survey of 1000 GPs in the UK to explore their experiences and opinions about the impact of generative AI on clinical practice. Participants were recruited from registered GPs currently working in the UK using the clinician marketing service Doctors.net.uk. Quantitative data were analyzed using descriptive statistics and nonparametric tests. We used thematic content analysis to investigate free-text responses and conducted a qualitative descriptive analysis of written responses (“comments”) to 2 open-ended questions embedded in the web-based questionnaire.
RESULTS
A total of 1006 GPs responded, with 53% being male and 54% aged 46 years and older. Most GPs (80%) expressed a need for more support and training in understanding these tools. GPs at least somewhat agreed AI would improve documentation (59%), patient information gathering (56%), treatment plans (41%), diagnostic accuracy (40%), and prognostic accuracy (38%). Additionally, 62% believed patients might rely more on AI, 55% felt it could increase inequities, and 54% saw potential for patient harm, but 47% believed it would enhance healthcare efficiency. GPs who used these tools were significantly more optimistic about the scope for generative AI in improving clinical tasks compared with those who did not report using them. Elaborating on the quantitative component of the survey, 31% (307/1006) left comments that were classified into 4 major themes in relation to generative AI in medicine: (1) lack of familiarity and understanding, (2) a role in clinical practice, (3) concerns, and (4) thoughts on future of healthcare.
CONCLUSIONS
This study highlights UK GPs' perspectives on generative AI in clinical practice, emphasizing the need for more training. Many GPs reported a lack of knowledge and experience with this technology and a significant proportion used non-medical grade technology for clinical tasks, with the risks that this entails. Medical organizations must urgently invest in educating and guiding physicians on AI use and limitations.