Please login or create an account. If you do not have access to this content, you will be shown a 30 second preview and licensing options.
- Presentation
Utilizing Natural Language Processing Tools to Help Reduce Physician Burnout: The Resident Perspective
Description
In a symposium presentation, Kelly Reynolds, a third-year dermatology resident at the University of Michigan, discussed the potential of leveraging natural language processing (NLP) tools, including AI chatbots like ChatGPT, to mitigate physician burnout. This issue has become particularly pressing in the context of the COVID-19 pandemic, which significantly increased the volume of patient messages and associated work for physicians, contributing to higher burnout rates. Reynolds shared findings from a study she conducted, which evaluated the quality of AI-generated responses to patient questions compared to those created by dermatology providers. The study concluded that while AI could assist by generating preliminary responses, the quality and empathy of physician-generated replies were superior. Reynolds highlighted the efficiency that NLP tools could bring, estimating that they could save substantial time in patient communication, thereby allowing physicians to focus more on clinical work. Despite the promising capabilities of AI, she emphasized that these tools are not replacements for the physician but rather serve as aids in managing mundane tasks, ultimately aiming to improve physician well-being and patient satisfaction in dermatology and beyond.
View moreConclusions
- The COVID-19 pandemic significantly increased rates of burnout among resident physicians.
- Natural language processing (NLP) tools show promise in reducing physician burnout by streamlining communication tasks.
- ChatGPT can assist in responding to patient questions, potentially saving physicians time.
- Despite concerns about AI, the study found that physician-generated responses were preferred over ChatGPT's outputs.
- Physician responses demonstrated higher empathy, readability, and overall quality compared to ChatGPT responses.
- ChatGPT's output may still serve as a helpful tool for generating first drafts of responses, requiring some editing before use.
- Implementation of NLP tools may help improve workflows and patient outcomes, contributing to reduced burnout.
- Johnstone J, Gabara A, Hopman WM, Touma NJ. Impact of the COVID-19 pandemic on the burnout rates of graduating Canadian urology residents. BJU Int. 2022; 130: 389-93.
- Nath B, Williams B, Jeffery MM, et al. Trends in Electronic Health Record Inbox Messaging During the COVID-19 Pandemic in an Ambulatory Practice Network in New England. JAMA Netw Open. 2021;4(10):e2131490. doi:10.1001/jamanetworkopen.2021.31490.
- Tai-Seale M, Dillon EC, Yang Y, et al. Physicians' well-being linked to in-basket messages generated by algorithms in electronic health records. Health Aff (Millwood). 2019;38(7):1073-1078. doi:10.1377/hlthaff.2018.05509
- OpenAI. ChatGPT: Optimizing language models for dialogue. OpenAI, 2022. https://openai.com/blog/chatgpt/
- Ayers JW, Poliak A, Dredze M, et al. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med. 2023;183(6):589-596.
- Zhu L, Mou W, Chen R. Can the ChatGPT and other large language models with internet-connected database solve the questions and concerns of patient with prostate cancer and help democratize medical knowledge? J Transl Med. 2023;21(1):269. doi:10.1186/s12967-023-04123-5
- Yeo YH, Samaan JS, Ng WH, et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma [published online ahead of print, 2023 Mar 22]. Clin Mol Hepatol. 2023;10.3350/cmh.2023.0089. doi:10.3350/cmh.2023.0089
- Rasmussen MLR, Larsen AC, Subhi Y, Potapenko I. Artificial intelligence-based ChatGPT chatbot responses for patient and parent questions on vernal keratoconjunctivitis [published online ahead of print, 2023 May 2]. Graefes Arch Clin Exp Ophthalmol. 2023;10.1007/s00417-023-06078-1. doi:10.1007/s00417-023-06078-1
- Chervenak J, Lieman H, Blanco-Breindel M, Jindal S. The promise and peril of using a large language model to obtain clinical information: ChatGPT performs strongly as a fertility counseling tool with limitations [published online ahead of print, 2023 May 20]. Fertil Steril. 2023;S0015-0282(23)00522-8. doi:10.1016/j.fertnstert.2023.05.151
- Dubin JA, Bains SS, Chen Z, et al. Using a Google Web Search Analysis to Assess the Utility of ChatGPT in Total Joint Arthroplasty [published online ahead of print, 2023 Apr 10]. J Arthroplasty. 2023;S0883-5403(23)00352-2. doi:10.1016/j.arth.2023.04.007
- Lee TC, Staller K, Botoman V, Pathipati MP, Varma S, Kuo B. ChatGPT Answers Common Patient Questions About Colonoscopy [published online ahead of print, 2023 May 5]. Gastroenterology. 2023;S0016-5085(23)00704-7. doi:10.1053/j.gastro.2023.04.033
- Samaan JS, Yeo YH, Rajeev N, et al. Assessing the Accuracy of Responses by the Language Model ChatGPT to Questions Regarding Bariatric Surgery. Obes Surg. 2023;33(6):1790-1796. doi:10.1007/s11695-023-06603-5
- Seth I, Cox A, Xie Y, et al. Evaluating Chatbot Efficacy for Answering Frequently Asked Questions in Plastic Surgery: A ChatGPT Case Study Focused on Breast Augmentation [published online ahead of print, 2023 May 9]. Aesthet Surg J. 2023;sjad140. doi:10.1093/asj/sjad140
- Xie Y, Seth I, Hunter-Smith DJ, Rozen WM, Ross R, Lee M. Aesthetic Surgery Advice and Counseling from Artificial Intelligence: A Rhinoplasty Consultation with ChatGPT [published online ahead of print, 2023 Apr 24]. Aesthetic Plast Surg. 2023;10.1007/s00266-023-03338-7. doi:10.1007/s00266-023-03338-7