Utilizing ChatGPT-4 for Providing Medical Information on Blepharoplasties to Patients
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
The advent of life-saving devices and electronic health records highlights technology's impact on medicine, demonstrated by OpenAI's (San Francisco, CA) ChatGPT, a large language model with human-like responsiveness and self-improvement capabilities.1 Plastic and reconstructive surgery is an innovative surgical discipline that depends heavily on research to enhance patient-centric outcomes. The subspecialty of cosmetic surgery is continuously evolving, and it has a significant impact on the economy. In 2020, the American Society of Plastic Surgeons (ASPS) reported that the US cosmetic surgery industry was valued at $16.7 billion.2 Blepharoplasty is a common surgical intervention aimed at correcting functional and aesthetic abnormalities of the eyelids/conjunctiva which has gained significant traction in recent years.3 The growing interest in this procedure among patients seeking aesthetic and vision-related improvements necessitates access to accurate and comprehensive information. Although blepharoplasty has a high success rate, potential complications include infection, hematoma, dry eye syndrome, and temporary or permanent changes in vision.4 Postoperative care and adherence to the surgeon's recommendations are crucial for optimal outcomes and to avoid serious complications. Therefore, prior to undergoing blepharoplasty, it is crucial for patients to be well-informed about various aspects of the procedure to achieve greater satisfaction. Artificial intelligence (AI) language models such as ChatGPT-4 can bridge the communication gap between medical professions and patients by supplying pertinent, accurate, evidence-based information in language that is logical, coherent, and easy to understand. ChatGPT-4 has exhibited exceptional prowess in producing human-like text in response to input. Its training encompasses a vast array of data sources, including high-level-evidence medical literature, which enables it to provide general information on a multitude of cosmetic procedures, including blepharoplasty.5 Due to the emergent nature of ChatGPT and its ability to deliver high-quality evidence-based information on cosmetic procedures, the aim of this study was to determine whether ChatGPT can furnish accurate and safe medical information to patients. The objectives include evaluating the accuracy, clarity, and comprehensibility of the information generated by ChatGPT-4 in response to patient queries related to blepharoplasty, as well as assessing its potential to support healthcare professionals in educating patients and addressing their concerns. These questions were developed from the ASPS handbook.6 These findings may contribute to the growing body of knowledge on AI applications in healthcare and pave the way for further research on how AI-driven language models can complement and enhance traditional patient education methods in the context of cosmetic and reconstructive surgery. The inclusion criteria encompassed documenting ChatGPT's initial response to each question, without permitting any follow-up clarifications or corrections. Careful attention was given to ensure the absence of grammatical or syntactical errors in each query. All questions were submitted on the same day via a single ChatGPT Plus account with access to ChatGPT-4. No exclusion criteria were applied to ChatGPT's generated answers. No institutional ethics approval was required for analyzing an artificial chatbot and for this type of study design (observational case study of a freely available chatbot). The first prompt was “Hi ChatGPT, I am a patient seeking blepharoplasty for lax upper eyelid, what are the risks and complications associated with this procedure? Can you provide me with 3 high-level evidence studies to read prior to the operation” (Figure 1). The second prompt was “Hi ChatGPT, I am a 64-year-old female patient with no comorbidities seeking blepharoplasty for lax upper eyelid, how long of a recovery period can I expect, and what kind of help will I need during my recovery?” (Figure 2). The last prompt was “Hi ChatGPT, same patient as previous questions, how can I expect my eyes to look over time?” (Figure 3). Prompt 1. Prompt 2. Prompt 3. Overall, ChatGPT-4 provided quick and safe medical advice to questions commonly asked by patients considering blepharoplasty. From a patient perspective, they are provided information with sufficient depth, without any excessive medical jargon. The answers are understandably broad, as the AI chatbot is incapable of providing personalized advice, and appropriately encourages discussion between the patient and their plastic and reconstructive surgeon in all the answers. The responses provided by ChatGPT-4 provide an excellent adjunct to those discussions and a foundation for the patient to develop more detailed questions to ask. Despite the potential benefits of ChatGPT-4 in disseminating medical information to patients, it is essential to acknowledge the software’s limitations. Primarily,
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ChatGPT - Reshaping medical education and clinical management
Khan, R. A., Jawaid, M., Khan, A. R., & Sajjad, M. (2023) · Pakistan Journal of Medical Sciences · doi:10.12669/pjms.39.2.7653 · Cited by 628
Cited by
Large Language Models for Chatbot Health Advice Studies: A Systematic Review
Huo, B., Boyle, A., Marfo, N., Tangamornsuksan, W., Steen, J. P., McKechnie, T., Lee, Y., Mayol, J., Antoniou, S. A., Thirunavukarasu, A. J., et al. (2025) · JAMA Network Open · doi:10.1001/jamanetworkopen.2024.57879 · Cited by 283
Younis, H. A., Eisa, T. A. E., Nasser, M., Sahib, T. M., Noor, A. A., Alyasiri, O. M., Salisu, S., Hayder, I. M., & Younis, H. A. (2024) · Diagnostics · doi:10.3390/diagnostics14010109 · Cited by 242
Assessing the research landscape and clinical utility of large language models: a scoping review
Park, Y.-J., Pillai, A., Deng, J., Guo, E., Gupta, M., Paget, M., & Naugler, C. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02459-6 · Cited by 187
Kim, J., Wang, K., Weng, C., & Liu, C. (2024) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2024.08.010 · Cited by 53
Wang, G., Gao, K., Liu, Q., Wu, Y., Zhang, K., Zhou, W., & Guo, C. (2023) · Journal of Medical Internet Research · doi:10.2196/49771 · Cited by 48
“We found that ChatGPT performs excellently in many areas, but it also has the following limitations [25-27].”
Metadata
- Authors
- Cox, A., Seth, I., Xie, Y., Hunter-Smith, D. J., & Rozen, W. M.
- Venue
- Aesthetic Surgery Journal
- Publisher
- Oxford University Press (OUP)
- Published
- 2023-04-10
- Volume
- 43
- Issue
- 8
- Pages
- NP658-NP662
- ISSN
- 1090-820X (ISSN-L)
- 1527-330X
- OpenAlex
- W4362735179
- Cited by
- 79
- References
- 1
- FWCI
- 2.70
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.