Appropriateness and Readability of ChatGPT-4-Generated Responses for Surgical Treatment of Retinal Diseases
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
OBJECTIVE To evaluate the appropriateness and readability of the medical knowledge provided by ChatGPT-4, an artificial-intelligence-powered conversational search engine regarding common vitreoretinal surgeries for retinal detachments, macular holes, and epiretinal membranes. DESIGN Retrospective cross-sectional study. SUBJECTS This study does not involve any human participants. METHODS We created lists of common questions about the definition, prevalence, visual impact, diagnostic methods, surgical and non-surgical treatment options, postoperative information, surgery-related complications, and visual prognosis of retinal detachment, macular hole, and epiretinal membrane, and asked each question three times on the online ChatGPT-4 platform. The data for this cross-sectional study were recorded on April 25, 2023. Two independent retina specialists graded the appropriateness of the responses. Readability was assessed using Readable, an online readability tool. MAIN OUTCOME MEASURES The "appropriateness" and "readability" of the answers generated by ChatGPT-4 bot. RESULTS Responses were consistently appropriate in 84.6% (33/39), 92% (23/25), and 91.7% (22/24) of the questions related to retinal detachment, macular hole, and epiretinal membrane, respectively. Answers were inappropriate at least once in 5.1% (2/39), 8% (2/25), and 8.3% (2/24) of the respective questions. The average Flesch Kincaid Grade Level and Flesch Reading Ease Score were 14.1±2.6 and 32.3±10.8 for retinal detachment, 14±1.3 and 34.4±7.7 for macular hole, and 14.8±1.3 and 28.1±7.5 for epiretinal membrane. These scores indicate that the answers are difficult or very difficult to read for the average lay person and college graduation would be required to understand the material. CONCLUSIONS Most of the answers provided by ChatGPT-4 were consistently appropriate. However, ChatGPT and other natural language models in their current form are not a source of factual information. Improving the credibility and readability of responses, especially in specialized fields such as medicine, is a critical focus of research. Patients, physicians, and laypersons should be advised of the limitations of these tools for eye- and health-related counseling.
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
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
ChatGPT and other large language models are double-edged swords
Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023) · Radiology · doi:10.1148/radiol.230163 · Cited by 1,008
Yeo, Y. H., Samaan, J. S., Ng, W. H., Ting, P.-S., Trivedi, H., Vipani, A., Ayoub, W., Yang, J. D., Liran, O., Spiegel, B., et al. (2023) · doi:10.1101/2023.02.06.23285449 · Cited by 666
Sallam, M., Salim, N. A., Al-Tammemi, A. B., Barakat, M., Fayyad, D., Hallit, S., Harapan, H., Hallit, R., & Mahafzah, A. (2023) · Cureus · doi:10.7759/cureus.35029 · Cited by 130
Cited by
Lim, Z. W., Pushpanathan, K., Yew, S. M. E., Lai, Y., Sun, C.-H., Lam, J. S. H., Chen, D. Z., Goh, J. H. L., Tan, M. C. J., Sheng, B., et al. (2023) · eBioMedicine · doi:10.1016/j.ebiom.2023.104770 · Cited by 310
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
Tangadulrat, P., Sono, S., & Tangtrakulwanich, B. (2023) · JMIR Medical Education · doi:10.2196/50658 · Cited by 99
“The responses to common questions about retinal detachments were rated appropriate in 80%-90% of the questions asked [20].”
BackgroundGhanem, Y. K., Rouhi, A. D., Al-Houssan, A., Saleh, Z., Moccia, M. C., Joshi, H., Dumon, K. R., Hong, Y., Spitz, F., Joshi, A. R., et al. (2024) · Surgical Endoscopy · doi:10.1007/s00464-024-10739-5 · Cited by 97
“As highlighted by our study and Momenaei et al.’s study, these AI platforms produce content that is difficult to read in a wide variety of topics, not just gastrointestinal surgery [24].”
BackgroundResultFFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer
Chen, X., Zhang, W., Xu, P., Zhao, Z., Zheng, Y., Shi, D., & He, M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01101-z · Cited by 72
Xu, P., Chen, X., Zhao, Z., & Shi, D. (2024) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-325054 · Cited by 63
Analyzing evaluation methods for large language models in the medical field: a scoping review
Lee, J., Park, S., Shin, J., & Cho, B. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02709-7 · Cited by 52
Tepe, M., & Emekli, E. (2024) · Patient Education and Counseling · doi:10.1016/j.pec.2024.108307 · Cited by 42
ICGA-GPT: report generation and question answering for indocyanine green angiography images
Chen, X., Zhang, W., Zhao, Z., Xu, P., Zheng, Y., Shi, D., & He, M. (2024) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-324446 · Cited by 36
Accuracy of large language models in answering ophthalmology board-style questions: A meta-analysis
Wu, J.-H., Nishida, T., & Liu, T. Y. A. (2024) · Asia-Pacific Journal of Ophthalmology · doi:10.1016/j.apjo.2024.100106 · Cited by 16
Metadata
- Authors
- Momenaei, B., Wakabayashi, T., Shahlaee, A., Durrani, A. F., Pandit, S. A., Wang, K., Mansour, H. A., Abishek, R. M., Xu, D., Sridhar, J., Yonekawa, Y., & Kuriyan, A. E.
- Venue
- Ophthalmology Retina
- Publisher
- Elsevier BV
- Published
- 2023-10
- Volume
- 7
- Issue
- 10
- Pages
- 862-868
- ISSN
- 2468-6530 (ISSN-L)
- OpenAlex
- W4379209901
- Cited by
- 178
- References
- 5
- FWCI
- 6.16
- Type
- journal article
- Language
- en
- Open access
- closed
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.