Artificial intelligence in pediatric ophthalmology: a comparative study of ChatGPT-4.0 and DeepSeek-R1 performance
Abstract
Objective: This study aims to evaluate and compare the accuracy and performance of two large language models (LLMs), ChatGPT-4.0 and DeepSeek-R1, in answering pediatric ophthalmology-related questions. Methods: A total of 44 multiple-choice questions were selected, covering various subspecialties of pediatric ophthalmology. Both LLMs were tasked with answering these questions, and their responses were compared in terms of accuracy. Results: ChatGPT-4.0 correctly answered 82% of the questions, while DeepSeek-R1 achieved a higher accuracy rate of 93% (p: 0.06). In strabismus, ChatGPT-4.0 answered 70% of questions correctly, while DeepSeek-R1 achieved 82% (p: 0.50). In other subspecialties, ChatGPT-4.0 answered 89% correctly, and DeepSeek-R1 achieved 100% accuracy (p: 0.25). Conclusion: DeepSeek-R1 outperformed ChatGPT-4.0 in overall accuracy, particularly in pediatric ophthalmology. These findings suggest the need for further optimization of LLM models to enhance their performance and reliability in clinical settings, especially in pediatric ophthalmology.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 · see citing works
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · see citing works
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 · see citing works
ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health
De Angelis, L., Baglivo, F., Arzilli, G., Privitera, G. P., Ferragina, P., Tozzi, A. E., & Rizzo, C. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1166120 · Cited by 708 · see citing works
Xu, L., Sanders, L., Li, K., & Chow, J. C. L. (2021) · JMIR Cancer · doi:10.2196/27850 · Cited by 571 · see citing works
Evaluating the Performance of ChatGPT in Ophthalmology
Antaki, F., Touma, S., Milad, D., El-Khoury, J., & Duval, R. (2023) · Ophthalmology Science · doi:10.1016/j.xops.2023.100324 · Cited by 563 · see citing works
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., Zhu, Q., Xu, R., Zhang, R., Ma, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.12948 · Cited by 538 · cited 1× · see citing works
“7 The most distinguishing characteristic of physicians compared to other professions is their ability to make complex diagnoses and medical decisions, a skill honed through experience.”
Cascella, M., Semeraro, F., Montomoli, J., Bellini, V., Piazza, O., & Bignami, E. (2024) · Journal of Medical Systems · doi:10.1007/s10916-024-02045-3 · Cited by 219 · see citing works
Large language model (ChatGPT) as a support tool for breast tumor board
Sorin, V., Klang, E., Sklair‐Levy, M., Cohen, I., Zippel, D. B., Lahat, N. B., Konen, E., & Barash, Y. (2023) · npj Breast Cancer · doi:10.1038/s41523-023-00557-8 · Cited by 216 · see citing works
Why and how to embrace AI such as ChatGPT in your academic life
Lin, Z. (2023) · Royal Society Open Science · doi:10.1098/rsos.230658 · Cited by 202 · see citing works
Why and how to embrace AI such as ChatGPT in your academic life
Lin, Z. (2023) · doi:10.31234/osf.io/sdx3j · Cited by 202 · see citing works
Lum, Z. C. (2023) · Clinical Orthopaedics and Related Research · doi:10.1097/corr.0000000000002704 · Cited by 152 · see citing works
Performance of Generative Large Language Models on Ophthalmology Board–Style Questions
Cai, L. Z., Shaheen, A., Jin, A., Fukui, R., Yi, J. S., Yannuzzi, N., & Alabiad, C. (2023) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2023.05.024 · Cited by 139 · see citing works
Moshirfar, M., Altaf, A. W., Stoakes, I. M., Tuttle, J. J., & Hoopes, P. C. (2023) · Cureus · doi:10.7759/cureus.40822 · Cited by 124 · see citing works
The Pros and Cons of Using ChatGPT in Medical Education: A Scoping Review
Mohammad, B., Supti, T., Alzubaidi, M., Shah, H., Alam, T., Shah, Z., & Househ, M. (2023) · Studies in Health Technology and Informatics · doi:10.3233/shti230580 · Cited by 114 · see citing works
Auxiliary use of ChatGPT in surgical diagnosis and treatment
Au, K., & Yang, W. (2023) · International Journal of Surgery · doi:10.1097/js9.0000000000000686 · Cited by 38 · see citing works
Tao, B. K.-L., Hua, N. J., Milkovich, J., & Micieli, J. A. (2024) · Eye · doi:10.1038/s41433-024-03037-w · Cited by 32 · see citing works
Botross, M., Mohammadi, S. O., Montgomery, K. E., & Crawford, C. M. (2024) · Cureus · doi:10.7759/cureus.57348 · Cited by 32 · see citing works
Gill, G. S., Tsai, J., Moxam, J., Sanghvi, H. A., & Gupta, S. (2024) · Cureus · doi:10.7759/cureus.69612 · Cited by 22 · see citing works
Ming, C. T. Y., Rojas-Carabali, W. A., Cifuentes‐González, C., et al. (2023) · Ocular Immunology and Inflammation · doi:10.1080/09273948.2023.2242462 · Cited by 20 · see citing works
Performance of Chatgpt in ophthalmology exam; human versus AI
Balcı, A. S., Yazar, Z., Öztürk, B., & Altan, Ç. (2024) · International Ophthalmology · doi:10.1007/s10792-024-03353-w · Cited by 17 · see citing works
Gill, G. S., Blair, J., & Litinsky, S. M. (2024) · Cureus · doi:10.7759/cureus.73812 · Cited by 11 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Yang, M., Long, J., He, Y., Meng, R., Ling, C., Long, Q., & Wen, J. (2026) · BMC Nursing · doi:10.1186/s12912-026-05132-7
“0, Gemini Advanced, and DeepSeek, for instance, have shown promising results on ophthalmology knowledge tests and clinical reasoning exercises, with certain models outperforming others in terms of reasoning accuracy, factual correctness, and consistency [22, 31].”
- Authors
- Karataş, G., & Karataş, M. E.
- Affiliations
- Prof. Dr. Cemil Taşcıoğlu City Hospital
- Şişli Etfal Eğitim ve Araştırma Hastanesi (TR)
- Corresponding author
- Karataş, Gamze
- Venue
- Strabismus
- Publisher
- Informa UK Limited
- Published
- 2025-07-29
- Volume
- 34
- Issue
- 1
- Pages
- 61-67
- ISSN
- 0927-3972 (ISSN-L)
- 1744-5132
- OpenAlex
- W4412728270
- Cited by
- 7
- References
- 22
- Citations by year
- 2026: 7
- FWCI
- 1.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Strabismus (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Ophthalmology › Ophthalmology and Visual Health Research
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- large language models, ChatGPT-4, DeepSeek-R1, pediatric ophthalmology, multiple-choice question accuracy, LLM comparison, medical question answering
- MeSH terms
- Generative Artificial Intelligence, Artificial Intelligence, Child, Humans, Ophthalmology, Pediatrics, Reproducibility of Results
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
