期刊目次

加入编委

期刊订阅

添加您的邮件地址以接收即将发行期刊数据:

Open Access Article

International Journal of Medicine and Data. 2025; 9: (1) ; 13-19 ; DOI: 10.12208/j.ijmd.20250003.

The current applications of ChatGPT in ophthalmology
ChatGPT在眼科的应用现状

作者: 李鹏峰, 方冬, 庄仪婧, 白冰玉, 黑向青, 刁滢滢, 陈璐, 张少冲 *

暨南大学第二临床医学院,深圳市眼科医院 广东深圳

*通讯作者: 张少冲,单位:暨南大学第二临床医学院,深圳市眼科医院 广东深圳;

发布时间: 2025-02-27 总浏览量: 92

摘要

近年来,人工智能(Artificial intelligence,AI),特别是大型语言模型(Large language models,LLM)如ChatGPT,在医学领域展现出巨大应用潜力,尤其在眼科领域。凭借强大的自然语言处理能力,ChatGPT为医学教育、医疗文书生成、临床决策支持、医学研究和患者教育等场景提供了高效技术支持。然而,其在医学信息准确性、多模态数据处理、数据隐私保护及知识更新等方面仍面临挑战。未来需通过模型优化、数据安全增强及知识库更新,确保ChatGPT可靠应用于医学领域,推动临床和科研效率提升。

关键词: 人工智能;大型语言模型;聊天机器人;生成式预训练转化器;眼科学

Abstract

In recent years,Artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has demonstrated immense potential in the medical field, especially in ophthalmology. With its powerful natural language processing capabilities, ChatGPT provides efficient technical support in medical education, medical documentation generation, clinical decision support, medical research, and patient education. However, it still faces challenges regarding the accuracy of medical information, multimodal data processing, data privacy protection, and knowledge updates. In the future, model optimization, enhanced data security, and knowledge base updates are necessary to ensure the reliable application of ChatGPT in the medical field, thereby improving clinical and research efficiency.

Key words: Artificial Intelligence (AI); Large Language Models; Chatbots; Generative Pre-trained Transformers (GPT); Ophthalmology

参考文献 References

[1] Kojima, T., S.S. Gu, M. Reid, et al. Large language models are zero-shot reasoners[J]. Advances in neural information processing systems, 2022. 35: p. 22199-22213.

[2] OpenAI, R. Gpt-4 technical report. arxiv 2303.08774[J]. View in Article, 2023. 2(5).

[3] Mihalache, A., R.S. Huang, M.M. Popovic, et al. ChatGPT-4: an assessment of an upgraded artificial intelligence chatbot in the United States Medical Licensing Examination[J]. Medical Teacher, 2024. 46(3): p. 366-372.

[4] Mihalache, A., M.M. Popovic, and R.H. Muni. Performance of an artificial intelligence chatbot in ophthalmic knowledge assessment[J]. JAMA ophthalmology, 2023. 141(6): p. 589-597.

[5] Kung, T.H., M. Cheatham, A. Medenilla, et al., Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models[J]. PLoS digital health, 2023. 2(2): p. e0000198.

[6] Waisberg, E., J. Ong, M. Masalkhi, et al., GPT-4 and Ophthalmology Operative Notes[J]. Ann Biomed Eng, 2023. 51(11): p. 2353-2355.

[7] Singh, S., A. Djalilian, and M.J. Ali, ChatGPT and Ophthalmology: Exploring Its Potential with Discharge Summaries and Operative Notes[J]. Semin Ophthalmol, 2023. 38(5): p. 503-507.

[8] Cascella, M., J. Montomoli, V. Bellini, et al., Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios[J]. J Med Syst, 2023. 47(1): p. 33.

[9] Leong, Y.-Y., C. Vasseneix, M.T. Finkelstein, et al., Artificial intelligence meets neuro-ophthalmology[J]. The Asia-Pacific Journal of Ophthalmology, 2022. 11(2): p. 111-125.

[10] Shemer, A., M. Cohen, A. Altarescu, et al., Diagnostic capabilities of ChatGPT in ophthalmology[J]. Graefes Arch Clin Exp Ophthalmol, 2024. 262(7): p. 2345-2352.

[11] Salvagno, M., F.S. Taccone, and A.G. Gerli, Can artificial intelligence help for scientific writing?[J]. Crit Care, 2023. 27(1): p. 75.

[12] 惠延年.人工智能聊天机器人助力眼科和科学论文写作[J]. 国际眼科杂志, 2024. 24(01): p. 1-4.

[13] Chen, J.S., W.C. Lin, S. Yang, et al., Development of an Open-Source Annotated Glaucoma Medication Dataset From Clinical Notes in the Electronic Health Record[J]. Transl Vis Sci Technol, 2022. 11(11): p. 20.

[14] Bernstein, I.A., Y.V. Zhang, D. Govil, et al., Comparison of ophthalmologist and large language model chatbot responses to online patient eye care questions[J]. JAMA network open, 2023. 6(8): p. e2330320-e2330320.

[15] Goodman, R.S., J.R. Patrinely, C.A. Stone, et al., Accuracy and reliability of chatbot responses to physician questions[J]. JAMA network open, 2023. 6(10): p. e2336483-e2336483.

[16] Smith, A.L., F. Greaves, and T. Panch, Hallucination or Confabulation? Neuroanatomy as metaphor in Large Language Models[J]. PLOS Digit Health, 2023. 2(11): p. e0000388.

[17] Wang, C., J. Ong, C. Wang, et al., Potential for GPT Technology to Optimize Future Clinical Decision-Making Using Retrieval-Augmented Generation[J]. Ann Biomed Eng, 2024. 52(5): p. 1115-1118.

[18] Khoje, M. Navigating Data Privacy and Analytics: The Role of Large Language Models in Masking conversational data in data platforms. in 2024 IEEE 3rd International Conference on AI in Cybersecurity (ICAIC). 2024. IEEE.

[19] Brown, T.B., Language models are few-shot learners[J]. arXiv preprint arXiv:2005.14165, 2020.

[20] Ouyang, L., J. Wu, X. Jiang, et al., Training language models to follow instructions with human feedback[J]. Advances in neural information processing systems, 2022. 35: p. 27730-27744.

[21] Vaswani, A., Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017.

[22] Mihalache, A., R.S. Huang, M.M. Popovic, et al., ChatGPT-4: An assessment of an upgraded artificial intelligence chatbot in the United States Medical Licensing Examination[J]. Med Teach, 2024. 46(3): p. 366-372.

[23] Teebagy, S., L. Colwell, E. Wood, et al., Improved Performance of ChatGPT-4 on the OKAP Examination: A Comparative Study with ChatGPT-3.5[J]. J Acad Ophthalmol (2017), 2023. 15(2): p. e184-e187.

[24] Haddad, F. and J.S. Saade, Performance of ChatGPT on Ophthalmology-Related Questions Across Various Examination Levels: Observational Study[J]. JMIR Med Educ, 2024. 10: p. e50842.

[25] Mihalache, A., R.S. Huang, M.M. Popovic, et al., Accuracy of an Artificial Intelligence Chatbot's Interpretation of Clinical Ophthalmic Images[J]. JAMA Ophthalmol, 2024. 142(4): p. 321-326.

[26] Read-Brown, S., M.R. Hribar, L.G. Reznick, et al., Time Requirements for Electronic Health Record Use in an Academic Ophthalmology Center[J]. JAMA Ophthalmol, 2017. 135(11): p. 1250-1257.

[27] Waisberg, E., J. Ong, M. Masalkhi, et al., GPT-4 to document ophthalmic post-operative complications[J]. Eye (Lond), 2024. 38(3): p. 414-415.

[28] Anderson, R.L., M. de Los Angeles Ramos Cadena, and J.S. Schuman, Glaucoma Diagnosis: from the Artisanal to the Defined[J]. Ophthalmol Glaucoma, 2018. 1(1): p. 3-14.

[29] Delsoz, M., Y. Madadi, H. Raja, et al., Performance of ChatGPT in Diagnosis of Corneal Eye Diseases[J]. Cornea, 2024. 43(5): p. 664-670.

[30] Delsoz, M., H. Raja, Y. Madadi, et al., The use of ChatGPT to assist in diagnosing glaucoma based on clinical case reports[J]. Ophthalmology and Therapy, 2023. 12(6): p. 3121-3132.

[31] Leong, Y.Y., C. Vasseneix, M.T. Finkelstein, et al., Artificial Intelligence Meets Neuro-Ophthalmology[J]. Asia Pac J Ophthalmol (Phila), 2022. 11(2): p. 111-125.

[32] Rojas-Carabali, W., C. Cifuentes-González, X. Wei, et al., Evaluating the diagnostic accuracy and management recommendations of ChatGPT in uveitis[J]. Ocular immunology and inflammation, 2024. 32(8): p. 1526-1531.

[33] Liu, X., J. Wu, A. Shao, et al., Uncovering Language Disparity of ChatGPT on Retinal Vascular Disease Classification: Cross-Sectional Study[J]. J Med Internet Res, 2024. 26: p. e51926.

[34] Milad, D., F. Antaki, J. Milad, et al., Assessing the medical reasoning skills of GPT-4 in complex ophthalmology cases[J]. Br J Ophthalmol, 2024. 108(10): p. 1398-1405.

[35] Hu, X., A.R. Ran, T.X. Nguyen, et al., What can GPT-4 do for Diagnosing Rare Eye Diseases? A Pilot Study[J]. Ophthalmol Ther, 2023. 12(6): p. 3395-3402.

[36] Waisberg, E., J. Ong, M. Masalkhi, et al., Google's AI chatbot "Bard": a side-by-side comparison with ChatGPT and its utilization in ophthalmology[J]. Eye (Lond), 2024. 38(4): p. 642-645.

[37] Tao, B.K., N. Hua, J. Milkovich, et al., ChatGPT-3.5 and Bing Chat in ophthalmology: an updated evaluation of performance, readability, and informative sources[J]. Eye (Lond), 2024. 38(10): p. 1897-1902.

[38] Owens, B., How Nature readers are using ChatGPT[J]. Nature, 2023. 615(7950): p. 20.

[39] Dahmen, J., M.E. Kayaalp, M. Ollivier, et al., Artificial intelligence bot ChatGPT in medical research: the potential game changer as a double-edged sword[J]. Knee Surg Sports Traumatol Arthrosc, 2023. 31(4): p. 1187-1189.

[40] Haman, M. and M. Školník, Using ChatGPT to conduct a literature review[J]. Account Res, 2024. 31(8): p. 1244-1246.

[41] Singh, S. and S. Watson, ChatGPT as a tool for conducting literature review for dry eye disease[J]. Clinical & Experimental Ophthalmology, 2023. 51(7).

[42] Kuehn, B.M., More than one-third of US individuals use the Internet to self-diagnose[J]. Jama, 2013. 309(8): p. 756-7.

[43] Nadarzynski, T., O. Miles, A. Cowie, et al., Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study[J]. Digit Health, 2019. 5: p. 2055207619871808.

[44] Lyons, R.J., S.R. Arepalli, O. Fromal, et al., Artificial intelligence chatbot performance in triage of ophthalmic conditions[J]. Can J Ophthalmol, 2024. 59(4): p. e301-e308.

[45] Zandi, R., J.D. Fahey, M. Drakopoulos, et al., Exploring Diagnostic Precision and Triage Proficiency: A Comparative Study of GPT-4 and Bard in Addressing Common Ophthalmic Complaints[J]. Bioengineering (Basel), 2024. 11(2).

[46] Alqudah, A.A., A.J. Aleshawi, M. Baker, et al., Evaluating accuracy and reproducibility of ChatGPT responses to patient-based questions in Ophthalmology: An observational study[J]. Medicine (Baltimore), 2024. 103(32): p. e39120.

[47] Tan, D.N.H., Y.C. Tham, V. Koh, et al., Evaluating Chatbot responses to patient questions in the field of glaucoma[J]. Front Med (Lausanne), 2024. 11: p. 1359073.

[48] Rasmussen, M.L.R., A.C. Larsen, Y. Subhi, et al., Artificial intelligence-based ChatGPT chatbot responses for patient and parent questions on vernal keratoconjunctivitis[J]. Graefes Arch Clin Exp Ophthalmol, 2023. 261(10): p. 3041-3043.

[49] Ferro Desideri, L., J. Roth, M. Zinkernagel, et al., "Application and accuracy of artificial intelligence-derived large language models in patients with age related macular degeneration"[J]. Int J Retina Vitreous, 2023. 9(1): p. 71.

[50] Yılmaz, I.B.E. and L. Doğan, Talking technology: exploring chatbots as a tool for cataract patient education[J]. Clin Exp Optom, 2024: p. 1-9.

[51] Anguita, R., C. Downie, L. Ferro Desideri, et al., Assessing large language models' accuracy in providing patient support for choroidal melanoma[J]. Eye (Lond), 2024.

[52] Tailor, P.D., L.A. Dalvin, J.J. Chen, et al., A Comparative Study of Responses to Retina Questions from Either Experts, Expert-Edited Large Language Models, or Expert-Edited Large Language Models Alone[J]. Ophthalmol Sci, 2024. 4(4): p. 100485.

[53] Biswas, S., N.S. Logan, L.N. Davies, et al., Assessing the utility of ChatGPT as an artificial intelligence‐based large language model for information to answer questions on myopia[J]. Ophthalmic and Physiological Optics, 2023. 43(6): p. 1562-1570.

[54] Lim, Z.W., K. Pushpanathan, S.M.E. Yew, et al., Benchmarking large language models' performances for myopia care: a comparative analysis of ChatGPT-3.5, ChatGPT-4.0, and Google Bard[J]. EBioMedicine, 2023. 95: p. 104770.

[55] Ong, J., N. Kedia, S. Harihar, et al., Applying large language model artificial intelligence for retina international classification of diseases (ICD) coding[J]. Journal of Medical Artificial Intelligence, 2023. 6.

[56] Zhao, H., Q. Ling, Y. Pan, et al., Ophtha-llama2: A large language model for ophthalmology[J]. arXiv preprint arXiv:2312.04906, 2023.

[57] Wang, C., J. Ong, C. Wang, et al., Potential for GPT technology to optimize future clinical decision-making using retrieval-augmented generation[J]. Annals of Biomedical Engineering, 2024. 52(5): p. 1115-1118.

[58] Xu, P., X. Chen, Z. Zhao, et al., Evaluation of a digital ophthalmologist app built by GPT4-V (ision)[J]. medRxiv, 2023: p. 2023.11. 27.23299056.

[59] 5Waisberg, E., J. Ong, M. Masalkhi, et al., Automated ophthalmic imaging analysis in the era of generative pre-trained transformer-4[J]. The Pan-American Journal of Ophthalmology, 2023. 5(1): p. 50.

引用本文

李鹏峰, 方冬, 庄仪婧, 白冰玉, 黑向青, 刁滢滢, 陈璐, 张少冲, ChatGPT在眼科的应用现状[J]. 国际医学与数据杂志, 2025; 9: (1) : 13-19.