Ophthalmic Plastic Surgery Service, L.V. Prasad Eye Institute, Hyderabad, India.
Department of Ophthalmology, University of Illinois, Chicago, Illinois, USA.
Semin Ophthalmol. 2023 Jul;38(5):503-507. doi: 10.1080/08820538.2023.2209166. Epub 2023 May 3.
This study aimed to report the abilities of the large language model ChatGPT (OpenAI, San Francisco, USA) in constructing ophthalmic discharge summaries and operative notes.
A set of prompts was constructed through statements incorporating common ophthalmic surgeries across the subspecialties of the cornea, retina, glaucoma, paediatric ophthalmology, neuro-ophthalmology, and ophthalmic plastics surgery. The responses of ChatGPT were assessed by three surgeons carefully and analyzed them for evidence-based content, specificity of the response, presence of generic text, disclaimers, factual inaccuracies, and its abilities to admit mistakes and challenge incorrect premises.
A total of 24 prompts were presented to the ChatGPT. Twelve prompts assessed its ability to construct discharge summaries, and an equal number explored the potential for preparing operative notes. The response was found to be tailored based on the quality of inputs given and was provided in a matter of seconds. The ophthalmic discharge summaries had a valid but significant generic text. ChatGPT could incorporate specific medications, follow-up instructions, consultation time, and location within the discharge summaries when prompted appropriately. While the operative notes were detailed, they required significant tuning. ChatGPT routinely admits its mistakes and corrects itself immediately when confronted with factual inaccuracies. The mistakes are avoided in subsequent reports when given similar prompts.
The performance of ChatGPT in the context of ophthalmic discharge summaries and operative notes was encouraging. These are constructed rapidly in a matter of seconds. Focused training of ChatGPT on these issues with inclusion of a human verification step has an enormous potential to impact healthcare positively.
本研究旨在报告大型语言模型 ChatGPT（美国旧金山的 OpenAI）在构建眼科出院小结和手术记录方面的能力。
通过纳入角膜、视网膜、青光眼、小儿眼科、神经眼科和眼科整形手术等亚专业常见手术的陈述，构建了一组提示。三位外科医生仔细评估了 ChatGPT 的回复，并分析了其内容的循证依据、回复的特异性、通用文本的存在、免责声明、事实错误以及承认错误和挑战错误前提的能力。
总共向 ChatGPT 提出了 24 个提示。其中 12 个提示评估了其构建出院小结的能力，另外 12 个提示探索了编写手术记录的潜力。回复是根据输入质量定制的，并在几秒钟内提供。眼科出院小结有有效的但明显的通用文本。当适当提示时，ChatGPT 可以在出院小结中纳入特定药物、随访说明、咨询时间和地点。虽然手术记录详细，但需要进行重大调整。ChatGPT 会常规承认错误，并在发现事实错误时立即纠正。当给出类似的提示时，错误会在后续报告中避免。
ChatGPT 在眼科出院小结和手术记录方面的表现令人鼓舞。这些记录可以在几秒钟内快速生成。对 ChatGPT 进行针对这些问题的集中培训，并纳入人工验证步骤，具有对医疗保健产生积极影响的巨大潜力。
