ChatGPT: the future of discharge summaries?

By Sajan B Patel, Kyle Lam. 2023

607 citations recorded by the source corpus.

Subfields: Emergency Medicine, General Health Professions, Health Informatics, Large Language Models, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Emergency Medicine

1. Changyu Wang
2. Jialin Liu
3. Siru Liu

In General Health Professions

1. Changyu Wang
2. Jialin Liu
3. Siru Liu

In Health Informatics

1. Jan Egger
2. Jianning Li
3. Changyu Wang
4. Amin Dada
5. Jens Kleesiek
6. Behrus Puladi
7. Jialin Liu
8. Siru Liu

In Large Language Models

1. Arun James Thirunavukarasu
2. Changyu Wang
3. Ting Fang Tan
4. Jialin Liu
5. Siru Liu

In Medical & Health AI

1. Changyu Wang
2. Jialin Liu
3. Siru Liu

Citations in the corpus

• A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation (2025, neutral): “Despitetheexponentialgrowthinbenchmarksformodelreasoning abilities 31 , the evaluation of LLMs on clinical tasks has typically been carried out via “ question-answering ” (QA) benchmarks 5,8,32 .”
• Large language models in medicine (2023, background): “However, deployment in clinical contexts, where patient well-being is at risk, requires extensive validation 57 .”
• A study of generative large language model for medical research and healthcare (2023, neutral): “People are enthusiastic about LLMs in the potential to facilitate documentation of patient reports (e.g., a progress report) 3,4 , improving diagnostic accuracy 5 , and assisting in various clinical care 6,7 , while at the same time concerning the hallucinations and fabrications 7,8 , bias and…”
• Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health (2023, background): “Patel and Lam [89] discussed the possibility of using an LLM to generate discharge summaries, and Tang et al. [90] tested performance of ChatGPT on their in-house medical evidence dataset.”
• Utility of ChatGPT in Clinical Practice (2023, positive): “ChatGPT can also improve the quality of the discharge summary itself [23].”
• From human writing to artificial intelligence generated text: examining the prospects and potential threats of ChatGPT in academic writing (2023, neutral): “Summarizing lengthy academic papers can be a time-consuming process, but ChatGPT can be trained to automatically generate them [12, 14, 15].”
• Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential (2023, methodology): “…huge success of ChatGPT, studies have been conducted recently on adapting it for downstream tasks, such as writing a systematic literature review [7], medical school education [8], language translation [9], scholarly content generation for publication [9], and solving mathematical problems [10].”
• ChatGPT in Healthcare: A Taxonomy and Systematic Review (2023, methodology): “[82] clinical workflow comment use ChatGPT to generate a discharge summary for a patient who had hip replacement surgeries including follow-up care suggestions) Level 2”
• Investigating the Impact of User Trust on the Adoption and Use of ChatGPT: Survey Analysis (2023, neutral): “ChatGPT has garnered substantial traction among computer users, largely due to its impressive ability to generate responses that resemble those of the human language [7-10].”