Leveraging ChatGPT for Digital Healthcare Speech Writing
Keywords:
Evaluation, narrative medicine, large language models, chatgptAbstract
Introduction: Conversational agents, powered by artificial intelligence (AI) and natural language processing (NLP), are gaining traction in healthcare for various purposes. This study aimed to assess the potential of ChatGPT, a large language model, for generating health-related communication. Methods: ChatGPT was prompted with identical queries related to healthcare challenges, digital hospital benefits, and principles for organizing a digital hospital. The prompts were presented in January 2023 and 2024, and the resulting outputs were compared. Results: ChatGPT's outputs demonstrated a significant increase in complexity and detail between 2023 and 2024. The 2023 content catered to a general audience, offering clear and concise explanations suitable for raising awareness. In contrast, the 2024 outputs delved deeper into the topics, presenting multifaceted solutions and a broader global perspective. Notably, the 2024 outputs incorporated more technical language, potentially limiting accessibility for a lay audience. Both the 2023 and 2024 versions could benefit from including data to support the claims presented. This study suggests that ChatGPT exhibits promise for generating healthcare content. The observed increase in complexity over time aligns with advancements in AI language models. However, considerations like data inclusion, audience adaptation, and the use of clear language remain crucial. Conclusion: This research contributes to the growing body of knowledge on large language models in healthcare communication. The findings highlight the potential of ChatGPT for content creation while emphasizing the importance of human oversight and tailoring content for the target audience. Future research can explore these aspects in greater detail to optimize the use of AI in healthcare communication strategies.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Ariana-Anamaria CORDOȘ, Sebastian-Aurelian ŞTEFANIGĂ, Călin MUNTEAN
This work is licensed under a Creative Commons Attribution 4.0 International License.
All papers published in Applied Medical Informatics are licensed under a Creative Commons Attribution (CC BY 4.0) International License.