TLDR: Generative artificial intelligence is rapidly transforming patient care, with over half of health systems exploring its applications. Prompt engineering is identified as a foundational skill to maximize the effectiveness of these AI tools, particularly Large Language Models (LLMs), in clinical workflows. A 2025 workshop by the American Medical Informatics Association aims to bridge the educational gap and empower healthcare professionals with practical prompt engineering skills.
Generative artificial intelligence (AI) is rapidly reshaping the landscape of patient care, with a significant majority of health systems, well over half, actively experimenting with various generative AI applications. At the core of successfully harnessing these powerful tools lies prompt engineering, a foundational discipline essential for enabling healthcare professionals to effectively leverage Large Language Models (LLMs), such as OpenAI’s GPT. These models are being applied to critical tasks like summarizing clinical notes and enhancing patient communication.
Despite the growing proliferation of generative AI resources, a notable void persists in educational content specifically tailored to the unique context of healthcare. To address this crucial need for clinician-focused education, the American Medical Informatics Association (AMIA) is offering an updated workshop titled ‘Prompt Engineering 101: A First Principles Approach (2025 Update).’. This session, scheduled for May 20, 2025, from 8:00 AM to 10:00 AM at the AMIA Clinical Informatics Conference, builds upon a successful workshop first introduced at AMIA CIC 2024 and subsequently delivered at numerous national conferences and grand rounds.
The workshop’s primary objective is to empower clinicians and informaticists by providing evidence-based strategies and practical, healthcare-oriented examples. Participants will gain a fundamental understanding of LLMs, including their training and fine-tuning processes, and the significant impact of prompt design on performance. The 2025 update will feature an in-depth exploration of three key techniques: few-shot learning, chain of thought, and clear communication. A major barrier to effective LLM integration in healthcare, identified as ‘the perceived lack of clinician expertise in AI and prompt engineering,’ is directly addressed by this initiative.
Also Read:
- Agentic AI Transforms Healthcare: A New Era of Autonomous Patient Care and Research
- Breakthrough Generative AI Framework Revolutionizes Medical Image Segmentation in Data-Scarce Environments
The session is led by esteemed speakers and authors Shivam Vedak, MD, MBA, and Dong-han Yao, MD, both affiliated with Stanford Medicine, underscoring the academic and practical rigor of the program.
