Generative artificial intelligence and prompt engineering in asthma-related settings

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare

Background:

• Generative artificial intelligence (AI) and large language models (LLMs) are increasingly utilized in medical practice.
• These AI systems can synthesize clinical information, streamline workflows, and summarize documentation.

Purpose of the Study:

• To explore the application of AI, particularly LLMs, in asthma and allergy care.
• To explain the principles and importance of prompt engineering for optimizing LLM outputs in clinical settings.

Main Methods:

• The study reviews the capabilities of LLMs in analyzing patient data and supporting clinical decisions.
• It details prompt engineering strategies, including defining roles, tasks, context, and output formats.
• Different prompting techniques like open-ended, focused, chained, and choice-based prompts are discussed.

Main Results:

• AI systems can analyze patient data, aid clinical decision-making, and enhance access to educational resources in asthma care.
• Effective prompt engineering guides LLMs to generate accurate and clinically relevant outputs.
• Structured prompts can support summarizing encounters, creating patient materials, and clinical reasoning.

Conclusions:

• Understanding prompt design principles is crucial for clinicians using LLMs in asthma and allergy practice.
• Appropriate prompt selection enhances the precision and clinical relevance of AI-generated information.
• Prompt engineering empowers clinicians to leverage AI for improved patient care and workflow efficiency.