Large language models simplify complex medical texts for patients
Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation
Computation and Language
Summary
Medical information is often hard to understand because it uses complicated words and sentences. This paper shows how powerful language AI models can automatically rewrite medical texts into simpler language that patients can understand better. The authors test different strategies and advanced AI techniques to improve how well the models simplify text while keeping the important details. Their work demonstrates that AI can help make healthcare information more accessible to everyone.
What this means in practice
- •For health it developers: Automate simplification of medical documents to improve patient portals and health apps with easier-to-understand content.
- •For consumer health app designers: Integrate language model-based text simplification to help users better comprehend health information without specialist knowledge.$Commercial implications: Enables the creation of commercial health apps offering tailored, accessible health content to broad consumer audiences.
Authors
Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi Chen
Abstract
This paper addresses the challenge of making complex healthcare information more accessible through automated Plain Language Adaptation (PLA). PLA aims to simplify technical medical language, bridging a critical gap between the complexity of healthcare texts and patients' reading comprehension. Recent advances in Large Language Models (LLMs), such as GPT and BART, have opened new possibilities for PLA, especially in zero-shot and few-shot learning contexts where task-specific data is limited. In this work, we leverage the capabilities of LLMs such as GPT-4o-mini, Gemini-1.5-pro, and LLaMA for text simplification. Additionally, we incorporate Mixture-of-Agents (MoA) techniques to enhance adaptability and robustness in PLA tasks. Key contributions include a comparative analysis of prompting strategies, finetuning with QLoRA on different LLMs, and the integration of MoA technique. Our findings demonstrate the effectiveness of LLM-driven PLA, showcasing its potential in making healthcare information more comprehensible while preserving essential content.