Enhancing Nursing and Elderly Care with Large Language Models: An AI-Driven Framework

TL;DR

This work investigates the use of large language models (LLMs) to enhance nursing and elderly care through AI-driven patient monitoring and interaction. It introduces NursingPiles, a multilayer Chinese nursing dataset, and proposes Incremental Pretraining (IPT) plus Supervised Fine-Tuning (SFT) with Parameter-Efficient Fine-Tuning (PEFT) to adapt GLM4-Chat 9B and LLaMA 3.1 for domain-specific tasks, including a LangChain-based dynamic nursing assistant with multimodal capabilities. Benchmarking on nursing-exam style questions demonstrates significant performance gains from IPT+SFT, with GLM4+IPT+SFT achieving the top results, and ablations confirming both components are critical. The work also addresses practical deployment considerations, such as secure data handling, real-time monitoring, and ethical governance, highlighting the potential of AI-driven nursing tools to alleviate workforce pressures while acknowledging current limitations and the need for broader multimodal integration.

Abstract

This paper explores the application of large language models (LLMs) in nursing and elderly care, focusing on AI-driven patient monitoring and interaction. We introduce a novel Chinese nursing dataset and implement incremental pre-training (IPT) and supervised fine-tuning (SFT) techniques to enhance LLM performance in specialized tasks. Using LangChain, we develop a dynamic nursing assistant capable of real-time care and personalized interventions. Experimental results demonstrate significant improvements, paving the way for AI-driven solutions to meet the growing demands of healthcare in aging populations.