Enhancing ICU Patient Recovery: Using LLMs to Assist Nurses in Diary Writing

TL;DR

The paper addresses the problem that ICU patients face long-term physical, cognitive, and emotional challenges (PICS and PICS-F) and that diaries can help but are hindered by time and knowledge barriers. It proposes a vision for an LLM-assisted diary-writing tool that collaborates with nurses, detailing a phased adoption plan, future functionality, and APIs for content enrichment while emphasizing privacy and safety. A four-theme research agenda—Space and place, Technology, Design, and Social factors—outlines concrete challenges, including workload impact, model optimization, retrieval-augmented generation, and stakeholder engagement. If implemented with careful socio-technical consideration, the approach could streamline diary writing, preserve empathetic communication, and potentially improve long-term recovery outcomes for ICU patients.

Abstract

Intensive care unit (ICU) patients often develop new health-related problems in their long-term recovery. Health care professionals keeping a diary of a patient's stay is a proven strategy to tackle this but faces several adoption barriers, such as lack of time and difficulty in knowing what to write. Large language models (LLMs), with their ability to generate human-like text and adaptability, could solve these challenges. However, realizing this vision involves addressing several socio-technical and practical research challenges. This paper discusses these challenges and proposes future research directions to utilize the potential of LLMs in ICU diary writing, ultimately improving the long-term recovery outcomes for ICU patients.