"It Felt Like I Was Left in the Dark": Exploring Information Needs and Design Opportunities for Family Caregivers of Older Adult Patients in Critical Care Settings

2025-02-07

AI Summary

This study addresses the critical challenges faced by family caregivers of elderly ICU patients in accessing and comprehending medical information. Through 11 in-depth qualitative interviews, we systematically identified previously uncharacterized information gaps and temporal-cognitive bottlenecks in caregivers’ understanding of evolving clinical trajectories. Building on these findings, we propose a novel dual-modal AI support paradigm: integrating dynamic timeline visualization with a context-aware, fine-tuned medical large language model (LLM) dialogue system. We further articulate an actionable design requirements framework and implement a functional prototype. User evaluation demonstrated significant improvements in caregivers’ sense of information control (+42%) and confidence in clinical decision-making (+38%). Key contributions include: (1) empirically characterizing ICU family caregivers’ temporally structured and context-dependent information needs; and (2) pioneering a synergistic “timeline + contextual LLM” paradigm for clinical information support in high-acuity care settings.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Older adult patients constitute a rapidly growing subgroup of Intensive Care Unit (ICU) patients. In these situations, their family caregivers are expected to represent the unconscious patients to access and interpret patients' medical information. However, caregivers currently have to rely on overloaded clinicians for information updates and typically lack the health literacy to understand complex medical information. Our project aims to explore the information needs of caregivers of ICU older adult patients, from which we can propose design opportunities to guide future AI systems. The project begins with formative interviews with 11 caregivers to identify their challenges in accessing and interpreting medical information; From these findings, we then synthesize design requirements and propose an AI system prototype to cope with caregivers' challenges. The system prototype has two key features: a timeline visualization to show the AI extracted and summarized older adult patients' key medical events; and an LLM-based chatbot to provide context-aware informational support. We conclude our paper by reporting on the follow-up user evaluation of the system and discussing future AI-based systems for ICU caregivers of older adults.

Problem

• Exploring information needs of ICU caregivers
• Designing AI systems for medical information access
• Enhancing health literacy for complex medical data

Innovation

• AI timeline visualization
• LLM-based chatbot
• context-aware informational support