Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model

TL;DR

Talk2Care investigates how large language models can facilitate asynchronous communication between home-based older adults and healthcare providers. Through two need-finding studies and two user studies, the work demonstrates that an LLM-powered voice assistant for patients and an LLM-assisted information dashboard for providers can enrich information transfer, improve usability, and reduce provider workload, without delivering medical advice. The findings highlight benefits in accessibility and efficiency, while also underscoring ethical, privacy, and deployment challenges requiring integration with EHRs, long-term memory management, and strong human oversight. Overall, this study offers a foundational step toward human–AI collaboration in healthcare communication, with design implications for scalable, privacy-conscious, AI-mediated workflows.

Abstract

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered VA interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

Figures (10)

• Figure 1: Overview of Talk2Care System. The system consists of two modules. 1) The patient module: An LLM-powered VA interface (in purple) that generates natural conversation with home-based older adults to collect health information and forward it to healthcare providers; 2) The provider module: A dashboard interface (in green) that summarizes the key information from the older patient conversation to assist providers who are responsible for communication (e.g., nurses and patient navigators). Note that Talk2Care does not provide specific healthcare advice. Our current implementation does not involve an actual electronic health record (EHR) system, which can be a promising future direction.
• Figure 2: The Component of Talk2Care System for Home-based Older Adults. The VA interface has multi-turn personalized conversations with the older adult to collect related health information. The LLM-powered Question Generation Module is responsible for taking the older adult's words and generating questions for effective information collection. The prompt design of this module is detailed in Figure \ref{['fig:prompt-design-older-adults']}. Another LLM-powered Content Loopback Module is to make sure that key information from the older adult (e.g., pain level) is accurate by double-checking the content, a common healthcare communication practice. The older adult's information, conversation protocol, and conversation log are stored in the information database.
• Figure 3: Prompt Design of High-Quality Question Generation for Health Information Collection. The input prompt consists of five parts: 1) patient information, 2) conversation protocol, 3) system setting, 4) conversation history, and 5) response optimization. For multi-turn conversation, 5) will be repeated for each round of conversation. The colored texts are parameters that can be extracted from the information database (see Figure \ref{['fig:system-older-adults']}). Note that the conversation protocol needs to be set by researchers or healthcare providers to ensure question validity. This figure shows an example of daily-care protocol.
• Figure 4: The Component of Talk2Care System for Healthcare Providers. The information dashboard summarizes and highlights key older adults' information. The main content on the dashboard is generated by three LLM-powered modules: (1) The Content Summary Module formats the conversation log and user information into a clinical note structure. (2) The Information Highlight Module color-codes the parts in the conversation log that require attention. (3) The Risk Prediction Module suggests the health risk (low, moderate, and high) based on the current conversation log. Providers can take notes or further actions on the dashboard, which are then stored in the information database.
• Figure 5: Prompt Design of Patient-VA Conversation Summary for Healthcare Providers. Similar to Figure \ref{['fig:prompt-design-older-adults']}, the input prompt consists of five parts: 1) patient information, 2) conversation protocol, 3) system setting, 4) conversation log, and 5) summary optimization. For multi-turn conversation, 5) will be repeated for each round of conversation. This figure continues the example of the protocol of daily care.