Table of Contents
Fetching ...

More than Decision Support: Exploring Patients' Longitudinal Usage of Large Language Models in Real-World Healthcare-Seeking Journeys

Yancheng Cao, Yishu Ji, Chris Yue Fu, Sahiti Dharmavaram, Meghan Turchioe, Natalie C Benda, Lena Mamykina, Yuling Sun, Xuhai "Orson" Xu

TL;DR

This paper presents a four-week diary study with 25 patients to examine LLMs'roles across healthcare-seeking trajectories and conceptualize future LLMs as a longitudinal boundary companion that continuously mediates between patients and clinicians throughout longitudinal healthcare-seeking trajectories.

Abstract

Large language models (LLMs) have been increasingly adopted to support patients' healthcare-seeking in recent years. While prior patient-centered studies have examined the capabilities and experience of LLM-based tools in specific health-related tasks such as information-seeking, diagnosis, or decision-supporting, the inherently longitudinal nature of healthcare in real-world practice has been underexplored. This paper presents a four-week diary study with 25 patients to examine LLMs' roles across healthcare-seeking trajectories. Our analysis reveals that patients integrate LLMs not just as simple decision-support tools, but as dynamic companions that scaffold their journey across behavioral, informational, emotional, and cognitive levels. Meanwhile, patients actively assign diverse socio-technical meanings to LLMs, altering the traditional dynamics of agency, trust, and power in patient-provider relationships. Drawing from these findings, we conceptualize future LLMs as a longitudinal boundary companion that continuously mediates between patients and clinicians throughout longitudinal healthcare-seeking trajectories.

More than Decision Support: Exploring Patients' Longitudinal Usage of Large Language Models in Real-World Healthcare-Seeking Journeys

TL;DR

This paper presents a four-week diary study with 25 patients to examine LLMs'roles across healthcare-seeking trajectories and conceptualize future LLMs as a longitudinal boundary companion that continuously mediates between patients and clinicians throughout longitudinal healthcare-seeking trajectories.

Abstract

Large language models (LLMs) have been increasingly adopted to support patients' healthcare-seeking in recent years. While prior patient-centered studies have examined the capabilities and experience of LLM-based tools in specific health-related tasks such as information-seeking, diagnosis, or decision-supporting, the inherently longitudinal nature of healthcare in real-world practice has been underexplored. This paper presents a four-week diary study with 25 patients to examine LLMs' roles across healthcare-seeking trajectories. Our analysis reveals that patients integrate LLMs not just as simple decision-support tools, but as dynamic companions that scaffold their journey across behavioral, informational, emotional, and cognitive levels. Meanwhile, patients actively assign diverse socio-technical meanings to LLMs, altering the traditional dynamics of agency, trust, and power in patient-provider relationships. Drawing from these findings, we conceptualize future LLMs as a longitudinal boundary companion that continuously mediates between patients and clinicians throughout longitudinal healthcare-seeking trajectories.
Paper Structure (42 sections, 1 figure, 5 tables)

This paper contains 42 sections, 1 figure, 5 tables.

Figures (1)

  • Figure 1: Overview of the LLM's four dynamic roles integrated into patients' healthcare-seeking journeys: (1) Behavioral—supporting and negotiating healthcare decisions; (2) Informational—facilitating patient–provider communication; (3) Emotional—providing emotional support and companionship; and (4) Cognitive—scaffolding patients’ sensemaking and knowledge in understanding professional healthcare information. These roles accompany patients across multiple stages of their journeys, dynamically shifting to meet patients' evolving needs. A case of a patient with eardrum perforation illustrates how LLMs enact these roles at different time points along the healthcare-seeking journey.