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

TL;DR

This study explores how patients use large language models over four weeks during real-world healthcare journeys, revealing they serve as dynamic companions influencing trust and decision-making.

Contribution

It provides the first longitudinal analysis of patient interactions with LLMs in healthcare, highlighting their evolving roles beyond simple decision support.

Findings

Patients use LLMs as emotional and informational companions.

Patients assign diverse meanings to LLMs, affecting trust and agency.

LLMs act as boundary companions mediating patient-clinician interactions.

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.