Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Jan 17, 2026
Date Accepted: Jun 1, 2026

The final, peer-reviewed published version of this preprint can be found here:

Exploring the Role of Large Language Models in Primary Care: Qualitative Study of Physicians in the United States and the Netherlands

Super I, Bawa H, Asan O

Exploring the Role of Large Language Models in Primary Care: Qualitative Study of Physicians in the United States and the Netherlands

JMIR Med Inform 2026;14:e91652

DOI: 10.2196/91652

PMID: 42430718

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

AI at the Frontline: Primary Care Physicians’ Use of Large Language Models for Clinical Support, Collaboration, and Patient Engagement

  • Ilse Super; 
  • Harinder Bawa; 
  • Onur Asan

ABSTRACT

Background:

Primary care is becoming increasingly complex, with primary care physicians (PCPs) facing rising workloads driven by workforce shortages, growing administrative demands, and expanding clinical responsibilities. These pressures have been associated with increased stress and risk of burnout among PCPs, potentially threatening the sustainability and quality of primary care delivery. Recent advances in large language models (LLMs) offer new opportunities to support PCPs across clinical, administrative, and communication-related tasks within their workflows. Understanding how these technologies are perceived and used in primary care practice is therefore critical to inform their safe, effective, and human-centered implementation.

Objective:

The objective of this study is to explore primary care physicians’ perceptions and experiences regarding the use of LLMs in clinical practice, with particular attention to clinical usability, communication and teamwork, and implications for everyday workflows.

Methods:

We conducted a qualitative study using semi-structured interviews with 15 primary care physicians from the United States and the Netherlands. Data were collected between February and June 2025 and analyzed using inductive thematic analysis. Thematic analysis was performed iteratively, with themes developed through affinity diagramming, team-based coding, regular reflexive discussions with an experienced advisor, and a practicing primary care physician.

Results:

From our thematic analysis, we identified three overarching categories: (1) Clinical work support, (2) Teamwork and communication, and (3) Risks and concerns. In total, these categories encompass ten emerging themes related to the use of LLMs in primary care clinical practice. Each theme consists of a set of subthemes.

Conclusions:

LLMs are being integrated into primary care as both clinical and communication support tools, assisting with diagnostic reasoning, administrative tasks, workload management, and interprofessional and patient communication. While PCPs reported perceived benefits, they also expressed concerns about safety, efficiency, authenticity, and the preservation of the therapeutic relationship, highlighting the need for careful, context-sensitive use. Understanding how clinicians navigate these trade-offs in everyday practice is essential to ensure that LLMs support high-quality, patient-centered primary care and inform organizational policy and LLM design.


 Citation

Please cite as:

Super I, Bawa H, Asan O

Exploring the Role of Large Language Models in Primary Care: Qualitative Study of Physicians in the United States and the Netherlands

JMIR Med Inform 2026;14:e91652

DOI: 10.2196/91652

PMID: 42430718

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.