Applications of large language model in general practice: a qualitative interview study with professionals and patients
- 1University Medical Center Rotterdam
Abstract
Background: Workload is increasing in general practice. Large language models (LLMs) are a promising tool that could relieve part of this workload. However, existing studies offer little insight into how professionals and patients want specific LLM applications to be implemented in practice. Objectives: This study aimed to prioritize a broad range of LLM applications in general practice and identify the benefits, risks, and requirements of each application. Methods: We conducted semi-structured one-on-one interviews with 12 general practitioners (GPs), 7 GP assistants, 6 practice nurses, and 6 patient representatives in the Netherlands between October and December 2025. To guide the interviews, we developed a list of 21 LLM applications derived from literature, existing tools, and GP input. Application were divided into 5 categories: administrative tasks, pre-consultation and triage, clinical decision support, management of (chronic) diseases, and patient interaction and communication. Participants discussed and prioritized each application. Transcripts were analyzed with a combined deductive and inductive approach. Results: Priorities for LLM applications differed by group: GPs favored clinical decision support, assistants favored triage, and practice nurses and patient representatives favored chronic disease management. The most prioritized applications were summarizing consultations and triage and urgency classification (high priority 18/31; 58%), followed by clarification of medical information around the consultation (14/31; 45%). The qualitative analysis revealed three recurring considerations when applying LLMs for different tasks. First, participants questioned whether an LLM is needed, as simpler or existing tools may suffice. Second, they questioned whether LLMs relieve workload or create extra work. Third, a possible benefit on workload has to explicitly be weighed against risks such as mistakes, reduced personal care and accessibility, and negative effects on professionals. Conclusions: Professionals and patients see potential for LLM support across many areas of general practice. Realizing this potential requires three steps: critically assessing whether an LLM is the right tool, establishing that it relieves workload, and designing applications so that their benefits outweigh the risks. Our application-level prioritization and analysis provide a starting point for assessment and design.
Related
- Healthcare professionals’ experiences of providing care for patients with Graves’ disease: a qualitative interview study in Swedish secondary care
- Adolescent well-being in the context of the polycrisis, through the lens of school social workers’ practice in Finland - a qualitative interview study
- Emotional meanings of clinical practice with head and neck cancer patients: a qualitative study with Brazilian professionals.
- Language, perceived discrimination and barriers to complaint use: sub-Saharan African immigrants' healthcare experiences in Oslo, a qualitative interview study
- Navigating result disclosure in the context of reproductive genetic carrier screening: an interview study of genetic healthcare professionals in Belgium
BibTeX
@misc{heerdt2026applications,
title = {{Applications of large language model in general practice: a qualitative interview study with professionals and patients}},
author = {Y. ter Heerdt and E. Bischoff and J. Yang and M. Timmers and J. Jung and R. van Linschoten},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.30.26366911},
url = {https://www.medrxiv.org/content/10.64898/2026.10.30.26366911v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Applications of large language model in general practice: a qualitative interview study with professionals and patients
AU - Y. ter Heerdt
AU - E. Bischoff
AU - J. Yang
AU - M. Timmers
AU - J. Jung
AU - R. van Linschoten
PY - 2026
DA - 2026/10/30
PB - medRxiv
DO - 10.64898/2026.10.30.26366911
UR - https://www.medrxiv.org/content/10.64898/2026.10.30.26366911v1
AB - Background: Workload is increasing in general practice. Large language models (LLMs) are a promising tool that could relieve part of this workload. However, existing studies offer little insight into how professionals and patients want specific LLM applications to be implemented in practice. Objectives: This study aimed to prioritize a broad range of LLM applications in general practice and identify the benefits, risks, and requirements of each application. Methods: We conducted semi-structured one-on-one interviews with 12 general practitioners (GPs), 7 GP assistants, 6 practice nurses, and 6 patient representatives in the Netherlands between October and December 2025. To guide the interviews, we developed a list of 21 LLM applications derived from literature, existing tools, and GP input. Application were divided into 5 categories: administrative tasks, pre-consultation and triage, clinical decision support, management of (chronic) diseases, and patient interaction and communication. Participants discussed and prioritized each application. Transcripts were analyzed with a combined deductive and inductive approach. Results: Priorities for LLM applications differed by group: GPs favored clinical decision support, assistants favored triage, and practice nurses and patient representatives favored chronic disease management. The most prioritized applications were summarizing consultations and triage and urgency classification (high priority 18/31; 58%), followed by clarification of medical information around the consultation (14/31; 45%). The qualitative analysis revealed three recurring considerations when applying LLMs for different tasks. First, participants questioned whether an LLM is needed, as simpler or existing tools may suffice. Second, they questioned whether LLMs relieve workload or create extra work. Third, a possible benefit on workload has to explicitly be weighed against risks such as mistakes, reduced personal care and accessibility, and negative effects on professionals. Conclusions: Professionals and patients see potential for LLM support across many areas of general practice. Realizing this potential requires three steps: critically assessing whether an LLM is the right tool, establishing that it relieves workload, and designing applications so that their benefits outweigh the risks. Our application-level prioritization and analysis provide a starting point for assessment and design.
ER -