EUVIMEDEUVIMED entdecken
Systematische ÜbersichtMetaanalyseOpen Access

Impact of Large Language Model–Based AI Tools on Physician-Patient Communication: Systematic Review and Meta-Analysis

Sven Richter, Clara Helene Buszello, Markus Prem, Sophia Willkommen, Elida Hasani, Ortrud Uckermann, Tareq A Juratli, Ilker Y Eyüpoglu, Witold H Polanski

Journal of Medical Internet Research · 31.07.2026 · 28 · e77307-e77307

DOI: 10.2196/77307 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 31.07.2026. Verfasst von Sven Richter und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, Medical Faculty and University Hospital Carl Gustav Carus, Technische Universität Dresden, Fetscherstrasse 74, Dresden, 0…. Hauptthemen laut MEDLINE: Physician-Patient Relations, Artificial Intelligence, Communication. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Recent advances in large language models (LLMs) such as GPT-3/4 have spurred the development of artificial intelligence (AI) chatbots and advisory tools in medicine. These systems are posited to assist or augment physician-patient communication, potentially improving empathy, clarity, and responsiveness. However, their actual impact on communication outcomes remains uncertain.

Objective

This study aimed to systematically review and meta-analyze peer-reviewed studies (2020‐2025) evaluating how LLM-based interventions affect physician-patient communication, including empathy, clarity, trust, and patient understanding.

Methods

Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines, we searched PubMed/MEDLINE, Embase, Scopus, and Web of Science for studies published from 2020 to 2025 examining LLM or chatbot applications in clinical communication contexts. Eligible designs included randomized, observational, cross-sectional, and qualitative studies. Two reviewers (WHP and SR) independently screened titles or abstracts, assessed full texts, and extracted data on study design, population, LLM type, communication measures, and outcomes. We conducted a qualitative synthesis and random-effects meta-analysis, reporting pooled standardized mean differences or odds ratios with 95% CIs.

Results

From 312 records, 10 studies were included, all quantitative and predominantly cross-sectional. Populations ranged from patients with chronic conditions to health care professionals and laypersons. Outcomes assessed included empathy (8 studies), clarity or information quality (6 studies), satisfaction or usefulness (4 studies), and trust perceptions (2 studies). In 6 direct comparisons of AI- versus physician-generated responses, LLMs were rated significantly higher in empathy in 5 studies. One large study found that chatbot replies were judged empathetic in 45.1% of cases versus 4.6% for physician replies (odds ratio approximately 9.8, P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Physician-Patient RelationsArtificial IntelligenceCommunicationHumansLarge Language ModelsEmpathyGenerative Artificial Intelligence

Stichwörter der Autor:innen

ChatGPTLLMsartificial intelligence in health careempathylarge language modelsphysician-patient communication

Autor:innen und Institutionen

  • Department of Neurosurgery, Medical Faculty and University Hospital Carl Gustav Carus, Technische Universität Dresden, Fetscherstrasse 74, Dresden, 01307, Germany, 49 3514582883.
  • Else Kröner Fresenius Center for Digital Health, Medical Faculty and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.

Zitieren

APA

Richter, S., Buszello, C. H., Prem, M., Willkommen, S., Hasani, E., Uckermann, O., Juratli, T. A., Eyüpoglu, I. Y., & Polanski, W. H. (2026). Impact of Large Language Model–Based AI Tools on Physician-Patient Communication: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e77307-e77307. https://doi.org/10.2196/77307

Vancouver

Richter S, Buszello CH, Prem M, Willkommen S, Hasani E, Uckermann O, et al. Impact of Large Language Model–Based AI Tools on Physician-Patient Communication: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e77307-e77307. doi:10.2196/77307

BibTeX
@article{Richter2026,
  author = {Richter, Sven and Buszello, Clara Helene and Prem, Markus and Willkommen, Sophia and Hasani, Elida and Uckermann, Ortrud and Juratli, Tareq A and Eyüpoglu, Ilker Y and Polanski, Witold H},
  title = {Impact of Large Language Model–Based AI Tools on Physician-Patient Communication: Systematic Review and Meta-Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e77307--e77307},
  doi = {10.2196/77307}
}
Kostenlos starten →