Page 7 - AIH-2-2

Artificial Intelligence in Health

REVIEW ARTICLE
Role of large language models in improving

provider–patient experience and interaction
efficiency: A scoping review

1†
2†
Aditya B. Vishwanath , Vijay Kumar Srinivasalu , and
3
Narayana Subramaniam *
1 Ramaiah Medical College, Bengaluru, Karnataka, India
2 Department of Medical Oncology, Sparsh Hospital, Yelahanka, Bengaluru, Karnataka, India
3 Department of Head and Neck Surgery and Oncology, Sparsh Hospital, Yelahanka, Bengaluru,
Karnataka, India

Abstract

Large language models (LLMs) have rapidly emerged as transformative tools
across multiple domains, including healthcare. The ability of LLMs to process
vast amounts of data and generate human-like responses has facilitated their
† These authors contributed equally
to this work. integration into patient care, particularly in enhancing communication, improving
patient satisfaction, and streamlining administrative processes. Despite this
*Corresponding author:
Narayana Subramaniam potential, there are concerns regarding their accuracy, reliability, and ethical use
(narayana.subramaniam@gmail. in clinical settings. This scoping review aims to investigate and map the current
com) literature on the use of LLMs in improving provider–patient experience and
Citation: Vishwanath AB, interaction efficiency. Following the Preferred Reporting Items for Systematic
Srinivasalu VK, Subramaniam N. Reviews and Meta-Analyses extension for Scoping Reviews guidelines, we
Role of large language models
in improving provider–patient conducted a systematic search of Ovid MEDLINE, PubMed, and Google Scholar
experience and interaction databases to identify relevant articles published between January 2015 and June
efficiency: A scoping review. 2024. Of the 3568 articles initially screened, 47 satisfied the inclusion criteria.
Artif Intell Health. 2025;2(2):1-10.
doi: 10.36922/aih.4808 These articles spanned 13 countries and encompassed diverse healthcare settings.
Thematic areas of LLM utilization included improving communication between
Received: September 10, 2024 patients and healthcare providers, resolving patient inquiries, enhancing patient
Revised: October 25, 2024 education, and increasing operational efficiency. Although numerous studies
Accepted: November 11, 2024 have yielded positive outcomes, significant challenges related to data accuracy,
hallucinations, bias, and ethical concerns remain. LLMs can considerably improve
Published online: December 12, 2024 patient experience in healthcare, particularly in areas of communication,
Copyright: © 2024 Author(s). education, and administrative efficiency. However, concerns regarding
This is an Open-Access article accuracy, ethical implications, and the need for rigorous safeguards to prevent
distributed under the terms of the
Creative Commons Attribution misinformation impede their widespread adoption. Future research should focus
License, permitting distribution, on developing context-specific LLMs tailored to healthcare environments and
and reproduction in any medium, addressing the identified limitations to optimize their implementation in clinical
provided the original work is
properly cited. practice.
Publisher’s Note: AccScience
Publishing remains neutral with Keywords: Large language models; Patient experience; Artificial intelligence; Healthcare;
regard to jurisdictional claims in
published maps and institutional Communication; Patient satisfaction; Patient interaction
affiliations.

Volume 2 Issue 2 (2025) 1 doi: 10.36922/aih.4808