Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’

The rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, and personalized health monitoring. This paper reviews the adv...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng Zhang, Jiayu Shi, Maged N. Kamel Boulos
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/16/12/462
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050284403818496
author Peng Zhang
Jiayu Shi
Maged N. Kamel Boulos
author_facet Peng Zhang
Jiayu Shi
Maged N. Kamel Boulos
author_sort Peng Zhang
collection DOAJ
description The rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, and personalized health monitoring. This paper reviews the advancements in medicine-specific LLMs, the integration of Retrieval-Augmented Generation (RAG) and prompt engineering, and their applications in improving diagnostic accuracy and educational utility. Despite the potential, these technologies present challenges, including bias, hallucinations, and the need for robust safety protocols. The paper also discusses the regulatory and ethical considerations necessary for integrating these models into mainstream healthcare. By examining current studies and developments, this paper aims to provide a comprehensive overview of the state of LLMs in medicine and highlight the future directions for research and application. The study concludes that while LLMs hold immense potential, their safe and effective integration into clinical practice requires rigorous testing, ongoing evaluation, and continuous collaboration among stakeholders.
format Article
id doaj-art-becdea0cef414770a363e42198c5be3d
institution DOAJ
issn 1999-5903
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-becdea0cef414770a363e42198c5be3d2025-08-20T02:53:30ZengMDPI AGFuture Internet1999-59032024-12-01161246210.3390/fi16120462Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’Peng Zhang0Jiayu Shi1Maged N. Kamel Boulos2Department of Computer Science and Data Science Institute, Vanderbilt University, Nashville, TN 37240, USADepartment of Computer Science and Data Science Institute, Vanderbilt University, Nashville, TN 37240, USASchool of Medicine, University of Lisbon, 1649-028 Lisbon, PortugalThe rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, and personalized health monitoring. This paper reviews the advancements in medicine-specific LLMs, the integration of Retrieval-Augmented Generation (RAG) and prompt engineering, and their applications in improving diagnostic accuracy and educational utility. Despite the potential, these technologies present challenges, including bias, hallucinations, and the need for robust safety protocols. The paper also discusses the regulatory and ethical considerations necessary for integrating these models into mainstream healthcare. By examining current studies and developments, this paper aims to provide a comprehensive overview of the state of LLMs in medicine and highlight the future directions for research and application. The study concludes that while LLMs hold immense potential, their safe and effective integration into clinical practice requires rigorous testing, ongoing evaluation, and continuous collaboration among stakeholders.https://www.mdpi.com/1999-5903/16/12/462generative AIlarge language modelsAI chatbotsChatGPTartificial intelligenceretrieval-augmented generation
spellingShingle Peng Zhang
Jiayu Shi
Maged N. Kamel Boulos
Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
Future Internet
generative AI
large language models
AI chatbots
ChatGPT
artificial intelligence
retrieval-augmented generation
title Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
title_full Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
title_fullStr Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
title_full_unstemmed Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
title_short Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’
title_sort generative ai in medicine and healthcare moving beyond the peak of inflated expectations
topic generative AI
large language models
AI chatbots
ChatGPT
artificial intelligence
retrieval-augmented generation
url https://www.mdpi.com/1999-5903/16/12/462
work_keys_str_mv AT pengzhang generativeaiinmedicineandhealthcaremovingbeyondthepeakofinflatedexpectations
AT jiayushi generativeaiinmedicineandhealthcaremovingbeyondthepeakofinflatedexpectations
AT magednkamelboulos generativeaiinmedicineandhealthcaremovingbeyondthepeakofinflatedexpectations