Search Articles

View query in Help articles search

Search Results (1 to 10 of 52 Results)

Download search results: CSV END BibTex RIS


Exploring the Dilemma of AI Use in Medical Research and Knowledge Synthesis: A Perspective on Deep Research Tools

Exploring the Dilemma of AI Use in Medical Research and Knowledge Synthesis: A Perspective on Deep Research Tools

In particular, large language models (LLMs) have caught the popular imagination, because unlike advanced machine learning or natural language processing (NLP) tools, proprietary LLMs such as Chat GPT do not require technical knowledge - their user-friendly interfaces and capacity for accepting plain language as inputs democratizing access to the AI revolution for the average person.

Ariel Yuhan Ong, David A Merle, Siegfried K Wagner, Pearse A Keane

J Med Internet Res 2025;27:e75666

Using Large Language Models to Assess Burnout Among Health Care Workers in the Context of COVID-19 Vaccine Decisions and Health Beliefs: Retrospective Cohort Study

Using Large Language Models to Assess Burnout Among Health Care Workers in the Context of COVID-19 Vaccine Decisions and Health Beliefs: Retrospective Cohort Study

To address this, this study applies large language models (LLMs), which excel at interpreting nuanced, unstructured textual data. Unlike traditional machine learning models—which require extensive feature engineering and often miss deeper linguistic or conceptual structures—LLMs can process entire sentences or paragraphs as coherent units, capturing context, tone, and latent psychological meaning [12].

Samaneh Omranian, Lu He, AkkeNeel Talsma, Arielle A J Scoglio, Susan McRoy, Janet W Rich-Edwards

JMIR Nursing 2025;8:e73672

Enhancing Diagnostic Accuracy of Ophthalmological Conditions With Complex Prompts in GPT-4: Comparative Analysis of Global and Low- and Middle-Income Country (LMIC)–Specific Pathologies

Enhancing Diagnostic Accuracy of Ophthalmological Conditions With Complex Prompts in GPT-4: Comparative Analysis of Global and Low- and Middle-Income Country (LMIC)–Specific Pathologies

One low-cost potential solution that could assist health care workers in lower income countries is online clinical assistants powered by artificial intelligence (AI) large language models (LLMs). These clinical assistants could help clinicians to triage patients and identify the causes of their conditions in settings where secondary or tertiary specialist care is unavailable. The advent of chatbots and AI within the field of medicine is not a new occurrence.

Shona Alex Tapiwa M'gadzah, Andrew O'Malley

JMIR Form Res 2025;9:e64986

Author’s Reply: Large Language Models Could Revolutionize Health Care, but Technical Hurdles May Limit Their Applications

Author’s Reply: Large Language Models Could Revolutionize Health Care, but Technical Hurdles May Limit Their Applications

We appreciate the their thoughtful input, which strengthens our discussion on the role of large language models (LLMs) in health care. Our article aimed to provide a forward-looking perspective on LLMs’ potential in medicine, prioritizing conceptual insights over granular technical details. The reviewers’ points regarding multimodal data integration, image analysis, and resource allocation align with emerging research and underscore LLMs’ transformative capabilities.

Jiaming Ji, Xiangbin Meng, Xiangyu Yan

J Med Internet Res 2025;27:e73144

Large Language Models Could Revolutionize Health Care, but Technical Hurdles May Limit Their Applications

Large Language Models Could Revolutionize Health Care, but Technical Hurdles May Limit Their Applications

The authors synthesized all the possible applications of large language models (LLMs) very well, not only detailing applications related to clinical medicine, but also offering some examples of LLMs’ potential in a broader hospital environment and in public health policies.

Diva Beltramin, Cédric Bousquet, Théophile Tiffet

J Med Internet Res 2025;27:e71618

AI-Powered Drug Classification and Indication Mapping for Pharmacoepidemiologic Studies: Prompt Development and Validation

AI-Powered Drug Classification and Indication Mapping for Pharmacoepidemiologic Studies: Prompt Development and Validation

It is positioned to benefit from advances in an even wider array of disciplines, including bioinformatics, data science, machine learning, artificial intelligence (AI), natural language processing, large language models (LLMs), systems pharmacology, pharmacogenomics, pharmacometabolomics, and health informatics [2-7].

Benjamin Ogorek, Thomas Rhoads, Eric Finkelman, Isaac R Rodriguez-Chavez

JMIR AI 2025;4:e65481

Comparison of ChatGPT and Internet Research for Clinical Research and Decision-Making in Occupational Medicine: Randomized Controlled Trial

Comparison of ChatGPT and Internet Research for Clinical Research and Decision-Making in Occupational Medicine: Randomized Controlled Trial

The recent rapid innovation of large language models (LLMs) has led to the emergence of Chat GPT, which is the first LLM to provide the data basis and performance to support or carry out medical research and clinical decisions. Nevertheless, the clinical application is currently viewed with a degree of skepticism, as Chat GPT, especially in the earlier versions 2 and 3, demonstrated a marked tendency to “confabulate,” to fabricate statements and even references [2].

Felix A Weuthen, Nelly Otte, Hanif Krabbe, Thomas Kraus, Julia Krabbe

JMIR Form Res 2025;9:e63857

Comparing Artificial Intelligence–Generated and Clinician-Created Personalized Self-Management Guidance for Patients With Knee Osteoarthritis: Blinded Observational Study

Comparing Artificial Intelligence–Generated and Clinician-Created Personalized Self-Management Guidance for Patients With Knee Osteoarthritis: Blinded Observational Study

In recent years, large language models (LLMs) based on transformer architectures, such as Chat GPT (Open AI), Gemini (Google Deep Mind), and Claude (Anthropic), have emerged as promising tools in the medical domain [13].

Kai Du, Ao Li, Qi-Heng Zuo, Chen-Yu Zhang, Ren Guo, Ping Chen, Wei-Shuai Du, Shu-Ming Li

J Med Internet Res 2025;27:e67830