PMC is a free full-text archive of biomedical and life sciences journal literature at the U.S. National Institutes of Health's National Library of Medicine (NIH/NLM).

YouTube video by Creative Commons

Journal of Negative Results in Biomedicine (JNRBM) will cease to be published by BioMed Central as of 1stSeptember 2017. BioMed Central will continue to host ...

Large language models (LLMs) are increasingly deployed for clinical decision support, yet standard evaluations such as medical licensing exams overlook how clinicians update decisions in dynamic co...

This study compared language models’ responses to open-ended questions on regenerative therapy guidelines for chronic pain, assessing their accuracy, reliability, usefulness, readability, semantic similarity, and hallucination rates. This cross-sectional study used 16 open-ended questions based on the American Society of Pain and Neuroscience’s regenerative therapy guidelines for chronic pain. Questions were answered by ChatGPT-4o, Gemini 2.5 Flash, and Claude 4 Opus. Responses were rated on a 7-point Likert scale for usability and reliability, and a 5-point scale for accuracy. Hallucinogenicity, readability (FKRE, FKGL), and similarity (USE, ROUGE-L) were also assessed. Statistical comparisons were made, with significance set at p < 0.05. Claude Opus 4 showed the highest reliability (5.19 ± 1.11), usefulness (5.06 ± 1.0), and clinical accuracy (4.06 ± 0.68), outperforming ChatGPT-4o (4.13 ± 0.96; 3.94 ± 0.85; 3.38 ± 0.72) and Gemini 2.5 (4.19 ± 0.98; 4.06 ± 0.93; 3.38 ± 0.62). Claude had the lowest reference hallucinations (RHS 4.44 ± 3.18) vs. ChatGPT-4o (8.38 ± 1.86) and Gemini 2.5 (8.75 ± 1.73). In semantic similarity, Claude (0.68 ± 0.08) and Gemini (0.65 ± 0.07) surpassed ChatGPT-4o (0.60 ± 0.09). Gemini led in ROUGE-L F1 (0.12 ± 0.03) vs. Claude (0.10 ± 0.02) and ChatGPT-4o (0.07 ± 0.03). Readability was similar, though Gemini had a higher FKGL (11.3 ± 1.06) than Claude (10.3 ± 2.09). Claude Opus 4 showed superior accuracy, reliability, and usefulness, with significantly fewer hallucinations. Readability scores were similar across models. Further research is recommended.

This JAMA Insights provides evidence-based recommendations for communicating numerical information to patients.

Large language models (LLMs) are playing an increasingly integral, though largely informal, role in scholarly peer review. Yet it remains unclear whether LLMs reproduce the biases observed in human de...

Patient and family advisory councils (PFACs) serve as structured collaborative groups where patients and caregivers partner with healthcare professionals to sha...

Experts find fake sources in Canadian government report that took 18 months to complete.

Reminder: check to see if OpenAI, Meta, and others used your published work illegally to train their LLMs. https://www.theatlantic.com/technology/archive/2025/03/search-libgen-data-set/682094/ If yo...

Anthropic’s new data policy raises legal concerns with its use of questionable dark patterns.

We retracted a story in May. Here’s what happened.

1. INTRODUCTION Imaging findings should be interpreted within the broader context of an individual's shoulder symptoms (1). While imaging is valuable in ...

The importance of skeletal muscle mass is increasingly being recognised in the medical field.1 The crucial roles of skeletal muscle have come to the forefront of public attention due to data on the us...

Synopsis. Social media has become widely used by the scientific community for a variety of professional uses, including networking and public outreach. For

Although 10 000 steps per day can still be a viable target for those who are more active, 7000 steps per day is associated with clinically meaningful improvements in health outcomes and might be a mor...

Background Initiatives are increasingly encouraging health and social care staff involvement in research, with evidence for patient and organisational level benefits. There is less evidence of the ben...

Many-author non-empirical papers include recommendations or consensus statements, catalogs of ideas, roadmaps for future research, calls to action, or “how to” articles. These papers have great potent...

By analysing the smartphone data of 2,112,288 participants, in particular observing and comparing the activity of the same individual in two different environments, we find that increases in the walka...

Study finds the chatbot doesn’t acknowledge concerns with problematic studies

Spreadsheet software can be frustrating, but adopting some helpful habits can improve its effectiveness.

Shen et al. show that pre-existing neural similarity in strangers predicts future friendship and changes in social distance over time in an emerging social network of MBA students.