Large language models: what are they and how can the clinician use them?

Clicks: 18
ID: 331577
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #160 of 228 articles by views in clinical kidney journal

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 228 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Abstract Background: Large Language Models (LLMs) such as ChatGPT represent the latest advancements in natural language processing and artificial intelligence. These models are increasingly being explored for applications in medicine and healthcare, including nephrology. Objectives: To provide an accessible introduction to LLMs, explain their underlying concepts, discuss their challenges and limitations in medical applications, highlight opportunities for their use in medicine and nephrology, and offer perspectives for future research. Methods: This article synthesizes recent literature on LLMs in medicine with examples in nephrology. It also reviews key concepts such as word embeddings, the Transformer architecture, and the pretrain-then-finetune paradigm. Moreover, the article discusses the differences between standard pretrained language models and LLMs Results: LLMs have demonstrated potential in various clinical tasks, including patient triaging, phenotyping, and report generation. In nephrology, LLMs have been used for triaging patient communications, answering exam questions, and informing patients about chronic kidney disease and transplantation. However, challenges remain, such as privacy, the generation of false information (hallucinations), data and model bias, reproducibility and language coverage. Opportunities include making health information more accessible for patients, reducing administrative burdens for healthcare workers, and tackling complex clinical tasks with multi-agent systems. Conclusions: LLMs offer transformative potential in medicine, but their deployment must address issues of hallucination, bias, privacy, the environment, and more. Integrating complementary technologies and rigorous evaluation is essential for safe and effective use. Collaboration among AI researchers, clinicians, and policymakers is crucial to maximize benefits and minimize risks, ensuring transparency, accountability, and inclusivity in LLM development.
Reference Key
openalex_W7220723343 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Iacer Calixto, Carmine Zoccali, Giovanni Luigi Tripepi, Merel van Diepen, Roemer J. Janse, Friedo Wilhelm Dekker, Kitty J. Jager, Vianda S Stel, Ameen Abu–Hanna
Are you one of these authors? Claim your profile
Journal clinical kidney journal
Year 2026
DOI
10.1093/ckj/sfag353
URL
https://doi.org/10.1093/ckj/sfag353
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.