Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
The advent of Deep Learning (DL) has significantly propelled the field of diagnostic radiology forward by enhancing image analysis and interpretation. The introduction of the Transformer architecture, followed by the development of Large Language Models (LLMs), has further revolutionized this domain. LLMs now possess the potential to automate and refine the radiology workflow, extending from report generation to assistance in diagnostics and patient care. The integration of multimodal technology with LLMs could potentially leapfrog these applications to unprecedented levels.However, LLMs come with unresolved challenges such as information hallucinations and biases, which can affect clinical reliability. Despite these issues, the legislative and guideline frameworks have yet to catch up with technological advancements. Radiologists must acquire a thorough understanding of these technologies to leverage LLMs' potential to the fullest while maintaining medical safety and ethics. This review aims to aid in that endeavor.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11217134 | PMC |
| http://dx.doi.org/10.1007/s11604-024-01552-0 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Applications of Federated Large Language Model for Adverse Drug Reactions Prediction: Scoping Review.
J Med Internet Res
September 2025
Department of Information Systems and Cybersecurity, The University of Texas at San Antonio, 1 UTSA Circle, San Antonio, TX, 78249, United States, 1 (210) 458-6300.
Background: Adverse drug reactions (ADR) present significant challenges in health care, where early prevention is vital for effective treatment and patient safety. Traditional supervised learning methods struggle to address heterogeneous health care data due to their unstructured nature, regulatory constraints, and restricted access to sensitive personal identifiable information.
Objective: This review aims to explore the potential of federated learning (FL) combined with natural language processing and large language models (LLMs) to enhance ADR prediction.
Automated Literature Screening for Hepatocellular Carcinoma Treatment Through Integration of 3 Large Language Models: Methodological Study.
JMIR Med Inform
September 2025
Department of Hepatobiliary and Vascular Surgery, First Affiliated Hospital of Chengdu Medical College, Chengdu, China.
Background: Primary liver cancer, particularly hepatocellular carcinoma (HCC), poses significant clinical challenges due to late-stage diagnosis, tumor heterogeneity, and rapidly evolving therapeutic strategies. While systematic reviews and meta-analyses are essential for updating clinical guidelines, their labor-intensive nature limits timely evidence synthesis.
Objective: This study proposes an automated literature screening workflow powered by large language models (LLMs) to accelerate evidence synthesis for HCC treatment guidelines.
The Contribution of Language Ability and Linguistic Factors to Disfluency in Bilingual Children.
J Speech Lang Hear Res
September 2025
Department of Communication Sciences and Disorders, University of Wisconsin-Madison.
Purpose: Speech disfluencies are common in individuals who do not stutter, with estimates suggesting a typical rate of six per 100 words. Factors such as language ability, processing load, planning difficulty, and communication strategy influence disfluency. Recent work has indicated that bilinguals may produce more disfluencies than monolinguals, but the factors underlying disfluency in bilingual children are poorly understood.
View Article and Find Full Text PDFDiversity on the bench: An analysis of gendered biases in the language of Australian Family Law Court judgments.
PLoS One
September 2025
School of Law, Society and Criminology, UNSW, Sydney, New South Wales, Australia.
In this paper we analyse gender-based biases in the language within complex legal judgments. Our aims are: (i) to determine the extent to which purported biases discussed in the literature by feminist legal scholars are identifiable from the language of legal judgments themselves, and (ii) to uncover new forms of bias represented in the data that may promote further analysis and interpretation of the functioning of the legal system. We consider a large set of 2530 judgments in family law in Australia over a 20 year period, examining the way that male and female parties to a case are spoken to and about, by male and female judges, in relation to their capacity to provide care for children subject to the decision.
View Article and Find Full Text PDFEvaluating anti-LGBTQIA+ medical bias in large language models.
PLOS Digit Health
September 2025
Department of Dermatology, Stanford University, Stanford, California, United States of America.
Large Language Models (LLMs) are increasingly deployed in clinical settings for tasks ranging from patient communication to decision support. While these models demonstrate race-based and binary gender biases, anti-LGBTQIA+ bias remains understudied despite documented healthcare disparities affecting these populations. In this work, we evaluated the potential of LLMs to propagate anti-LGBTQIA+ medical bias and misinformation.
View Article and Find Full Text PDF