An autonomous agentic workflow for clinical detection of cognitive concerns using large language models. [PDF]
Tian J +12 more
europepmc +1 more source
Abstract Purpose To evaluate the accuracy, agreement, and efficiency of a dual‐large language model (LLM) approach using Generative Pre‐Trained Transformer 5.2 (GPT‐5.2) and Google Gemini 3 Pro for automated data extraction in orthopaedic systematic reviews.
Prushoth Vivekanantha +6 more
wiley +1 more source
Abstract Purpose Large language models (LLMs) are a form of artificial intelligence (AI) that have emerged as potential tools to augment systematic review workflows. This study aimed to evaluate GPT‐5 as a third reviewer for full‐text screening across orthopaedic subspecialties. Methods Three review topics were selected.
Prushoth Vivekanantha +5 more
wiley +1 more source
A modular pipeline for natural language processing-screened human abstraction of a pragmatic trial outcome from electronic health records. [PDF]
Lee RY +12 more
europepmc +1 more source
Criteria used to define appropriate red blood cell transfusion in the perioperative setting: a scoping review. [PDF]
Ivankovic V +6 more
europepmc +1 more source
Large language models for thematic analysis in healthcare research: A blinded mixed-methods comparison with human analysts. [PDF]
Hill C +6 more
europepmc +1 more source
Sudden cardiac death secondary to acute aortic syndromes in young athletes in the United States. [PDF]
Petek BJ +9 more
europepmc +1 more source
Clinical trials for lupus nephritis. It is time for change. [PDF]
Morales E, Galindo M.
europepmc +1 more source
Evaluation of plasma calprotectin as a marker for infection in various clinical settings: a prospective observational study. [PDF]
Zimmermann T +8 more
europepmc +1 more source

