Importance: Large language models (LLMs) have proven useful for extracting data from publicly available sources, but their uses in clinical settings and with clinical data are unknown.
Objective: To determine the accuracy of data extraction using "Versa Chat," a chat implementation of the general-purpose OpenAI gpt-35-turbo LLM model, versus manual chart review for hepatocellular carcinoma (HCC) imaging reports.
Design: We engineered a prompt for the data extraction task of six distinct data elements and input 182 abdominal imaging reports that were also manually tagged. We evaluated performance by calculating accuracy, precision, recall, and F1 scores.
Setting/participants: Cross-sectional abdominal imaging reports of patients diagnosed with hepatocellular carcinoma enrolled in the Functional Assessment in Liver Transplantation (FrAILT) study.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10491368 | PMC |
| http://dx.doi.org/10.1101/2023.08.31.23294924 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A blueprint for large language model-augmented telehealth for HIV mitigation in Indonesia: A scoping review of a novel therapeutic modality.
Health Informatics J
January 2025
Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC, Australia.
The HIV epidemic in Indonesia is one of the fastest growing in Southeast Asia and is characterised by a number of geographic and sociocultural challenges. Can large language models (LLMs) be integrated with telehealth (TH) to address cost and quality of care? A literature review was performed using the PRISMA-ScR (2018) guidelines between Jan 2017 and June 2024 using the PubMed, ArXiv and semantic scholar databases. Of the 694 records identified, 12 studies met the inclusion criteria.
View Article and Find Full Text PDFAssociation of social determinants of health with first antiseizure medication prescription for patients with newly diagnosed epilepsy: A systematic review and meta-analysis.
Epilepsia
January 2025
Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
Objective: To assess whether social determinants of health (SDOHs) are associated with the first antiseizure medication (ASM) prescribed for newly diagnosed epilepsy.
Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards were followed, and the protocol registered (CRD42023448998). Embase, Medline, and Web of Science were searched up to July 31, 2023.
Inter-Rater Disagreements in Applying the Montreal Classification for Crohn's Disease: The Five-Nations Survey Study.
United European Gastroenterol J
January 2025
Sheba Medical Center, Institute of Gastroenterology, Ramat-Gan, Israel.
Background: The Montreal classification has been widely used in Crohn's disease since 2005 to categorize patients by the age of onset (A), disease location (L), behavior (B), and upper gastrointestinal tract and perianal involvement. With evolving management paradigms in Crohn's disease, we aimed to assess the performance of gastroenterologists in applying the Montreal classification.
Methods: An online survey was conducted among participants at an international educational conference on inflammatory bowel diseases.
Management Measures and Trends of Biological Invasions in Europe: A Survey-Based Assessment of Local Managers.
Glob Chang Biol
January 2025
Departament de Ciències Ambientals, Facultat de Ciències, Universitat de Girona, Girona, Spain.
Biological invasions are a major threat to biodiversity, ecosystem functioning and nature's contributions to people worldwide. However, the effectiveness of invasive alien species (IAS) management measures and the progress toward achieving biodiversity targets remain uncertain due to limited and nonuniform data availability. Management success is usually assessed at a local level and documented in technical reports, often written in languages other than English, which makes such data notoriously difficult to collect at large geographic scales.
View Article and Find Full Text PDFEfficient large language model with analog in-memory computing.
Nat Comput Sci
January 2025
Department of Computer Science, Royal Holloway, University of London, Egham, UK.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!