Journal article
Radiology Gets Chatty: The ChatGPT Saga Unfolds
CUREUS JOURNAL OF MEDICAL SCIENCE, v 15(6), E40135
08 Jun 2023
PMID: 37425598
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
As artificial intelligence (AI) continues to evolve and mature, it is increasingly finding applications in the field of healthcare, particularly in specialties like radiology that are data-heavy and image-focused. Language learning models (LLMs) such as OpenAI's Generative Pre-trained Transformer-4 (GPT-4) are new in the field of medicine and there is a paucity of literature regarding the possible utilities of GPT-4 given its novelty. We aim to present an in-depth exploration of the role of GPT-4, an advanced language model, in radiology. Giving the GPT-4 model prompts for generating reports, template generation, enhancing clinical decision-making, and suggesting captivating titles for research articles, patient communication, and education, can occasionally be quite generic, and at times, it may present factually incorrect content, which could lead to errors. The responses were then analyzed in detail regarding their potential utility in day-to-day radiologist workflow, patient education, and research processes. Further research is required to evaluate LLMs' accuracy and safety in clinical practice and to develop comprehensive guidelines for their implementation.
Metrics
5 Record Views
Details
- Title
- Radiology Gets Chatty: The ChatGPT Saga Unfolds
- Publication Details
- CUREUS JOURNAL OF MEDICAL SCIENCE, v 15(6), E40135
- Publisher
- SPRINGERNATURE; LONDON
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Drexel University
- Web of Science ID
- WOS:001022016800005
- Other Identifier
- 991021861310204721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Medicine, General & Internal