Editorial Commentary: Biomedical Research Investigating Artificial Intelligence Large Language Models Needs to Move Beyond Measuring Accuracy and Focus on Improving Patient Care.
| Autor: | Balazs GC |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association [Arthroscopy] 2024 Oct 18. Date of Electronic Publication: 2024 Oct 18. |
| DOI: | 10.1016/j.arthro.2024.10.010 |
| Abstrakt: | Orthopaedic surgeons are fascinated with artificial intelligence (AI). Since the release of ChatGPT to the general public on November 30, 2022, there have been a flurry of articles regarding use of large language models (LLMs) in our field. Most of these revolve around the accuracy of the models regarding orthopaedic topics (spoiler alert: the accuracy is good, yet unreliable, but improving). Unfortunately, the research around LLM is largely repetitive, applying the LLMs to the same essential tasks. LLM AI systems show amazing capabilities in data processing, collating and organizing and recognizing patterns. Now, research scientists need to innovate. Journals must encourage authors to investigate how AI systems can improve patient care. Competing Interests: Disclosures The author reports the following potential conflicts of interest or sources of funding: other from Fortis Surgical and Stryker, outside the submitted work; and Associate Editor, Arthroscopy. Full ICMJE author disclosure forms are available for this article online, as supplementary material. (Published by Elsevier Inc.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|