ChatGPT, Bard, and Large Language Models for Biomedical Research: Opportunities and Pitfalls.

Bard Biomedical research ChatGPT Large language models Natural language processing

Journal

Annals of biomedical engineering
ISSN: 1573-9686
Titre abrégé: Ann Biomed Eng
Pays: United States
ID NLM: 0361512

Informations de publication

Date de publication:
Dec 2023
Historique:
received: 10 06 2023
accepted: 13 06 2023
medline: 9 11 2023
pubmed: 17 6 2023
entrez: 16 6 2023
Statut: ppublish

Résumé

Large Language Models (LLMs) such as ChatGPT and Bard have emerged as groundbreaking interactive chatbots, capturing significant attention and transforming the biomedical research landscape. These powerful tools offer immense potential for advancing scientific inquiry, but they also present challenges and pitfalls. Leveraging large language models, researchers can streamline literature reviews, summarize complex findings, and even generate novel hypotheses, enabling the exploration of uncharted scientific territories. However, the inherent risk of misinformation and misleading interpretations underscores the critical importance of rigorous validation and verification processes. This article provides a comprehensive overview of the current landscape and delves into the opportunities and pitfalls associated with employing LLMs in biomedical research. Furthermore, it sheds light on strategies to enhance the utility of LLMs in biomedical research, offering recommendations to ensure their responsible and effective implementation in this domain. The findings presented in this article contribute to the advancement of biomedical engineering by harnessing the potential of LLMs while addressing their limitations.

Identifiants

pubmed: 37328703
doi: 10.1007/s10439-023-03284-0
pii: 10.1007/s10439-023-03284-0
doi:

Types de publication

Review Letter

Langues

eng

Sous-ensembles de citation

IM

Pagination

2647-2651

Informations de copyright

© 2023. The Author(s) under exclusive licence to Biomedical Engineering Society.

Références

Adhikari, S., S. Thapa, U. Naseem, H. Y. Lu, G. Bharathy, and M. Prasad. Explainable hybrid word representations for sentiment analysis of financial news. Neural Netw. 164:115–123, 2023.
doi: 10.1016/j.neunet.2023.04.011 pubmed: 37148607
Zhao, W. X., K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, et al. A survey of large language models. arXiv preprint arXiv:2303.18223 , 2023.
Dwivedi, Y. K., N. Kshetri, L. Hughes, E. L. Slade, A. Jeyaraj, A. K. Kar, A. M. Baabdullah, A. Koohang, V. Raghavan, M. Ahuja, et al. So what if chatgpt wrote it? multidisciplinary perspectives on opportunities, challenges and implications of generative conversational ai for research, practice and policy. Int. J. Inf. Manag. 71:102642, 2023.
doi: 10.1016/j.ijinfomgt.2023.102642
Mbakwe, A. B., I. Lourentzou, L. A. Celi, O. J. Mechanic, and A. Dagan. ChatGPT Passing USMLE Shines a Spotlight on the Flaws of Medical Education. San Francisco: Public Library of Science, 2023.
doi: 10.1371/journal.pdig.0000205
Thapa, S., U. Naseem, and M. Nasim. From humans to machines: can ChatGPT-like LLMs effectively replace human annotators in NLP tasks? In: Workshop Proceedings of the 17th International AAAI Conference on Web and Social Media, 2023.
Chen, Q., H. Sun, H. Liu, Y. Jiang, T. Ran, X. Jin, X. Xiao, Z. Lin, Z. Niu, and H. Chen. A comprehensive benchmark study on biomedical text generation and mining with ChatGPT. bioRxiv, 2023.

Auteurs

Surendrabikram Thapa (S)

Virginia Tech, Blacksburg, VA, 24060, USA. surendrabikram@vt.edu.

Surabhi Adhikari (S)

Columbia University, New York, NY, 10027, USA.

Articles similaires

Humans Male Female Mental Health Child, Preschool
Humans Resilience, Psychological Rhode Island Biomedical Research Stress, Psychological
United States Periodicals as Topic Cross-Sectional Studies Humans Biomedical Research

Classifications MeSH