ChatGPT, Bard, and large language models for biomedical research: opportunities and pitfalls
Abstract
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs have capabilities in generating scientific text, guiding clinical trial design, optimizing code, synthesizing medical literature, and facilitating communication of technical findings.
“These studies highlight LLMs’ capabilities in generating scientific text, guiding clinical trial design, optimizing code, synthesizing medical literature, and facilitating communication of technical findings [4–7].”
From Integrating large language models in biostatistical workflows for clinical and translational research (2025) · cites this paper as [5]
Cites
ChatGPT passing USMLE shines a spotlight on the flaws of medical education
Mbakwe, A. B., Lourentzou, I., Celi, L. A., Mechanic, O. J., & Dagan, A. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000205 · Cited by 273 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
The application of large language models in medicine: A scoping review
Meng, X., Yan, X., Zhang, K., Liu, D., Cui, X., Yang, Y., Zhang, M., Cao, C., Wang, J., Wang, X., et al. (2024) · iScience · doi:10.1016/j.isci.2024.109713 · Cited by 414 · see citing works
Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
Tian, S., Jin, Q., Yeganova, L., Lai, P.-T., Zhu, Q., Chen, X., Yang, Y., Chen, Q., Kim, W., Comeau, D. C., et al. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad493 · Cited by 359 · see citing works
Shi, W., Xu, R., Zhuang, Y., Yu, Y., Zhang, J., Wu, H., Zhu, Y., Ho, J. C., Yang, C., & Wang, M. D. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.1245 · Cited by 54 · see citing works
“…multi-tabular reasoning tasks within EHRs (orange) typically involve a significantly larger number of records per table and necessitate querying multiple tables to answer each question, thereby requiring more advanced reasoning and problem-solving capabilities. verse corpora during pretraining.”
BackgroundBiri, S. K., Kumar, S., Panigrahi, M., Mondal, S., Behera, J. K., & Mondal, H. (2023) · Cureus · doi:10.7759/cureus.47468 · Cited by 40 · see citing works
Huang, Y.-M., Chen, P.-H., Lee, H.-Y., Sandnes, F. E., & Wu, T.-T. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108659 · Cited by 35 · see citing works
ChatGPT as a Tool for Biostatisticians: A Tutorial on Applications, Opportunities, and Limitations
Dobler, D., Binder, H., Boulesteix, A., Igelmann, J., Köhler, D., Mansmann, U., Pauly, M., Scherag, A., Schmid, M., Al Tawil, A., et al. (2025) · Statistics in Medicine · doi:10.1002/sim.70263 · Cited by 20 · see citing works
Generative artificial intelligence performs rudimentary structural biology modeling
Ille, A. M., Markosian, C., Burley, S. K., Mathews, M. B., Pasqualini, R., & Arap, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-69021-2 · Cited by 16 · see citing works
Evaluating large language models for selection of statistical test for research: A pilot study
Mondal, H., Mondal, S., & Mittal, P. (2024) · Perspectives in Clinical Research · doi:10.4103/picr.picr_275_23 · Cited by 9 · see citing works
Grambow, S. C., Desai, M., Weinfurt, K. P., Lindsell, C. J., Pencina, M. J., Rende, L., & Pomann, G.-M. (2025) · Journal of Clinical and Translational Science · doi:10.1017/cts.2025.10064 · Cited by 7 · see citing works
Gilani, K., Verket, M., Peters, C., Dumontier, M., Rocca, H.-P. B.-L., & Urovi, V. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110745 · Cited by 5 · see citing works
- Authors
- Thapa, S., & Adhikari, S.
- Affiliations
- Virginia Tech (US)
- Columbia University (US)
- Corresponding author
- Thapa, Surendrabikram
- Venue
- Annals of Biomedical Engineering
- Published
- 2023-06-16
- Volume
- 51
- Issue
- 12
- Pages
- 2647-2651
- ISSN
- 0090-6964 (ISSN-L)
- 1573-9686
- OpenAlex
- W4380887490
- Cited by
- 111
- References
- 1
- Citations by year
- 2026: 15 · 2025: 35 · 2024: 46 · 2023: 15
- FWCI
- 4.42
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Annals of Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Keywords
- large language models, ChatGPT, Google Bard, biomedical research, literature review automation, hypothesis generation, misinformation, responsible AI use, AI-assisted research
- MeSH terms
- Biomedical Engineering, Language, Biomedical Research, Bioengineering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
