Integrating large language models in biostatistical workflows for clinical and translational research
LLM usage is notable among respondents at two academic medical centers, though response patterns likely reflect early adopters. While LLMs enhance productivity, challenges like errors and reliability concerns highlight the need for verification strategies and systematic validation. The strong interest in training underscores the need for structured guidance. As an initial step, we propose eight core principles for responsible LLM integration, offering a preliminary framework for structured usage, validation, and ethical considerations.
Authors
- Christopher John Lindsell (ORCID: https://orcid.org/0000-0002-3297-2811)
- Steven C. Grambow (ORCID: https://orcid.org/0000-0001-6037-3253)
- Manisha Desai (ORCID: https://orcid.org/0000-0002-6949-2651)
- Kevin P. Weinfurt (ORCID: https://orcid.org/0000-0002-0624-7448)
- Michael Pencina (ORCID: https://orcid.org/0000-0002-1968-2641)
- Gina‐Maria Pomann (ORCID: https://orcid.org/0000-0002-6324-3953)
- Lacey Rende (ORCID: https://orcid.org/0009-0005-8695-1839)
Institutions
- Duke University (US)
- Stanford University (US)
Publication Details
- Journal
- Journal of Clinical and Translational Science
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1017/cts.2025.10064
- Citations
- 2
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 1.61
Funders
- University of Cambridge
- National Institutes of Health
- National Center for Advancing Translational Sciences
- Duke Clinical Research Institute