The Development and Evaluation of a Retrieval-Augmented Generation Large Language Model Virtual Assistant for Postoperative Instructions
The simulated testing demonstrated strong technical accuracy, safety, and clinical relevance in simulated postoperative care. Its architecture effectively balances flexibility and safety, addressing key limitations of standalone NLP and LLMs. While readability remains a challenge, these findings establish a solid foundation, demonstrating readiness for clinical trials and real-world testing within surgical care pathways.
Authors
- Jack London (ORCID: https://orcid.org/0000-0001-5252-412X)
- César Cabello (ORCID: https://orcid.org/0000-0002-7180-460X)
- Bernardo Gabriele Collaço (ORCID: https://orcid.org/0000-0003-3845-2646)
- Antonio J. Forte (ORCID: https://orcid.org/0000-0003-2004-7538)
- Nadia G. Wood (ORCID: https://orcid.org/0000-0002-2685-6427)
- Cui Tao (ORCID: https://orcid.org/0000-0002-4267-1924)
- Sanjay P. Bagaria (ORCID: https://orcid.org/0000-0001-6677-8964)
- Syed Ali Haider (ORCID: https://orcid.org/0009-0007-5621-2861)
- Ariana Genovese (ORCID: https://orcid.org/0009-0000-9678-2163)
- Srinivasagam Prabha (ORCID: https://orcid.org/0000-0003-2573-8493)
Institutions
- Mayo Clinic (US)
- Jacksonville College (US)
- Mayo Clinic in Arizona (US)
- Mayo Clinic in Florida (US)
Publication Details
- Journal
- Bioengineering
- Published
- 2025-11-07
- DOI
- https://doi.org/10.3390/bioengineering12111219
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65