Development and Validation of a Large Language Model–Powered Chatbot for Neurosurgery: Mixed Methods Study on Enhancing Perioperative Patient Education
NeuroBot, leveraging LLMs with the retrieval-augmented generation technique, demonstrates the potential of LLM-based chatbots in perioperative neuroendovascular care, offering scalable and continuous support. By integrating domain-specific knowledge, NeuroBot simplifies communication between professionals and patients while ensuring patients have 24-7 access to reliable, evidence-based information. Further refinement and research will enhance NeuroBot's ability to foster patient-centered communication, optimize clinical outcomes, and advance AI-driven innovations in health care delivery.
Authors
- Vivian Hui (ORCID: https://orcid.org/0000-0003-1966-6139)
- Arkers Kwan Ching Wong (ORCID: https://orcid.org/0000-0001-6708-3099)
- Shaowei Guan
- Calvin Hoi‐Kwan Mak (ORCID: https://orcid.org/0000-0002-1443-2109)
- Cynthia K. Y. Ho
- Prudence Kwan-Lam Mok (ORCID: https://orcid.org/0009-0000-3942-1054)
- Jing Qin (ORCID: https://orcid.org/0000-0002-7059-0929)
- Won Ho
- C. Lam
Institutions
- Hong Kong Polytechnic University (HK)
- University of Pittsburgh (US)
- Chinese University of Hong Kong (HK)
- Queen Elizabeth Hospital (GB)
- Queen Elizabeth Hospital (CN)
- University of Hong Kong (HK)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-06-19
- DOI
- https://doi.org/10.2196/74299
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62