This is the authors' abstract. We don't add key points for this paper.
BACKGROUND: Recombinant Adeno-Associated Virus (rAAV) gene therapies are now approved for the treatment of certain rare diseases and require specialized knowledge for clinical implementation. OBJECTIVES: Our objective was to develop and evaluate an artificial intelligence (AI) chatbot called 'Gene-Genie' with domain expertise in the implementation of rAAV gene therapies. METHODS: The study was conducted in two phases. The first phase, Gene-Genie development, involved technical scoping, proof-of-concept, and technical testing by a team of pharmacists, medical practitioners, regulatory specialists, and laboratory scientists. In the second phase, Gene-Genie was evaluated using an exploratory pilot pre-post study design by feedback from hospital pharmacy leaders before and after using Gene-Genie. The total score on the questionnaire ranged from 0 - 28, with a higher score indicating better perceived knowledge of gene therapy. RESULTS: The AI chatbot was successfully developed in phase 1 to deliver accurate, reliable and context-aware interactions, aligned with the scope of the intended use case. The chatbot successfully referenced a curated and linked set of resources and avoided off-topic questions and responses. In the second phase, 8 pharmacy leaders tested Gene-Genie and provided feedback on its utility to further improve the chatbot. The mean (SD) score on the perceived knowledge questionnaire was 17.0 ± 5.5 pre and 20.0 ± 2.2 post using Gene-Genie. The majority of participants agreed or strongly agreed (n = 5, 62.5%) that they would recommend Gene-Genie to other hospital Directors of Pharmacy (or similar) to help them with gene therapy implementation. CONCLUSION: We have developed Gene-Genie, which is an AI conversational chatbot that is domain-specific to gene therapy. Exploratory findings suggest that a domain-specific chatbot like Gene-Genie may be useful to those in hospital pharmacy leadership positions to implement gene therapy programs.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Levy et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: