Adrijana Jeremić

Comparative analysis of AI enhancements to rules-based clinical triage chatbot: Convergent mixed-methods study

It is shown that safe clinical deployment of LLM-based chatbots requires governance addressing accuracy, interpretability, and masking of poorer performance by conversational fluency, and the divergence between user preference and measured accuracy underscores that safe clinical deployment of LLM-based chatbots require...