AI-Enhanced Clinical Triage Chatbots — Rules-Based vs. LLM Augmentation
COMPARISONA convergent mixed-methods study evaluated three AI enhancements — Dialogflow, ChatGPT, and Gemini — integrated into an existing rules-based clinical triage chatbot, with the goal of informing development of tools that improve patient access and healthcare system navigation. The study is notable for directly comparing LLM augmentation against an established rules-based baseline in a clinical triage context. Rules-based triage chatbots offer predictability and auditability but are limited in handling novel symptom presentations or natural language variation. LLM-augmented systems offer greater conversational flexibility but raise accuracy concerns that have limited their adoption in clinical settings. The study evaluated whether LLM enhancements improved triage performance without introducing unacceptable safety risks. Findings across the three LLM tools showed variable performance characteristics, with accuracy concerns remaining a primary limiting factor for LLM use in clinical triage. The mixed-methods design captured both quantitative performance metrics and qualitative user experience data, providing a more complete picture of the practical tradeoffs than benchmark-only evaluations. The study positions LLM augmentation as a tool for improving patient access and navigation rather than replacing clinical judgment. The research contributes to a growing evidence base on hybrid chatbot architectures — combining rules-based reliability for high-stakes clinical pathways with LLM…
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.