CLARITY: Clinical Assistant for Routing, Inference, and Triage

2025-10-02

AI Summary

Low referral efficiency and suboptimal triage accuracy hinder clinical workflow in specialty referral. Method: We propose a synergistic agent architecture integrating Finite State Machines (FSMs) with Large Language Models (LLMs), enabling a modular, scalable medical conversational system. The FSM ensures process safety and regulatory compliance, while the LLM enhances semantic understanding and contextual reasoning for automated clinical assessment, intelligent referral decision-making, and structured patient consultation. Deployed via a microservices architecture, the system maintains loose coupling and interoperability with existing healthcare information systems. Contribution/Results: Evaluated on over 55,000 real-world clinical dialogues, the system achieves statistically significant improvement in first-referral accuracy over human specialists (p < 0.01) and reduces average consultation time to one-third that of manual triage, establishing a novel, high-reliability, and deployable paradigm for AI-augmented clinical triage.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present CLARITY (Clinical Assistant for Routing, Inference, and Triage), an AI-driven platform designed to facilitate patient-to-specialist routing, clinical consultations, and severity assessment of patients' conditions. Its hybrid architecture combines a Finite State Machine (FSM) for structured dialogue flows with collaborative agents that employ Large Language Model (LLM) to analyze symptoms and prioritize referrals to appropriate specialists. Built on a modular microservices framework, CLARITY ensures safe, efficient, and robust performance, flexible and readily scalable to meet the demands of existing workflows and IT solutions in healthcare. We report integration of our clinical assistant into a large-scale nation-wide inter-hospital IT platform, with over 55,000 content-rich user dialogues completed within the two months of deployment, 2,500 of which were expert-annotated for a consequent validation. The validation results show that CLARITY surpasses human-level performance in terms of the first-attempt routing precision, naturally requiring up to 3 times shorter duration of the consultation than with a human.

Problem

• AI platform for patient routing and clinical consultations
• Combines FSM and LLM agents for symptom analysis
• Validated system outperforms human routing precision

Innovation

• Hybrid architecture combining FSM and LLM agents
• Modular microservices framework for scalable healthcare
• AI platform for patient routing and severity assessment