Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CLARITY: Clinical Assistant for Routing, Inference, and Triage

Vladimir Shaposhnikov, Aleksandr Nesterov, Ilia Kopanichuk, Ivan Bakulin, Egor Zhelvakov, Ruslan Abramov, Ekaterina Tsapieva, Iaroslav Bespalov, Dmitry V. Dylov, Ivan Oseledets

TL;DR

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.

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 patient 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 national interhospital platform, with more than 55,000 content-rich user dialogues completed within the two months of deployment, 2,500 of which were expert-annotated for subsequent 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.

CLARITY: Clinical Assistant for Routing, Inference, and Triage

TL;DR

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.

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 patient 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 national interhospital platform, with more than 55,000 content-rich user dialogues completed within the two months of deployment, 2,500 of which were expert-annotated for subsequent 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.

Paper Structure

This paper contains 63 sections, 16 equations, 2 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Architecture
  3. Chat Manager
  4. FSM Scalability
  5. Services
  6. Moderator
  7. Emergency Detector
  8. Readiness Estimator
  9. Question Detector
  10. Information Collector
  11. Medical Specialty Selector
  12. Answer Generator
  13. Experiments And Results
  14. First Pilot Study: Understanding User Behavior And Preferences
  15. Second Pilot Study: Focus On Real-World Application
  16. ...and 48 more sections

Figures (2)

  • Figure 1: The architecture of the CLARITY system.
  • Figure 2: Dialogue example illustrating the Transparency scenario. Full dialogue examples for Critical, Safety, and Adaptability are provided in Appendix \ref{['appx:dialogue_examples']}, Table \ref{['tab:example_full']}.