Technologies
Python FastAPI, Typescript/React, HeyGen (Avatars), OpenAI models, Whisper STT, PostgreSQL, Google Analytics, AWS
duration
3 months
customer
The client is a US-based independent continuing medical education company focused on delivering high-quality, innovative learning activities for healthcare providers. They wanted to create several custom interactive AI avatars that act as real patients to simulate doctor visits and follow-ups, combined with LLM-powered dialogue analysis to support their continuing medical education activities
Background and problem
Client wanted to build several interactive AI Avatars acting as real patients simulating doctor visit and follow-up, along with LLM-powered subsequent dialogue analysis
solution
The solution is a fully-functional web application with different medical cases, each with a dedicated patient avatar. Each patient avatar has its own medical chart, dynamically updated as soon as the doctor unlocks new information in the dialogue or confirms action, e.g., sending a patient to get Labs results. The solution was fully integrated into LearnWorlds (LMS) and FreeCME (course platform) to ensure better medical student audience coverage.
Back
Share:
