Caire
Award · Overcoming language barriers in healthcare with AI-powered reporting.
Team: Enough Slices
🥈 2nd Place at TUM.ai Makeathon (April 2023).
Caire is an AI-powered assistant designed to automate medical reporting. Using real-time speech-to-text and a fine-tuned LLM, it extracts medically relevant information and generates structured reports.
The Problem
In modern healthcare, nurses spend a significant portion of their shifts on manual documentation rather than patient care. This problem is exacerbated when language barriers exist between the patient and the nursing staff, leading to potentially critical information gaps and increased administrative burden.
Our Solution: Caire
Caire is an AI-powered assistant designed to automate medical reporting. The app follows a simple yet powerful pipeline:
- Speech-to-Text: Using OpenAI’s Whisper, we transcribe medical consultations or patient check-ins in real-time.
- Entity Extraction: A fine-tuned LLM parses the transcript to extract medically relevant information (symptoms, medication, patient history).
- Structured Reporting: The system automatically generates a structured medical report in the patient’s and hospital’s primary languages.
Success at TUM.ai Makeathon
Out of dozens of participating teams, Caire was awarded 2nd Place in the overall competition. The judges highlighted the solution’s feasibility and its potential for immediate impact in hospital workflows.
- Award: 🥈 2nd Place Overall
- Prize: €2,000
- Team: Enough Slices
- Challenge: “Bridge the Gap” by Knowron