MedalioNER
Advanced Named Entity Recognition (NER) model specially trained on Polish medical texts.
Model Description
MedalioNER is an advanced Named Entity Recognition (NER) model specially trained on Polish medical texts. The model can automatically identify and classify key medical information in medical documentation, clinical notes, and reports.
It uses a transformer architecture based on BERT, fine-tuned to the specifics of Polish medical terminology. The model was trained on a dataset containing over 50,000 annotated medical documents from various specializations.
Full control over data
The model can operate fully locally on your organization's infrastructure, ensuring maximum security of medical data and compliance with regulatory requirements.
Recognized Entities
Use Cases
- Automatic parameterization of medical documentation
- Data extraction for analytical systems
- Medical coding support (ICD-10)
- Documentation quality analysis
- Preparing data for machine learning
API Integration
Models are available as a REST API service or for local deployment within hospital infrastructure. We provide documentation and integration support.
curl -X POST https://api.medalion.tech/v1/ner/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Patient received 500mg paracetamol for headache.",
"model": "MedalioNER",
"format": "json"
}'Test MedalioNER at your facility
Contact us to get API access or discuss on-premise deployment.