NER Extractor
Category: Ai Ml Standards: HIPAA · Clinical NLP standards
Extract named entities from clinical text (medications, conditions, procedures)
What this node does
- Medical NER
- SNOMED coding
- Medication extraction
- Condition detection
How to use
- In the Agentic Studio, open or create a workflow
- In the node palette on the left, find NER Extractor under the Ai Ml category (or use the search bar)
- Drag the node onto the canvas
- Double-click the node to open its configuration dialog
- Fill in the required parameters (see Configuration below)
- Connect the Clinical Text input port from an upstream node
- Connect the Extracted Entities and FHIR Resources output to the next node downstream
Inputs
| Port | Type | Required | Description |
|---|---|---|---|
| Clinical Text | text | ✓ | Plain text string |
Outputs
| Port | Type | Description |
|---|---|---|
| Extracted Entities | json | JSON data object |
| FHIR Resources | fhir-bundle | A FHIR R4 Bundle containing one or more resources |
Configuration
Open the configuration dialog by double-clicking the NER Extractor node on the canvas.
| Parameter | What to enter |
|---|---|
model | AI model to use, e.g. claude-3-5-sonnet, gpt-4o. Affects cost and quality |
entityTypes | Configure entityTypes in the node settings |
confidenceThreshold | Configure confidenceThreshold in the node settings |
outputFormat | Output format: json, csv, fhir-bundle, or hl7 |
When to use this node
- Extract medications from notes
- Identify conditions
- Parse procedures
Need help configuring this node?
Go to Settings → Connectors to set up the connection this node depends on, then reference the connector ID in the node configuration dialog.