RLM Healthcare
Category: AI & ML
Node id: rlm-healthcare
Maturity: beta
Risk tier: C
Standards: HIPAA
Single-call clinical LLM presets: Q&A, medication review, diagnosis assist, treatment planning, lab interpretation. One chat completion per run — use rlm-query for the recursive RLM loop
What it does
- Clinical query answering with patient data context
- Medication review for interactions and contraindications
- AI-assisted differential diagnosis generation
- Evidence-based treatment planning recommendations
- Laboratory result interpretation in clinical context
Use cases
- Answering clinical questions about specific patients
- Reviewing medication lists for safety and appropriateness
- Generating ranked differential diagnoses from symptoms
- Planning evidence-based treatments for diagnosed conditions
- Interpreting lab panels in the context of patient history
Runtime
- Performance tier:
variable
Input ports
| Name | Type | Required | Description |
|---|---|---|---|
query | text | No | Clinical query (overrides config query) |
patient_data | json | No | Patient data as structured JSON |
clinical_context | text | No | Clinical context narrative |
Output ports
| Name | Type | Required | Description |
|---|---|---|---|
result | json | No | Healthcare query result containing answer, operation, query, and http_status |
success | boolean | No | Whether the operation succeeded |
Settings
Basic
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| LLM Endpoint | llm_endpoint | string | Yes | Base URL of the LLM API | ||
| Model | model | string | No | gpt-4o | Model name to use | |
| Operation | operation | enum | No | clinical_query | clinical_query, medication_review, diagnosis_assist, treatment_planning, lab_interpretation | Healthcare operation to perform |
| Query | query | text | No | Static clinical query (overridden by input) |
Auth
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| API Key | api_key | secret | No | API key for the LLM provider |
Advanced
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Temperature | temperature | number | No | 0.3 | min 0; max 2 | Sampling temperature |
| Max Tokens | max_tokens | number | No | 4096 | Maximum tokens to generate |
Errors
| Code | Description |
|---|---|
ENDPOINT_REQUIRED | llm_endpoint is not configured |
LLM_REQUEST_FAILED | LLM API call failed during healthcare query |
HTTP_ERROR | LLM endpoint returned an HTTP error status |
Runtime notes
- The query input takes precedence over the static query in config
- patient_data and clinical_context are both optional but improve answer quality
- The answer field is free-text LLM prose; it is not structured JSON
- All responses include a disclaimer that information should be verified by a healthcare professional
See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.
Quelque chose n'est pas clair ? Envoyez vos commentaires sur la documentation par courriel.