Clinical Reasoning
Category: Healthcare Standards
Node id: reasoning
Standards: HIPAA, GDPR, SOC2
Supports clinical reasoning including differential diagnosis generation, evidence assessment, reasoning chain construction, recommendation synthesis, and hypothesis validation
What it does
- Differential diagnosis generation from clinical findings
- Evidence strength assessment for hypotheses
- Clinical reasoning chain construction (complaint to conclusion)
- Treatment recommendation synthesis with personalization
- Hypothesis validation against clinical evidence
- Confidence scoring for clinical judgments
Use cases
- Structured clinical reasoning for complex presentations
- Differential diagnosis generation in emergency settings
- Evidence-based treatment recommendation synthesis
- Clinical hypothesis testing during diagnostic workup
Runtime
- Performance tier:
fast
Input ports
| Name | Type | Required | Description |
|---|---|---|---|
findings | json | No | Clinical findings array (for differential) |
patient | json | No | Patient demographics and context |
hypothesis | json | No | Hypothesis name (string) or object (for assess/validate) |
evidence | json | No | Clinical evidence items |
complaint | text | No | Presenting complaint (for reasoning chain) |
conclusion | text | No | Conclusion for reasoning chain |
diagnosis | text | No | Diagnosis (for recommendation synthesis) |
patient_factors | json | No | Patient-specific factors |
context | json | No | Clinical context data |
Output ports
| Name | Type | Required | Description |
|---|---|---|---|
result | json | No | Reasoning data (hypotheses, evidence assessment, reasoning chain, recommendations, validation) |
confidence | text | No | Confidence level (low/medium/high) |
success | boolean | No | Operation success flag |
Settings
Basic
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Operation | operation | enum | No | differential | differential, assess, reason, synthesize, validate | Reasoning operation to perform |
Advanced
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Top N | top_n | number | No | 5 | min 1; max 20 | Number of top hypotheses to return |
Errors
| Code | Description |
|---|---|
FINDINGS_REQUIRED | Clinical findings array required for differential |
HYPOTHESIS_REQUIRED | Hypothesis required for assess/validate operations |
COMPLAINT_REQUIRED | Presenting complaint required for reasoning chain |
DIAGNOSIS_REQUIRED | Diagnosis required for recommendation synthesis |
UNSUPPORTED_OPERATION | Operation not recognized |
Runtime notes
- Result shape varies by operation: differential returns hypotheses/top_hypothesis; assess returns evidence counts/strength; reason returns chain steps; synthesize returns recommendations; validate returns is_valid/strengths/weaknesses
- Hypotheses are ranked by probability (highest first) and capped by top_n config
- The confidence output is a top-level string (low/medium/high) derived from the primary result
- Findings input for differential must be an array of objects with a 'description' field
See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.
Something unclear? Send documentation feedback by email.