A living, connected model of patients, conditions, diagnostics, and AI — enabling context-aware healthcare applications that understand relationships, not just records.
The HealthCloud Knowledge Graph connects every clinical entity into a unified, queryable system. Instead of isolated records in separate databases, you get a rich network of relationships spanning the entire care journey.
Each node type maps to a clinical or AI entity. FHIR resources are native graph nodes.
FHIR Patient resource with demographics, identifiers, and coverage linkages.
FHIR: PatientClinician or care team member with credentials, specialty, and NPI.
FHIR: PractitionerICD-10 and SNOMED CT coded diagnoses and problem list entries.
FHIR: ConditionLab results, vital signs, and device readings encoded with LOINC codes.
FHIR: ObservationAI model output including confidence scores, evidence, and recommendations.
Clinical ML model with version, training dataset, and performance metrics.
Curated training or evaluation dataset with provenance and lineage metadata.
Orchestration definition linking agents, APIs, and data steps.
Edges express the relationships between entities. Every edge is typed, bidirectional, and queryable.
| Edge | From | To | Description |
|---|---|---|---|
has_condition | Patient | Condition | Patient is diagnosed with a condition |
has_observation | Patient | Observation | Patient has a clinical observation or measurement |
evaluated_by | Condition | AI Model | A condition is evaluated by an AI diagnostic model |
trained_on | AI Model | Dataset | An AI model was trained on a specific dataset |
triggers | Observation | Workflow | An observation anomaly triggers a clinical workflow |
recommended_by | Diagnostic | Provider | A diagnostic recommendation is surfaced to a provider |
ordered_by | Provider | Observation | A provider ordered a lab test or observation |
produces | Workflow | Diagnostic | A workflow execution produces a diagnostic result |
Query the graph using HealthCloud's graph query language — traverse relationships across patients, conditions, and AI models in a single request.
Query
query {
patients(
condition: "diabetes_type2",
observation: {
code: "LOINC:2339-0",
value_gt: 140
}
) {
id
name {
given
family
}
conditions {
code
onset_date
}
related_models {
id
name
accuracy
}
}
}Response
{
"data": {
"patients": [
{
"id": "pat_123",
"name": { "given": "Jane", "family": "Doe" },
"conditions": [
{ "code": "E11.9", "onset_date": "2024-06-15" }
],
"related_models": [
{
"id": "glucose_risk_v2",
"name": "Glucose Risk Predictor",
"accuracy": 0.94
}
]
}
]
}
}The Knowledge Graph is what makes HealthCloud's AI different. Models don't operate on isolated inputs — they reason across connected clinical context.
Models understand the full patient context — prior diagnoses, observations, and care history — not just the current input.
Trace any AI output back through the graph to the source data and model weights that produced it.
Link clinical outcomes to model predictions to enable feedback loops that improve accuracy over time.
The graph updates automatically when new observations arrive, workflows execute, or diagnostics complete.
Trace how conditions evolve over time by linking observations, encounters, and model outputs across the patient timeline.
Surface AI-recommended next steps by querying related models, evidence datasets, and prior outcomes for similar patients.
Identify care gaps by traversing patient → condition → workflow edges to surface unaddressed clinical triggers.
Aggregate cohort-level insights by querying shared condition or observation patterns across thousands of patients.
Identify high-quality training examples by traversing model → dataset → patient edges with outcome metadata.
Trace model outputs back to input observations and ground truth labels to audit accuracy and detect drift.
The Knowledge Graph is accessible via a REST API. Query patients, models, and relationships programmatically.
/v1/graph/query— Query patients with specific conditions and elevated lab valuesRequest Body
{
"query": "patients",
"filters": {
"condition": "diabetes_type2",
"observation": {
"code": "LOINC:2339-0",
"value_gt": 140
}
},
"include": ["conditions", "related_models"]
}Response
{
"patient_id": "pat_123",
"conditions": ["diabetes_type2"],
"related_models": ["glucose_risk_v2"]
}/v1/graph/patients/{id}— Retrieve the full knowledge graph subgraph for a single patientResponse
{
"id": "pat_123",
"nodes": 14,
"edges": 22,
"conditions": ["E11.9"],
"observations": 47,
"workflows_triggered": 3
}/v1/graph/models/related— Find AI models related to a given condition or observation typeResponse
{
"condition": "diabetes_type2",
"models": [
{ "id": "glucose_risk_v2", "accuracy": 0.94 },
{ "id": "hba1c_predictor_v1", "accuracy": 0.91 }
]
}Query across patients, conditions, diagnostics, and AI models in a single request. Build AI that reasons about context — not just data.