API Reference
Integrate medical intelligence into your platform
Authentication
All API requests require an HCC token obtained through your DataVault account. Include your token as a Bearer token in the Authorization header.
Endpoints
/v1/clinicalClinical Intelligence
Clinical intelligence queries including drug interactions, treatment suggestions, and diagnosis reasoning across the 8-axis model.
Example Request
{
"query": "Patient on metformin + lisinopril with declining NM axis. Suggest intervention.",
"axes": ["PO", "NM", "ER"],
"time_range": "6_months",
"response_format": "structured"
}Example Response
{
"reasoning_chain": [
"NM axis decline correlated with medication adherence drop at month 3",
"Metformin GI side effects flagged in 23% of similar profiles",
"Lisinopril interaction: no contraindication, but potassium monitoring recommended"
],
"suggestions": [
"Switch to extended-release metformin to reduce GI burden",
"Add weekly NM axis check-in via NexusOrb",
"Schedule nutritionist consult within 14 days"
],
"confidence": 0.87,
"contributing_data": {
"encounters": 12847,
"axis_correlations": {
"NM_PO": 0.72,
"NM_ER": 0.41
}
},
"hcc_cost": 2.5
}/v1/drug-outcomesDrug Outcome Analysis
Analyze drug efficacy, adverse events, and adherence patterns segmented by 8-axis wellness profile.
Example Request
{
"drug": "metformin",
"outcome_type": "efficacy",
"axes_filter": ["NM", "PO"],
"population_size": "minimum_500"
}Example Response
{
"drug": "metformin",
"outcome_type": "efficacy",
"cohort_size": 3241,
"efficacy_score": 0.78,
"adverse_event_rate": 0.12,
"axis_breakdown": {
"NM": { "correlation": 0.81, "trend": "positive" },
"PO": { "correlation": 0.64, "trend": "stable" }
},
"hcc_cost": 3.0
}/v1/risk-modelPatient Risk Modeling
Predict hospitalization, readmission, and health decline risk using multi-axis temporal data.
Example Request
{
"patient_profile": {
"axes_snapshot": { "PO": 6.2, "NM": 4.1, "ER": 7.8 },
"age_range": "55-64",
"conditions": ["type_2_diabetes", "hypertension"]
},
"risk_type": "hospitalization",
"horizon": "90_days"
}Example Response
{
"risk_type": "hospitalization",
"probability": 0.23,
"contributing_factors": [
{ "factor": "NM axis below threshold", "weight": 0.42 },
{ "factor": "Dual chronic condition", "weight": 0.31 }
],
"recommended_interventions": 3,
"hcc_cost": 5.0
}/v1/device-outcomesMedical Device Real-World Evidence
Access real-world evidence for medical devices including efficacy data, complication rates, and patient-reported outcomes.
Example Request
{
"device_category": "continuous_glucose_monitor",
"outcome_metrics": ["accuracy", "patient_satisfaction", "complication_rate"],
"time_period": "12_months"
}Example Response
{
"device_category": "continuous_glucose_monitor",
"studies_analyzed": 47,
"outcomes": {
"accuracy": 0.92,
"patient_satisfaction": 0.85,
"complication_rate": 0.03
},
"sample_size": 8920,
"hcc_cost": 3.0
}/v1/populationPopulation Health Analytics
Run cohort analysis and population-level health analytics across demographic and axis-based segments.
Example Request
{
"cohort_definition": {
"age_range": "40-65",
"axes_threshold": { "PO": { "min": 3.0 } },
"conditions": ["metabolic_syndrome"]
},
"analysis_type": "trend",
"granularity": "quarterly"
}Example Response
{
"cohort_size": 14203,
"analysis_type": "trend",
"periods": [
{ "quarter": "Q1_2026", "avg_PO": 4.8, "avg_NM": 5.1 },
{ "quarter": "Q4_2025", "avg_PO": 4.5, "avg_NM": 4.9 }
],
"statistical_significance": 0.003,
"hcc_cost": 10.0
}/v1/one-healthOne Health Intelligence
Cross-species analytics combining human and veterinary health data for zoonotic detection and comparative medicine.
Example Request
{
"query_type": "cross_species_correlation",
"human_condition": "respiratory_infection",
"animal_species": "canine",
"geographic_scope": "southeast_us"
}Example Response
{
"correlation_found": true,
"correlation_strength": 0.67,
"temporal_lag": "14_days",
"alert_level": "moderate",
"zoonotic_risk": "low",
"recommendation": "Monitor regional veterinary respiratory cases as leading indicator",
"hcc_cost": 5.0
}/v1/temporalTemporal Decay Analysis
Analyze how health behaviors decay over time and predict future trajectories using the 28 temporal decay rules.
Example Request
{
"patient_axes": {
"PO": [7.2, 6.8, 6.1, 5.5],
"NM": [8.0, 7.5, 7.0, 6.2]
},
"interval": "monthly",
"predict_ahead": 6
}Example Response
{
"decay_model": "exponential_plateau",
"predicted_trajectory": {
"PO": [5.1, 4.8, 4.6, 4.5, 4.5, 4.5],
"NM": [5.8, 5.4, 5.1, 4.9, 4.7, 4.6]
},
"intervention_urgency": "high",
"decay_rules_triggered": ["rule_7_exercise_plateau", "rule_12_nutrition_drift"],
"hcc_cost": 7.5
}/v1/catalogData Catalog
Retrieve available data domains, axes definitions, query types, and supported parameters.
Example Request
GET https://api.conceptualhealth.ai/v1/catalog
Authorization: Bearer <your_token>Example Response
{
"axes": ["PO", "NM", "ER", "SC", "RS", "ES", "TA", "PV"],
"domains": [
"clinical", "drug-outcomes", "risk-model",
"device-outcomes", "population", "one-health", "temporal"
],
"query_types": ["structured", "natural_language", "sql_like"],
"supported_time_ranges": ["30_days", "90_days", "6_months", "1_year", "all"],
"version": "1.0.0",
"hcc_cost": 0
}Rate Limits
| Tier | Daily Limit | Burst Rate |
|---|---|---|
| Starter | 100 queries/day | 10/min |
| Professional | 1,000 queries/day | 50/min |
| Enterprise | 10,000 queries/day | 200/min |
| Unlimited | Unlimited | Custom |
SDKs
Python
Availablepip install conceptualhealthSwift
AvailableSPM: conceptualhealth-swiftJavaScript
Coming Soonnpm install @conceptualhealth/sdkCreate your DataVault account to get API credentials and start building.
Create DataVault Account