The clinical intelligence layer for psychiatry.
Attunio turns the speech timing, labs, prescriptions, and symptom scales you already collect into structured, explainable, clinician-reviewable intelligence — delivered as an API. One auth model, one response envelope, the same HIPAA-aligned posture across every endpoint.
curl https://attuniohealth.com/api/v1/dmse/analyze \ -H "Authorization: Bearer att_sk_live_xxx" \ -H "Content-Type: application/json" \ -d '{ "responseLatencySeconds": 2.6, "speechRateWpm": 98, "psychomotorFidgetEpisodes": 4, "sustainedAttentionPct": 66, "explain": true }'{ "ok": true, "data": { "object": "dmse.analysis", "summary": { "status": "clinical_attention", "requiresClinicianReview": true, "flagged": ["Response latency", "..."] }, "signals": [ { "signalKey": "response_latency", "metricValue": 2.6, "interpretation": "clinical_attention", "referenceRange": "<1.8s typical; ≥2.5s clinical attention", "mseLine": "Speech: increased response latency (avg ~2.6s)." } ], "intelligence": { "reasoning": { "narrative": "Current findings suggest a pattern warranting clinical attention. Objective behavioral indicators, including response latency averaging 2.6 seconds against a 2.5-second threshold, demonstrate a consistent departure from typical range across all four measured signals. Confidence is high given complete session data, and the existing evidence supports clinician review of this result." } } }}5
Live intelligence APIs
1
Unified auth & response envelope
TLS 1.3
Encrypted in transit
0
Raw audio or video stored
Send the signals you already have. Get intelligence back.
1Send timing telemetry
curl https://attuniohealth.com/api/v1/dmse/analyze \ -H "Authorization: Bearer att_sk_live_xxx" \ -H "Content-Type: application/json" \ -d '{ "responseLatencySeconds": 2.6, "speechRateWpm": 98, "psychomotorFidgetEpisodes": 4, "sustainedAttentionPct": 66, "explain": true }'2Receive clinical intelligence
{ "ok": true, "data": { "object": "dmse.analysis", "summary": { "status": "clinical_attention", "requiresClinicianReview": true, "flagged": ["Response latency", "..."] }, "signals": [ { "signalKey": "response_latency", "metricValue": 2.6, "interpretation": "clinical_attention", "referenceRange": "<1.8s typical; ≥2.5s clinical attention", "mseLine": "Speech: increased response latency (avg ~2.6s)." } ], "intelligence": { "reasoning": { "narrative": "Current findings suggest a pattern warranting clinical attention. Objective behavioral indicators, including response latency averaging 2.6 seconds against a 2.5-second threshold, demonstrate a consistent departure from typical range across all four measured signals. Confidence is high given complete session data, and the existing evidence supports clinician review of this result." } } }}See it run on your own voice.
Extract Digital MSE™ telemetry on-device from your microphone and call the live API with a publishable key — right in your browser, no signup needed.
Try the live demo
Decision support you can actually defend.
Structured, explainable signals
Every endpoint returns discrete signals mapped to a clinical interpretation, a confidence level, and a ready-to-paste narrative line — never a black-box score.
Clinician-reviewable by design
Output is decision support for a human clinician, with explicit confidence and source traceability — never an autonomous diagnosis.
Baselines & trend built in
Send prior values and the API computes a per-patient baseline (mean, SD, n) and a trend direction against the patient's own history.
Real-time, low latency
Stateless POSTs return structured intelligence in milliseconds — fast enough for in-visit decision support.
Digital MSE™ is API #1 — not the whole story.
Each API builds on the data and signals beneath it. Start with the foundation you already collect, then climb the ladder as far as your product needs to go.
- Base
Raw signal
Visit telemetry, labs, prescriptions, symptom scales, wearables — the data you already capture.
- API 1
Digital MSE™
Speech & movement timing → four structured mental-status-exam signals with confidence and trend.
- API 2
Medication Intelligence™
Correlates each prescription against symptom trajectory and Digital MSE™ change.
- API 3
Biomarker Intelligence™
Maps abnormal lab biomarkers to psychiatric relevance before psychotropics escalate.
- API 4
Outcome Intelligence™
Fuses scales, MSE latency, meds, biomarkers, and sleep into one explainable response composite.
- API 5
Relapse Prediction™
Combines the velocity of every signal above into a transparent, additive early-warning score.
From raw signals to clinical decision support.
A family of APIs that turn the structured signals you already collect into clinician-reviewable intelligence. One auth model, one response envelope, the same compliance posture across every product.
Raw signals
- Visit telemetry
- Labs
- Wearables
- Medications
- Symptom scales
Attunio Intelligence APIs
- Digital MSE™
- Medication Intelligence™
- Biomarker Intelligence™
- Outcome Intelligence™
- Relapse Prediction™
Clinical decision support
- Clinician-reviewed insights
- Trends & baselines
- Early-warning flags
Digital MSE™
Measure behavioral and cognitive function objectively.
Returns
- Mental status signals
- Behavioral observations
- Longitudinal trends
POST /v1/dmse/analyze{
"ok": true,
"data": {
"object": "dmse.analysis",
"intelligence": {
"summary": {
"status": "review",
"requiresClinicianReview": true
}
}
}
}Medication Intelligence™
Analyze medication effectiveness and safety over time.
Returns
- Treatment response
- Adherence insights
- Monitoring signals
POST /v1/medication/analyze{
"ok": true,
"data": {
"object": "medication.analysis",
"intelligence": {
"summary": {
"status": "stable",
"requiresClinicianReview": false
}
}
}
}Biomarker Intelligence™
Transform lab results into behavioral health insights.
Returns
- Biomarker interpretation
- Deficiencies & abnormalities
- Clinical relevance
POST /v1/biomarker/analyze{
"ok": true,
"data": {
"object": "biomarker.analysis",
"intelligence": {
"summary": {
"status": "watch",
"requiresClinicianReview": true
}
}
}
}Outcome Intelligence™
Measure whether treatment is working over time.
Returns
- Outcome score
- Progress trends
- Treatment effectiveness
POST /v1/outcome/score{
"ok": true,
"data": {
"object": "outcome.score",
"intelligence": {
"summary": {
"status": "improving",
"requiresClinicianReview": false
}
}
}
}Relapse Prediction™
Estimate the likelihood of clinical deterioration.
Returns
- Risk score
- Risk drivers
- Recommended monitoring level
POST /v1/relapse/predict{
"ok": true,
"data": {
"object": "relapse.prediction",
"intelligence": {
"summary": {
"status": "elevated",
"requiresClinicianReview": true
}
}
}
}Engineered for protected health information.
TLS 1.3 everywhere
All traffic is encrypted in transit with modern ciphers.
HIPAA-aligned
Built for PHI workflows with strict access scoping per API key.
Data minimization
Only downstream numerical metrics are processed. Raw audio and video are never accepted or stored.
Start building today.
Create a sandbox key in seconds — no card required. Test against every live endpoint, then request production access when you're ready to ship.
Building at health-system scale? Talk to our team about enterprise access & BAAs.