// Post-session response
{
"risk_flags": ["physio_spike_no_verbal_ack"],
"evidence": {
"hr_trace": "segment_41m02s_41m48s",
"arousal_event": "41:12",
"verbal_ack": "none_in_window"
},
"confidence": 0.81,
"signal_quality": 0.94
}What the flag means
The say/body gap: heart rate spiked, the words didn’t acknowledge it. The clinician sees the trace behind the flag and can dismiss it.
confidence and signal_quality are computed by SeroState from heart-rate sample continuity across the session; the watch does not return them.
View API reference →
The session said “fine.” The body disagreed.
SeroState fuses wearable and vocal biomarkers from the behavioral-health session into post-session evidence for your EHR. Objective, reviewable, dismissible — the clinician always decides.
“SeroState began after the earthquakes in Hatay, where I watched skilled clinicians give everything, and still have no way to see whether it was working.” The story →
StartUp Health portfolio company · EU deep-tech incubation (Ege D-Tech) · global pharma innovation award
SeroState is the intelligence layer for behavioral care — not a device. We fuse post-session wearable heart-rate signal and vocal biomarkers into audit-ready FHIR R4 session physiology evidence, delivered to EHR and telehealth platforms via the QOAX API. The name refers to physiological session state in behavioral health. Company overview and founder story →
Deteriorating patients go unseen until crisis. In independent research, therapists caught 1 in 8 deteriorating clients (Østergård et al., 2024. Not our study, and the point stands).
A consumer wearable streams heart data during the session while vocal features are computed from the audio. Nothing changes about how the clinician works.
Post-session, SeroState time-aligns physiological and vocal signals against the session timeline and detects say/body gap events — physiological spikes with no verbal acknowledgment in the surrounding window.
The output arrives as a structured, FHIR-compatible payload in your EHR: risk flags, evidence segments, confidence and signal-quality scores. SeroState is an intelligence layer, not a diagnostic device. The clinician reviews the trace and always decides.
Add session physiology to every note.
Payers and regulators are moving behavioral health toward objective documentation. One API integration adds a physiology evidence layer to every session your clinicians produce — mapped to FHIR, ready for audit.
An objective arm alongside PHQ-9 and GAD-7.
Research-grade, session-time-aligned physiological and vocal data via API. Study in-session arousal, physiological synchrony, and recovery patterns without building your own capture pipeline.
Continuous behavioral endpoints across sites.
For CNS and behavioral trials, SeroState delivers objective, continuous endpoints instead of relying solely on episodic self-report. Fits decentralized trial designs with consistent, structured data across sites.
Session physiology is the measurement of the body’s signals (heart rate, heart-rate variability, and vocal patterns) during a behavioral-health session, time-aligned to what was said. Self-report tells clinicians what a client chooses to share. Session physiology shows how their nervous system actually responded, moment by moment.
The gap between the two is where clinical risk hides. SeroState calls this the say/body gap — the layer that notes, transcripts, and AI scribes don’t capture. Words can mask distress; physiology doesn’t.
Heart rate is the primary signal; heart-rate variability and vocal prosody are secondary/opportunistic. When physiological arousal spikes during a clinically relevant topic and the client’s language flattens or deflects, that’s a say/body gap — a moment worth reviewing. SeroState turns those moments into structured evidence: a flag, the trace behind it, a confidence score. Reviewable by the clinician, dismissible by the clinician, documented in the record.
Illustrative trace aligned to the hero API example. confidence and signal_quality appear in the post-session payload only.
Your organization holds the PHI. We don’t store it.
Architected for HIPAA-aligned deployments. BAAs for pilot partners.
Flags are reviewable evidence. Clinicians retain full judgment.
FAQ
We are a behavioral health evidence API company. SeroState fuses post-session wearable and vocal biomarkers into FHIR R4 session physiology evidence for EHR platforms. Full overview →
SeroState fuses smart wearable signal and vocal biomarker into FHIR R4 evidence after structured clinical sessions. Platforms integrate via REST API for audit-ready documentation — post-session, without replacing clinician workflow.
We validate by blinded comparison against expert clinical judgment, reported by population subgroup. Our prospective trial is in design; we pre-register and publish before making accuracy claims. The published scientific foundation is on our Science page.
Platforms embed SeroState via the QOAX REST API — one post-session call returns confidence-scored evidence and FHIR R4 artifacts. Stateless by default: zero PHI stored, never trained on partner patient data.
A post-session evidence record with physiological timeline, risk flags, confidence scores, signal-quality metadata, and FHIR R4 output — delivered after the behavioral-health session ends, not in real time.
No. SeroState is not related to prostate health, urology, or PSA testing. The name refers to physiological session state in behavioral care. SeroState is an API-first company serving behavioral health, RPM, and EHR platforms.
We’re selecting a small number of paid pilot partners for 2026. Tell us who you are and we’ll route you to the right conversation — everything stays on this page until you submit.
Where do you fit?