DeepSensi™

Technology & deployment

From a clinic shelf
to an air-gapped hospital.

DeepSensi™ deploys where the patient is: four tiers of commodity hardware, one identical safety discipline. At the top tier, the complete consilium runs fully air-gapped: no cloud, no external dependency, no byte leaving the building. Sovereignty is not a feature. It is the architecture.

4
deployment tiers, one safety discipline
Air-gapped
complete consilium, fully on premises
FHIR R4
EHR plug-and-play, HL7v2, SMART sign-in
Zero
data retention on the external API

Deployment tiers

Commodity hardware. Uncommon discipline.

Every tier enforces the same safety layer and the same privacy discipline. Hardware is commodity; the discipline is not.
TierRoleWhat runs thereTypical home
Gateway NodeIntegration & privacy edgeEHR bridging, de-identification at source, encrypted uplink. No AI inference.Any practice
Clinic NodeLocal triageOn-device intake screening and triage support.Single practices
Clinic Node ProLocal inferenceShared local reasoning for multi-physician teams.Group practices & clinics
Hospital NodeFull sovereigntyThe complete consilium and safety layer, fully air-gapped.Hospitals, systems, defense, government

Interoperability & security

Built to pass procurement, not just demos.

01

EHR plug-and-play

FHIR R4 with automated write-back under the physician’s digital signature, HL7v2 interfaces, SMART-on-FHIR sign-in. Fits Epic, Cerner, and the systems you already run.

02

Zero-retention API

External systems integrate against a hard no-retention guarantee with per-patient isolation. Diagnostics as a service; your data stays yours.

03

Security by default

Two-factor authentication per RFC 6238, de-identification at the edge in under a millisecond, deterministic safety overrides in under five milliseconds, and an immutable audit trail.

04

Field mode

Degraded-bandwidth satellite operation with automatic failover to local models. Clinics keep working when the link does not.

Talk to an architect

Enterprise fact sheet

Procurement answers, on one screen.

Regulatory posture
Engineered to FDA SaMD guidance; IEEE P2941-aligned model integrity; FDA pre-submission (Q-Sub) engaged; aligned with HIPAA, GDPR, and the EU AI Act by architecture.
EHR integration
Epic, Cerner, Allscripts, OpenEMR. Plug and play through standards, not custom glue.
Interfaces
FHIR R4 (read and digitally signed write-back), HL7v2, SMART on FHIR (OAuth 2.0 with PKCE), medical-imaging (DICOM) ingest.
Data boundary
Zero PII leaves the premises: deterministic de-identification at the source; k-anonymity (k ≥ 5) and l-diversity on research cohorts; air-gapped mode sends nothing at all.
Edge devices
Three tiers of commodity hardware: Gateway (integration and privacy, no inference) · Clinical (local triage and telemetry) · Enterprise (the complete consilium, fully air-gapped).
Model integrity
Boot-time attestation: SHA-256 against a signed registry plus RSA-2048 package signatures verified in the device secure enclave. Fail-closed: a tampered model refuses to start.
Audit & liability
Cryptographically signed reasoning ledger with root-hash anchoring to a public Layer-2 blockchain. Patent pending.
Transport security
TLS 1.3 with mutual authentication and certificate pinning; hardware-bound VPN tunnels; two-factor authentication per RFC 6238.
Resilience
Satellite-degraded field mode with automatic fallback to local models; disk-persisted offline queues; fully autonomous air-gap operation.
Research & pharma
Federated learning (gradients only, records never move); FAERS pharmacovigilance correlation; population twins with NNT before the first dose.
Deployment model
On premises by default; sovereign and national configurations; zero-retention external API.

Under the hood

The questions your CIO will ask. Answered before the meeting.

Engineering detail, cleared for daylight. The deeper dossier is available under NDA.

What runs where, exactly?
Three field tiers, one discipline. A Gateway Node does integration and privacy only: EHR bridging, PII scrubbing at the source, a disk-persisted offline queue, a hardware-bound VPN uplink, and no AI inference. A Clinical Node adds local triage and pre-screening models, imaging ingest, and vocal-biomarker telemetry. An Enterprise Node runs the complete consilium, the graph knowledge layer, and the digital-twin engine entirely on premises, with a fully autonomous air-gap mode. Hardware is commodity, from single-board gateways to workstation-class nodes.
How do you know the model on our site hasn’t been tampered with?
It refuses to start. At boot, every model artifact is hashed (SHA-256) and matched against a signed central registry; packages are additionally signed with DeepSensi’s private key (RSA-2048) and verified against a public key held in the device’s secure enclave. On any mismatch the node fails closed: initialization blocks, local execution locks, and a high-priority security alert fires. Aligned with FDA SaMD guidance and IEEE P2941 model-integrity principles.
How does DeepSensi connect to Epic or Cerner?
Through standards, not custom glue: SMART on FHIR sign-in (OAuth 2.0 with PKCE), reading Patient, Observation, and DiagnosticReport resources; the finalized result is written back as a FHIR ClinicalImpression plus a digitally signed DiagnosticReport, under the physician’s signature. Epic, Cerner, Allscripts, and OpenEMR are supported through the same connector suite.
What actually leaves the building?
Nothing identifiable. A local, deterministic scrubber redacts names, dates, geographic identifiers, and serial numbers under HIPAA rules before any context leaves the local network; research cohorts additionally receive k-anonymity (k ≥ 5) and l-diversity treatment. On an air-gapped enterprise node, the answer is simpler still: nothing leaves at all.
What happens when the network fails?
The node notices before you do. An uplink monitor watches link quality continuously; past tolerance, it switches to a degraded state: reasoning falls back to local on-device models, a context-compression engine strips non-essential history to save bandwidth, and timeout budgets extend gracefully. Satellite uplinks are first-class citizens. Clinics keep working when the link does not.
How is clinical data separated from billing?
By hard account isolation on the internal event mesh: clinical channels and financial channels are logically segregated planes, so a compromise of one cannot traverse into the other. Failed messages land in dead-letter queues for diagnostics; throughput scales elastically to hundreds of MB/s for imaging and population-scale simulation.
How does federated learning work here?
Gradients travel; records never do. Nodes train locally on hospital data and export only weight adjustments to the central repository. Combined with source-level de-identification and cohort anonymization, this is how pharma-grade research runs without a single patient record changing hands.
Why is the audit trail legally defensible?
Every step of the reasoning chain, prompts, agent interactions, consensus changes, is cryptographically signed (RSA-2048) into an immutable ledger, and the session log’s root hash is periodically anchored to a public Layer-2 blockchain, an anchoring mechanism that is patent-pending. The trail is tamper-evident even against the operator: court-grade provenance for liability scenarios.
Which security standards do you implement?
TLS 1.3 with mutual authentication and certificate pinning, hardware-bound VPN tunnels, secure-enclave key storage, boot-time model attestation, two-factor authentication per RFC 6238, HIPAA and GDPR compliance, and EU AI Act alignment by architecture. The deeper engineering dossier, model inventory, mesh topology, performance envelopes, is available under NDA.

Public edition. Model inventory, mesh topology, performance envelopes, and deployment runbooks: under NDA via [email protected].

Clinical validation

SILENT-DS: the prospective layer, already designed.

A multi-site, silent-mode, non-interventional study - pre-registered before the first patient, adjudicated independently, reported to STARD-AI. Hospitals can join as study sites on a rolling basis.

Become a study site How to evaluate any medical AI