Saltar al contenido principal

Waveform Perception (Signal Models)

Category: AI & ML
Node id: waveform-perception
Maturity: beta
Risk tier: B

Standards: HIPAA, GDPR, IEC 62304

Runs ECG waveforms through signal foundation models (ECGFounder, ECG-JEPA) via tietai-signal-service: embeddings and 150-label screening scores. Scores are screening output, never diagnoses.

What it does​

  • ECGFounder 12-lead / 1-lead: 1024-d embeddings + full 150-label screening head
  • ECG-JEPA (multiblock / random): 768-d pooled embeddings
  • Lead selection by name — send a 12-lead strip to an 8-lead model unchanged
  • Fails closed when a classify response lacks the screening-framing marker

Use cases​

  • Screen MCT/Holter strips for 150 rhythm and morphology labels
  • Produce cardiac embeddings for similarity search and probe training
  • Feed signal_findings to reasoner nodes under the authoritative-payload contract

Runtime​

  • Performance tier: variable

Input ports​

NameTypeRequiredDescription
stripsjsonNoArray of strips from ecg-strips-source (each with channels, leads, sample_rate_hz, gain_uv_per_lsb). Preferred input.
waveformjsonNoSingle waveform as a 2-D array [leads][samples] in mV (or raw counts with gain_uv_per_lsb). Used when no strips input is wired.
sample_rate_hznumberNoSample rate of the waveform input (required with waveform).
leadsjsonNoLead names for each waveform row, standard 12-lead order assumed when omitted.
gain_uv_per_lsbnumberNoµV per LSB when waveform carries raw ADC counts instead of mV.

Output ports​

NameTypeRequiredDescription
findingsjsonNoOne finding per waveform: model provenance (id + weights sha256), embedding or ranked screening scores with framing, quality block, timing.
successbooleanNoTrue when every waveform produced a finding.

Settings​

Basic​

SettingNameTypeRequiredDefaultAllowed valuesDescription
Model IDmodelstringYesSignal model id from the service's /v1/models (e.g. ecgfounder-12lead, ecgfounder-1lead, ecg-jepa-multiblock).
OperationoperationenumYesclassifyclassify, embedclassify: ranked screening scores (ECGFounder models only). embed: fixed-dimension embedding.
Top Ktop_knumberNo0Keep only the K highest scores (classify). 0 returns all 150 labels.
Score ThresholdthresholdnumberNo0Drop scores below this value (classify). 0 keeps everything.

Advanced​

SettingNameTypeRequiredDefaultAllowed valuesDescription
Timeout (s)timeout_secondsnumberNo120Per-request timeout. Must cover the service's documented cold start when min-instances is 0.
Service URLservice_urlstringNoOverride the signal service base URL (default from SIGNAL_SERVICE_URL).

Errors​

CodeDescription
SIGNAL_CONFIGMissing model/operation config or no waveform input wired
SIGNAL_REQUESTThe signal service was unreachable or returned an error
SIGNAL_FRAMINGA classify response lacked the screening-framing marker and was refused

Runtime notes​

  • Requires SIGNAL_SERVICE_URL (or the service_url config). Auth: SIGNAL_SERVICE_TOKEN for dev, GCE metadata OIDC identity token in production (Cloud Run IAM perimeter).
  • Scores are screening output with documented operating points, not diagnoses; keep the verifier chain downstream (RiskTier C applies when findings reach patient-facing content).
  • Wire strips from ecg-strips-source for the PHI-clean path; inline waveform input is intended for research graphs.

See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.

¿Algo no está claro? Envíe sus comentarios sobre la documentación por correo electrónico..