Gradient Biotech

Pipelines

Every analysis step you run — from a button in the Dataset inspector, Bulk Pipelines, or Cohort comparison — maps to one of these pipelines. This reference lists what each one takes as input and produces as output, so you know what to run and in what order.

ECG

PipelineInputOutputs
preprocess_ecgWFDB, CSV, or EDF waveformR-peaks, RR intervals, SQI, artifact rate, waveform preview
compute_hrvPreprocess run, RR artifact, or RR CSV uploadTime/frequency/nonlinear HRV plus advanced metrics (SDANN, DFA, entropy, fragmentation, PRSA AC/DC) and selectable PSD method (Welch/Lomb/multitaper/Burg)
full_ecg_analysisWFDB, CSV, or EDF waveformChained preprocess + HRV in one run
delineate_ecgECG waveform (+ optional preprocess run)P/Q/R/S/T fiducials; PR, QRS, QT/QTc, ST, T-wave morphology
compute_arrhythmia_burdenRR intervals from preprocessIrregularity %, pause burden, beat flags
windowed_hrvPreprocess run, RR artifact, or RR CSVSliding-window HRV, quality/missingness, trends, feature matrix

Wearable modalities and motion

PipelineInputOutputs
analyze_edaEDA CSVTonic (SCL) / phasic decomposition, skin conductance responses (SCRs)
analyze_accACC CSV (time + x/y/z or magnitude)ENMO activity intensity, motion burden, per-window activity
motion_qualityECG preprocess run + ACC runMotion burden %, % of beats during motion, high-motion intervals

RR-only

PipelineInputOutputs
compute_hrvRR CSV (format=rr_csv)HRV metrics without waveform preprocess

PPG

PipelineInputOutputs
preprocess_ppgPPG waveformPulse peaks, IBI intervals, quality, preview
compute_prvPPG preprocess runPulse rate variability metrics
analyze_ppg_morphologyPPG waveform (+ optional preprocess run)Per-pulse amplitude, rise/decay time, width, area, dicrotic notch
compute_pttECG preprocess run + PPG runPulse arrival/transit time (R-peak → PPG foot/peak), per-beat PAT/PTT

Blood pressure

PipelineInputOutputs
analyze_bpBP CSVSBP/DBP/MAP means, variability, dipping classification
analyze_abpABP waveform CSV (signal_type=abp)Beat-level SBP/DBP/MAP, pulse pressure, instantaneous HR, max upstroke dP/dt

Respiration and coupling

PipelineInputOutputs
analyze_respirationRespiration channelRate, breath timing, quality
compute_rsaECG preprocess + respiration runRespiratory sinus arrhythmia metrics
compute_baroreflexHRV/RR run + BP runBaroreflex sensitivity — sequence method + cross-spectral transfer function (TF gain, coherence, phase, latency)

Cohort

PipelineInputOutputs
cohort_summaryStudy subjects with completed HRVGroup means, SDs, p-values, plot series
cohort_windowed_summarySubjects with completed windowed HRVGroup comparison on per-subject medians and across-window CV
compute_risk_scoresCohort with outcomes metadataResearch-only signal-derived stratification

Analyze → Bulk Pipelines runs any of these across every eligible dataset in the study in one action, instead of one dataset at a time.

Interpretation and reporting

PipelineInputOutputs
interpret_resultsRun ID(s) or cohort contextDescriptive or mechanistic narrative JSON — powers Interpret everywhere it appears

A study-level report bundle with an auto-generated methods section (generate_report) is not yet available from the UI.

Job lifecycle

Every run moves through the same states, shown as a status badge on the run detail page and in the Jobs panel:

pending → running → completed | failed

Versioning

Every run records a pipeline version, visible on the run detail page's Summary tab. Include run IDs and versions in methods sections for reproducibility.