Gradient Biotech

Quick start

This walkthrough covers a single ECG recording from upload to interpretation.

1. Create a study

Click Create study. Enter a name (for example ECG demo) and optional description.

2. Upload a recording

Open Upload and add either:

  • CSV — one file with time (seconds) and ECG amplitude columns
  • WFDB — .hea and .dat together (PhysioNet-style)

Don't have a recording handy? See Sample data for a free, publicly downloadable ECG recording you can upload right away.

3. Run preprocessing

Go to Analyze → Signal Explorer, pick your dataset from the dropdown, then click Run preprocessing on the Overview tab. Wait for the job to complete — watch the Jobs panel in the navbar.

4. Compute HRV

When preprocessing completes, click Compute HRV on the same tab. Review time-domain metrics (SDNN, RMSSD, mean HR) and frequency metrics (LF, HF, LF/HF) in the HRV panel.

5. Explore the signal

Switch to the Explorer tab (still inside Signal Explorer). Pan and zoom the downsampled waveform. R-peak markers overlay the trace; low-quality segments may be highlighted when SQI is poor.

6. Interpret (optional)

Open the HRV run from the Runs tab or the recent-runs panel, and click Interpret on the run detail page for a plain-language summary that cites your computed metrics. Or, once you have a few completed runs, use the study-level Interpret tab to generate one grounded summary across everything completed so far.

If Interpret isn't available in your workspace, ask your administrator to enable AI interpretation.

Next steps