How to Start a New Label Generation

Label generation is the first step in equipping your human reviewers with super-human speed and scale. We recommend generating labels iteratively as described here.

To generate labels

Start a New Label Generation
- Go to the dashboard.
- Click Label Generation.
- Click Set Up New Generation.
1. Patients
  - Batch of Patients (default) — Generates labels for a random batch of patients that hasn't been generated yet. Choose a batch size — we recommend starting with 1 to verify results before scaling up.
  - Specific Patients — Enter one or more MRNs to generate labels for a targeted set of patients. Useful when debugging or reviewing a known case.
  - All Patients — Generates labels for every patient in your dataset. Note: this can be data- and time-intensive for large datasets. We recommend working in batches when possible.
2. Filter By (optional)
  - Use the Variables and Variable Values filters to narrow down which variables and notes are included in this generation. Useful for reducing compute costs and speeding up targeted runs. See: Conditional Generation for Variables.
3. Overwrite Existing Labels
  - Replace all AI-Generated Values Only (default) — Regenerates any AI-drafted labels that haven't been reviewed by a human, while preserving human-reviewed values.
  - Replace all Human and AI-Generated Values — Regenerates everything, including labels a human reviewer has already edited. Use with caution.
  - Skip It — Leaves all existing labels as-is. Only generates values where none currently exist.
4. Advanced Settings — Scope (optional)
  - All (default) — Runs the full generation pipeline. This is correct for most runs.
  - Variables — Runs only the variable extraction step.
  - Variable Aggregation — Runs only the aggregation step.
  - Dependent Variables — Runs only variables that depend on the output of other variables.
  - Use non-default scope options only when debugging or rerunning a specific processing step.
5. Click Generate.