Triage

Rule-based tiers, retrospective model evaluation, and (below) live triage.

Retrospective triage case IDs by tier
Model Predicted Triage (live database)

The saved triage model (e.g. random forest) is run on every case currently in the database — same implementation as live triage (triage_bundle.joblib). Tiers are computed on demand.

Triage model evaluation

Same pipeline as scripts/test_triage.py / train_triage_model.py: rule-based priority scores from triage_cases are binned into tiers; a random forest or shallow tree learns structured tags to predict those tiers on a held-out 20% test set (80% train), with a fixed split so results are comparable between runs.

Parameters

Labels are quantile bins of normalized rule scores (low / medium / high). This is a research view of how well extracted features recover the current rules—not investigator ground truth.

Live Triage Paste narratives

Paste one or more case narratives below. Start each case with Case N : case summary; the next Case line starts the following case. You can also paste a single narrative with no headers; it will be treated as one case.

Expected shape (example): Case 1 : First narrative text… Case 2 : Second narrative… Case 3 : …
Privacy — nothing is stored
  • Text you enter here is not written to the database or saved anywhere on the server.
  • When live triage runs, the model is called on this text in memory and cases are classified only for this session.
  • After classification, no case text, extracted features, or triage results are retained.