Eval Metrics
all demo dataPowered by Arize Phoenix · Last updated: just now
Cases processed
20
Urgency accuracy
90%
Guideline accuracy
88%
Avg confidence
85%
Routed to human
10%
Patients reached
85%
Confusion matrix — Predicted vs. actual urgency
Diagonal = correct predictions
| Predicted → | Urgent | Short interval | Routine | No follow-up |
|---|---|---|---|---|
| Urgent | 5 | 0 | 0 | 0 |
| Short interval | 0 | 6 | 1 | 0 |
| Routine | 0 | 0 | 5 | 0 |
| No follow-up | 0 | 0 | 0 | 3 |