Presentation | Interpreted risk by participants | Clinical scenarios (gold standard) | Performance | |||
---|---|---|---|---|---|---|
Low risk | Medium risk | High risk | Precision | Recall | ||
Baseline | Low | 14 | 10 | 2 | 0.54 | 0.70 |
Medium | 5 | 6 | 7 | 0.33 | 0.30 | |
High | 1 | 4 | 11 | 0.69 | 0.55 | |
Contextualised | Low | 13 | 9 | 2 | 0.54 | 0.65 |
Medium | 6 | 6 | 4 | 0.38 | 0.30 | |
High | 1 | 5 | 14 | 0.70 | 0.70 | |
Grouped | Low | 11 | 9 | 3 | 0.48 | 0.55 |
Medium | 7 | 5 | 6 | 0.28 | 0.25 | |
High | 2 | 6 | 11 | 0.58 | 0.55 |