TABLE 2.
Safety and appropriateness of triage recommendations for doctors and the Babylon Triage and Diagnostic System (Babylon AI) against a range of acceptable recommendations provided by an independent judge.
| Safety(95% CI) | Appropriateness(95% CI) | Number of vignettes | |
|---|---|---|---|
| Doctor A | 95.7 | 91.5 | 47 |
| Doctor B | 89.7 | 89.7 | 78 |
| Doctor C | 100.0 | 93.8 | 48 |
| Doctor D | 94.1 | 94.1 | 51 |
| Doctor E | 90.0 | 85.7 | 70 |
| Doctor F | 94.1 | 90.2 | 51 |
| Doctor G | 88.2 | 88.2 | 51 |
| Doctor average | 93.1 | 90.5 | 56.6 |
| — | (89.6–96.6) | (87.9–93.0) | — |
| Babylon AI | 97.0 | 90.0 | 100 |
The Babylon Triage and Diagnostic System gives safer triage recommendations than the doctors on average, at the expense of a marginally lower appropriateness.