Table 2. Individual algorithm performance.
| Animal ID | Algorithm detection (Y/N) | Time prior to pH drop (based on algorithm) | Expert detection (Y/N) | Time prior to pH drop (based on expert) | Comments |
| N/UCO group | |||||
| 461060 | Y | 1:10:00 | Y | 1:15:06 | Noisy |
| 473352 | Y | 0:33:40 | Y | 0:37:27 | |
| 473378 | Y | 0:30:00$ | Y | 0:32:29 | Noisy |
| 473361 | Y | 0:28:20 | Y | 0:27:59 | |
| 5054 | Y | 0:30:00 | Y | 0:27:17 | |
| 473727 | Y | 1:55:00 | Y | 1:52:17 | |
| 473377 | Y | 1:41:40 | Y | 1:41:51 | |
| 473360 | N | N/A | Y | 0:19:46 | Noisy |
| 5060 | N | N/A | Y | 0:20:41 | Noisy |
| H/UCO group | |||||
| 473351 | Y | 0:43:20 | Y | 0:38:29 | |
| 473376 | Y | 1:03:20 | Y | 1:07:43 | |
| 473726 | Y | 1:11:40 | Y | 1:17:37 | |
| 8003 | N | N/A | Y | 0:12:20 | Too short§ |
| 473362 | N | N/A | N | N/A | Noisy |
| LPS/UCO group | |||||
| 4934 | N | N/A | Y | 0:34 | |
| 4935 | N | N/A | N | N/A | UCO ruptured♯ |
| 5051 | N | N/A | N | N/A | UCO ruptured♯ |
| 5053 | N | N/A | Y | 0:37 | Noisy |
| 5059 | N | N/A | N | N/A | UCO ruptured♯ |
| 8002 | N | N/A | Y | 0:41 | |
N/UCO, normoxic UCO group; H/UCO, UCO group that was hypoxic prior to UCO start; LPS/UCO, UCO group that received LPS prior to UCO start.
Detection based on two subsequent crossing points, as opposed to three elsewhere.
♯ umbilical cord occluder ruptured during the experiments stopping worsening acidemia from developing further; consequently, no adaptive brain shut-down occurred and these foetuses were used as negative controls.
EEG-FHR synchronization pattern emerged too shortly prior to pH drop to <7.00 and the algorithm failed to pinpoint even two consecutive positive detections to define synchronization. Clinical benefit of such short time lag prior severe acidemia is also nearly absent, so that this case may represent a limitation of not only the algorithm, but also the clinical utility of the phenomenon itself, even when EEG and FHR are monitored directly visually.