Monitor numerics describe the past, never the future¶
Every monitor numeric describes a window of 3–30 s or more that ended 1–9 s before its stamp. None is stamped before its data exist, so the stamps already respect the availability rule.
| Status | established: shown on many cases, with a control. |
| Devices | Solar8000 monitor, Primus anaesthesia machine, BIS monitor |
| Variables | Solar8000 heart rate, Solar8000 ART and CVP numerics, Primus ETCO₂, PIP and RR, BIS index, SpO₂, Solar8000 pulse rate (PLETH_HR) |
What it means¶
Aligning a numeric with the waveform it came from means shifting it back by its delay and spreading it over its window. Left at its stamp, it is safe for real-time models but late for physiology.
What is done about it¶
The TimeNet import labels each numeric track with its typical delay and window (numeric_lag), and per-case labels carry each case's own delay. Stored times are never moved.
Evidence¶
| Study | Date | Status | Summary |
|---|---|---|---|
| How the BIS index trails its EEG | 2026-10-13 | current | Modelling the BIS index as a lagged mix of EEG features shows a trailing average starting about 3 s after its EEG window ends: about 16 s long in half the cases (the 15 s smoothing setting) and 32–61 s in most others. Half the response weight is older than 30 s. |
| How the monitors compute their numbers | 2026-10-12 | current | Recomputing each monitor numeric from its own waveform finds a short, simple algorithm for every one (a median, an exponential average or a time mean over 3–30 s) and a delay of 2–9 s behind the newest data it uses. No value is stamped before its data exist. |
| Numeric delays are fixed within a case, different between cases | 2026-10-12 | current | With each numeric's algorithm held fixed, delays were fitted for every case and every 30-minute block. They do not drift within a case, but 40–70% of their variance lies between cases, so a single population delay is wrong by up to 2 s for HR and 1 s for the others. Each case gets its own delay label. |