[latexr]

> My thought process is that any on-cat device is going to have a lot of false positives since cats' movements can be so unpredictable.

OP mentioned seizures usually last at least 3 minutes so there might be enough time for corrections (e.g. weird movements for 10 seconds then stopping may not warrant an alarm).

Having some amount of false positives might be desirable, at least at first, to calibrate expectations. Certainly many false positives are worth it when you consider a single false negative could be fatal.

[CitrusFruits]

Yeah that's fair pushback. Maybe the video approach could be a secondary confirmation then? I imagine it's pretty easy to confirm in video that the cat isnt moving location-wise, and you can cross-reference that with rapid movement detection on some sort of gyroscope enabled device.