> More specifically, the training for SAD required three main steps. First a positive association is created between the scent of a seizure and treats in order to induce a conditioned emotional response.

The paper goes into a bit of detail on training, but it's a fair and interesting point: How do they get the seizure scent? I guess you could maybe take a sample just after a seizure, or a second person could do it if they were present and prepared to take it.