sources_and_stuff

"It’s the variability that really makes it so stress-
ful. You never know when it is going to be chaos
again and you’ll have one. Just because this morn-
ing is terrific doesn’t mean tonight is going to be
terrific, either behavior-wise, medication-wise, or any
other-wise. So it is the unpredictability of it that is
really nerve-racking to live with.""

-Murray, Coping with the uncertainty of uncontrolled
epilepsy, Seizure 2 (1993) 167–178

"However, from the clinical point of view, no
significative practical advance has been verified: there is not any system usable
by patients allowing them to predict a coming seizure and to take action to
preserve his (her) safety and privacy, improving substantially his (her) social
integration. This is probably because most of the researchers look for a general
method and algorithm that would work for every patient. And although several
authors propose methods to which they claim a high performance, the considered
performance criteria is only partial, neglecting other parts of the problem that
prevent them to be used in a clinical environment."
-V. K̊urkov ́a et al. (Eds.): ICANN 2008, Part II, LNCS 5164, pp. 479–487, 2008.

Maiwald, Thomas, et al. "Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic." Physica D: nonlinear phenomena 194.3 (2004): 357-368.

Howbert JJ, Patterson EE, Stead SM, Brinkmann B, Vasoli V, Crepeau D, Vite CH, Sturges B, Ruedebusch V, Mavoori J, Leyde K, Sheffield WD, Litt B, Worrell GA (2014) Forecasting seizures in dogs with naturally occurring epilepsy. PLoS One 9(1):e81920.