Online prediction of onsets of seizure-like events in hippocampal neural networks using wavelet artificial neural networks.

It has been previously shown that wavelet artificial neural networks (WANNs) are able to classify the different states of epileptiform activity and predict the onsets of seizure-like events (SLEs) by offline processing (Ann. Biomed. Eng. 33(6):798-810, 2005) of the electrical data from the in-vitro hippocampal slice model of recurrent spontaneous SLEs. The WANN design entailed the assumption that time-varying frequency information from the biological recordings can be used to estimate the times at which onsets of SLEs would most likely occur in the future. Progressions of different frequency components were captured by the artificial neural network (ANN) using selective frequency inputs from the initial wavelet transform of the biological data. The training of the WANN had been established using 184 SLE episodes in 34 slices from 21 rats offline. Nine of these rats also exhibited periods of interictal bursts (IBs). These IBs were included as part of the training to help distinguish the difference in dynamics of bursting activities between the preictal- and interictal type. In this paper, we present the results of an online processing using WANN on 23 in-vitro rat hippocampal slices from 9 rats having 93 spontaneous SLE episodes generated under low magnesium conditions. Over the test cases, three of the nine rats exhibited over 30 min of IB activities. We demonstrated that the WANN was able to classify the different states, namely, interictal, preictal, ictal, and IB activities with an accuracy of 86.6, 72.6, 84.5, and 69.1%, respectively. Prediction of state transitions into ictal events was achieved using regression of initial "normalized time-to-onset" estimates. The SLE onsets can be estimated up to 36.4 s ahead of their actual occurrences, with a mean error of 14.3 +/- 27.0 s. The prediction errors decreased progressively as the actual time-to-onset decreased and more initial "normalized time-to-onset" estimates were used for the regression procedure.