injection needed to produce one spike; (5) the number determined in the fourth feature normalized by the total number of spikes as in the first feature; (6) the number of spikes in the first three current injections as in the fourth feature divided by the number of spikes in the next three current injections; (7) the normalized sodium currents at −20 mV (normalized by cell capacitance); and (8) the fast potassium currents at 20 mV divided by the slow potassium currents at 20 mV. The features were quantized into two levels. The distribution of each of the features was learned on the training data set: Pr{fi=xj|LR}=∑mδ[xj/LR]∑j∑mδ[xj/LR] and Pr{fi=xj|NR}=∑mδ[xj/NR]∑j∑mδ[xj/NR], where m is the number of sample from the training set. The test set was the recordings of the remaining (new to the model) patient, whose samples were not used to train the model, We used an NB classifier, which assumes statistical independence between the features, and so the likelihood of obtaining features f1, f2, …, fn from the positive or negative set is given by: Pr{f1,f2…fn|LR}=Pr{f1|LR}×Pr{f2|LR}×…×Pr{fn|LR},Pr{f1,f2…fn|NR}=Pr{f1|NR}×Pr{f2|NR}×…×Pr{fn|NR}We classified according to the maximal posterior probability and generated a score that was the ratio of the two posterior probabilities Pr{LR|f1,f2,…fn)=Pr{f1,f2,…fn|LR}∗Pr{LR}Pr{f1,f2,…fn}, Pr{NR|f1,f2,…fn)=Pr{f1,f2,…fn|NR}∗Pr{NR}Pr{f1,f2,…fn}Since when we have
