Discrimination between migraine patients and normal subjects based on steady state visual evoked potentials: discriminant analysis and artificial neural network classifiers.

Fifty-one migraine patients and 19 control subjects were examined by steady state visual evoked potentials (SSVEPs) procedure. The aim of this study was to develop a discriminant analysis and an artificial neural network (NN) classifier in order to discriminate between migraneurs during attack-free periods and normal subjects. Discriminant analysis correctly classified 72.5% of migraine patients with a false positive rate of 36.8%. The NN method had a sensitivity of 100% with a false positive rate of 15%. The results of this study confirm SSVEP pattern as a marker of migraine and demonstrate that NNs could be a useful method in the statistical analysis of topographic EEG data.

Steady-state visual-evoked potentials in headache: diagnostic value in migraine and tension-type headache patients.

We tested the hypothesis that migraine and tension-type headache are separate disorders based on visual evoked potentials. We recruited 120 migraine without aura patients (MwoA), 64 tension-type headache patients (TTH), and 51 healthy controls. We performed discriminant analysis combined with a stepwise selection of predictors. Mean values of the F1 component were significantly increased over Fp1, C3, P4, O2 and O1 electrodes in MwoA and TTH patients compared with normal subjects. Only the control subjects were correctly distinguished. The increased brain response to visual stimulation detected in both MwoA and TTH may suggest a common neuronal dysfunction in the two headache subtypes.

EEG spectral analysis in migraine without aura attacks.

In 16 patients suffering from migraine without aura, we examined quantitative EEG and steady-state visual evoked potentials (SSVEPs) at 27 Hz stimulation during the critical phase of migraine and in attack-free periods. The main spontaneous EEG abnormalities found during the critical phase were the slowing and asymmetry of the dominant frequency in the alpha range. The amplitude of the SSVEP F1 component was significantly reduced during the attack phase compared with the intercritical phase; in the latter condition the visual reactivity to 27 Hz stimulus was increased over almost the entire scalp compared with normal subjects. The EEG abnormalities confirm a fluctuating modification of alpha activity during the migraine attack, probably related to a functional disorder. The suppression of visual reactivity during the migraine attack could be related to a phenomenon of neuronal depolarization such as spreading depression, occurring in a situation of central neuronal increased excitability predisposing to migraine attacks.

Photic driving response in primary headache: diagnostic value tested by discriminant analysis and artificial neural network classifiers.

The aim of this study was to discriminate migraine patients (MWoA) from tension-type headache (TTH) patients and normals in order to confirm that the photic driving response in the medium frequency range is a marker of migraine and to test the hypothesis that MWoA and TTH are separate disorders based on electrophysiological pattern. We recruited 120 MWoA patients, 64 TTH patients, and 51 healthy controls without any history of headache or of migraine inheritance, according to International Headache Society (IHS) criteria. The classification method was discriminant analysis using both linear discriminant analysis with a stepwise selection of predictors and an artificial neural network classifier (NNs). The mean amplitude of the first harmonic elicited by flash stimulation in the 15-27 Hz range was significantly increased over Fp1, C3, C4, P4, O2, and O1 electrodes in MWoA and TTH patients in comparison with normal subjects. Using both classification methods, only the control subjects were correctly distinguished. When only the patient groups were matched, no significant difference was detectable. The increased brain response to visual stimulation detected in both migraine and TTH suggests a common neuronal dysfunction in the two headache subtypes.