Convolutional Neural Network Classification of Topographic Electroencephalographic Maps on Alcoholism.

Alcohol use is a leading risk factor for substantial health loss, disability, and death. Thus, there is a general interest in developing computational tools to classify electroencephalographic (EEG) signals in alcoholism, but there are a limited number of studies on convolutional neural network (CNN) classification of alcoholism using topographic EEG signals. We produced an original dataset recorded from Brazilian subjects performing a language recognition task. Then, we transformed the Event-Related Potentials (ERPs) into topographic maps by using the ERP's statistical parameters across time, and used a CNN network to classify the topographic dataset. We tested the effect of the size of the dataset in the accuracy of the CNNs and proposed a data augmentation approach to increase the size of the topographic dataset to improve the accuracies. Our results encourage the use of CNNs to classify abnormal topographic EEG patterns associated with alcohol abuse.

Pharmacological characterisation of anticonvulsant effects elicited by erythrartine.

OBJECTIVES: The erythrinan alkaloids erythravine and 11α-hydroxy-erythravine from Erythrina verna (Vell.) have been extensively investigated for their anxiolytic and anticonvulsant effects. Both are structurally similar to the erythrartine that also exhibit anxiolytic effects, but there is no report on its anticonvulsant potential. Since some anxiolytic drugs can be useful in the management of epileptic seizures, we investigated whether erythrartine could prevent seizures induced by different chemoconvulsants. METHODS: Experiments were performed using different concentrations of erythrartine injected via intracerebroventricular in rats submitted to pilocarpine, kainic acid, pentylenetetrazol or picrotoxin-induced seizures. Moreover, the rotarod test was performed to verify the effects of erythrartine on animal motor coordination. RESULTS: Our data showed for the first time that erythrartine prevented the occurrence of seizures induced by all of the chemoconvulsants tested and did not affect locomotor performance neither produced sedative effect on animals. CONCLUSION: Obtained results validate the ethnopharmacological significance of E. verna and provide new information on erythrartine, another erythrinian alkaloid of biotechnological and medicinal interest.

Neuroprotective effects and improvement of learning and memory elicited by erythravine and 11α-hydroxy-erythravine against the pilocarpine model of epilepsy.

Deficits in cognitive functions are often observed in epileptic patients, particularly in temporal lobe epilepsy (TLE). Evidence suggests that this cognitive decline can be associated with the occurrence of focal brain lesions, especially on hippocampus and cortex regions. We previously demonstrated that the erythrinian alkaloids, (+)-erythravine and (+)-11α-hydroxy-erythravine, inhibit seizures evoked in rats by different chemoconvulsants. AIMS: The current study evaluated if these alkaloids would be acting in a neuroprotective way, reducing hippocampal sclerosis, and consequently, improving learning/memory performance. MAIN METHODS: Here we confirmed the anticonvulsant effect of both alkaloids by means of the pilocarpine seizure-induced model and also showed that they enhanced spatial learning of rats submitted to the Morris Water Maze test reverting the cognition deficit. Additionally, immunohistochemistry assays showed that neuronal death and glial activation were prevented by the alkaloids in the hippocampus CA1, CA3 and dentate gyrus regions at both hemispheres indistinctly 15 days after status epilepticus induction. KEY FINDINGS: Our results show, for the first-time, the improvement on memory/learning elicited by these erythrinian alkaloids. Furthermore, data presented herein explain, at least partially, the cellular mechanism of action of these alkaloids. Together, (+)-erythravine and (+)-11α-hydroxy-erythravine seem to be a promising protective strategy against TLE, comprising three main aspects: neuroprotection, control of epileptic seizures and cognitive improvement. SIGNIFICANCE: Moreover, our findings on neuroprotection corroborate the view that seizure frequency and severity, hippocampal lesions and memory deficits are interconnected events.