RESUMO
Temporal lobe epilepsy (TLE) is the most common form of focal epilepsy and is associated with a variety of structural and psychological alterations. Recently, there has been renewed interest in using brain tissue resected during epilepsy surgery, in particular 'non-epileptic' brain samples with normal histology that can be found alongside epileptic tissue in the same epileptic patients - with the aim being to study the normal human brain organization using a variety of methods. An important limitation is that different medical characteristics of the patients may modify the brain tissue. Thus, to better determine how 'normal' the resected tissue is, it is fundamental to know certain clinical, anatomical and psychological characteristics of the patients. Unfortunately, this information is frequently not fully available for the patient from which the resected tissue has been obtained - or is not fully appreciated by the neuroscientists analyzing the brain samples, who are not necessarily experts in epilepsy. In order to present the full picture of TLE in a way that would be accessible to multiple communities (e.g., basic researchers in neuroscience, neurologists, neurosurgeons and psychologists), we have reviewed 34 TLE patients, who were selected due to the availability of detailed clinical, anatomical, and psychological information for each of the patients. Our aim was to convey the full complexity of the disorder, its putative anatomical substrates, and the wide range of individual variability, with a view toward: (1) emphasizing the importance of considering critical patient information when using brain samples for basic research and (2) gaining a better understanding of normal and abnormal brain functioning. In agreement with a large number of previous reports, this study (1) reinforces the notion of substantial individual variability among epileptic patients, and (2) highlights the common but overlooked psychopathological alterations that occur even in patients who become "seizure-free" after surgery. The first point is based on pre- and post-surgical comparisons of patients with hippocampal sclerosis and patients with normal-looking hippocampus in neuropsychological evaluations. The second emerges from our extensive battery of personality and projective tests, in a two-way comparison of these two types of patients with regard to pre- and post-surgical performance.
RESUMO
Epilepsy surgery is effective in reducing both the number and frequency of seizures, particularly in temporal lobe epilepsy (TLE). Nevertheless, a significant proportion of these patients continue suffering seizures after surgery. Here we used a machine learning approach to predict the outcome of epilepsy surgery based on supervised classification data mining taking into account not only the common clinical variables, but also pathological and neuropsychological evaluations. We have generated models capable of predicting whether a patient with TLE secondary to hippocampal sclerosis will fully recover from epilepsy or not. The machine learning analysis revealed that outcome could be predicted with an estimated accuracy of almost 90% using some clinical and neuropsychological features. Importantly, not all the features were needed to perform the prediction; some of them proved to be irrelevant to the prognosis. Personality style was found to be one of the key features to predict the outcome. Although we examined relatively few cases, findings were verified across all data, showing that the machine learning approach described in the present study may be a powerful method. Since neuropsychological assessment of epileptic patients is a standard protocol in the pre-surgical evaluation, we propose to include these specific psychological tests and machine learning tools to improve the selection of candidates for epilepsy surgery.
