Epilepsy surgery is effective in reducing both number and frequency of seizures, particularly in patients with temporal lobe epilepsy (TLE). However, a significant proportion of these patients continues suffering seizures after surgery.

In order to have information about the results before surgery, researchers from the Computational Intelligence Group of the Schools of Computing UPM assessed the influence of a battery of medical and psychological factors using predictive models developed from machine learning approaches.

They have identified three "very relevant" elements: the hemisphere of seizure origin, intelligence quotient and personality style (applying the Rorschach test). Researchers have obtained a success rate of 90% in terms of predicting the outcome after surgery by using advanced mathematical models for its combination.

From the researcher's point of view, this study opens the door for integration of complex mathematical models in previous assessment of surgeries. The team of medical assessor will have numerical results about the success of the surgery which are known as decision support tools.

Story Source:

Materials provided by Universidad Politécnica de Madrid. Note: Content may be edited for style and length.

Journal Reference:

1. Armañanzas, R., Alonso-Nanclares, L., DeFelipe-Oroquieta, J., Kastanauskaite, A., de Sola, R.G., DeFelipe, J., Bielza, C. & Larrañaga. Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery. PLoS ONE, April 2013