Perioperative Electroencephalography to predict Postoperative Delirium (POD)

Details

Supervisors

Mouraux, André ; Standaert, François-Xavier

Faculty

Ecole polytechnique de Louvain

Degree label

Master [120] : ingénieur civil biomédical, à finalité spécialisée

Abstract

Postoperative delirium (or POD) is a potentially life-threatening neurocognitive disorder that regularly occurs after sternum opening heart surgery. The study of EEG signals, biological signals from the patient's scalp during surgery will be investigated. Using statistical and learning tools to obtain information about the dataset, we will try to implement a classification model to know if this patient will develop delirium or not after the operation, and thus take better care of him and adapt his treatment. In this thesis, we have tried, thanks to features extracted in the Wavelet space (time-frequency domain), to classify our data from a single measurement per patient, with a set of 130 patients. This information from one measurement per patient remains insufficient to classify, having moreover an unbalanced data set. However, thanks to Bayes and the hypothesis of dividing the data set into 2 independent measures, our data set is slighly better classified with a better classification score, which suggests a cruel lack of information in our starting data set.