Mouraux, AndréStandaert, François-XavierChiliatte, YsalineYsalineChiliatte2025-02-042025-02-042021https://dial-mem.test.bib.ucl.ac.be/handle/123456789/24346Persistent Post Surgical Pain (PPSP) is currently a great challenge to improve the quality of life of individual after a surgery. Recent findings suggest a link with frequency content of the brain especially in the alpha band. This master thesis aims to use machine learning tools in order to predict the predisposition of an individual for PPSP. Other frequencies than the alpha band were found to be linked with PPSP as well such as the theta band. Several machine learning models were tested and the best results were achieved with the Extreme Gradient Boosting Classifier for which it was possible to predict whether the individual is likely to develop PPSP with 0.8310 of accuracy score and 0.7692 of recall score which was statistically higher than the random guess.Persistent postsurgical painElectroencephalographyMachine learningtext::thesis::master thesisthesis:33116