BRAIN+2: Characterization of EEG Signals in Patients with Anxiety

The BRAIN +2 project addresses the critical need to improve clinical anxiety diagnoses through advanced analysis of electroencephalographic (EEG) signals. Despite the high global prevalence of anxiety disorders, early identification remains a challenge. This transdisciplinary study, led by the Universidad Politécnica Salesiana and the Neuroscience Institute of the Universidad Católica de Cuenca, proposes a robust methodology for characterizing specific biomarkers. The technical approach includes signal pre-processing for artifact removal, spectral power analysis across frequency bands (alpha, beta, theta, delta), and the study of functional brain connectivity. By implementing machine learning algorithms in Matlab, the project seeks to model and classify patterns that can predict the presence or severity of anxiety. Expected outcomes include the creation of a diagnostic support tool, the publication of indexed scientific articles, and capacity building for health professionals and students. This joint effort not only strengthens neuroscientific research in the region but also provides a scalable technological solution to improve diagnostic accuracy and medical care for patients with anxiety disorders.<br/><br/><b>Goal</b>: <br/>Identify biomarkers associated with anxiety through the processing and analysis of EEG signals, using a database of control and pathological groups. The goal is to develop an artificial intelligence-based algorithm to quantify anxiety risk early and accurately.<br/><br/><b>Research lines</b>: <br/>Signal processing and prediction algorithm