The EEG has been around for almost 100 years since its first application in the 20s of the last century by Hans Berger. The very complex information it carries about ongoing neuronal activity at a millisecond scale reflect the brain mechanisms and brain states in an unprecedented manner.
To make use of these information contained within electrophysiological time series, the data has to be analysed with modern methods for data processing such as deep learning algorithms or vigilance analysis. The combination of complex data with state-of-the-art algorithms allows the extraction of clinically relevant information that can be used in neuropsychiatric disorders and symptoms.
In different psychiatric disorders, e.g. major depressive disorder (MDD) , it has been shown, that certain patterns in EEG data can predict treatment outcome to e.g. SSRI, SNRI or ECT therapy. However, there is a clear lack of replication and cross validation of a long list of potential EEG and ECG markers. This still prevents these markers of brain function to enter a clinical stage where they can be used to improve the way we chose treatment options for our patients. Therefore, we apply high dimensional EEG measurements to patients suffering from MDD and try to predict the probabilities for certain interventions to improve the symptoms.
Besides the diagnostic entities, our team also is interested in diagnosis-overlapping symptoms such as suicidality. Since suicide is one of the most frequent causes of death in the adult population between 14 and 65 years according to the WHO, a better understanding of the underlying causes and the identification of possible electrophysiological markers for the best treatment options is of great importance. This also includes psychotherapy interventions for prevention of repeated suicide attempts.
Autonomous Nervous System (ANS)
Wakefulness Regulation (Vigilance)
Deep Learning Algorithms (DL)
Major Depressive Disorder (MDD)
Autism Spectrum Disorder
Obsessive Compulsive Disorder (OCD)
Suicidality and Suicide
Research Projects (Selection)
- Deep Learning for Prediction “DeepPsy”: A platform for helping to improve the treatment for psychiatric disorders (Startup)
- EASI – Evaluation des Attempted Suicide Short Intervention Program (ASSIP): eine randomisierte kontrollierte klinische Studie (2019 – 2022)
- EASI multicenter - Evaluation des Attempted Suicide Short Intervention Program (ASSIP): eine multizentrische naturalistische Beobachtungsstudie (Annia Rüesch, Tania Villar and Christoph Hörmann, 2019-2022)
- Consortium for Sharing Electrophysiological data to improve Treatment Prediction in Psychiatry (CONSET) (Start 2020)
- Autismus-Spektrum-Störungen: Diagnostik und Suizidalität (Verantwortliche Tania Villar)
- Psychosis: EEG for prediction of symptom trajectories (Doctoral thesis Amexi Grammato)
- Heart Rate Variability for the prediction of Ketamine Treatment in MDD (Thorsten Meyer)
- High Frequency EEG and direct representation of Thoughts (Read-Out)