Learning Synchronization Patterns in Neural Signal

The human brain is the most complex system studied by science and bringing inspiration for emerging technologies. Over the last decade, the study of brain function has witnessed a pivotal change of focus from investigating the localization of specialized brain areas to investigation of spatially distributed brain networks. This paradigm shift was possible due to intensive development in the field of synchronization of nonlinear systems. In the proposed project we will use the concept of synchronization of nonlinear dynamical systems as the basis for development of the methods and algorithms for detection, characterization and modelling of interactions and dependence patterns in multivariate nonlinear time series. In particular, we will test changes of synchronization patterns of scalp electroencephalogram (EEG) of depressive patients as predictors of antidepressant therapeutic efficacy. We will tailor the developed methods to specific properties of EEG, in order to better understand synchronization phenomena in the human brain. The overall structure of EEG synchronization i.e. the synchronization patterns - will be considered as an approach for description of brain states and their changes due to mental disorders. The developed methods will be applicable not only in analysis of electrophysiological signals in neurology and psychiatry, but generally in analysis of complex multivariate and multiscale signals. We will classify the EEG synchronization patterns and their changes by computer science methods inspired by the brain itself neural networks, machine learning an data mining. The particular application, proposed in the project, promises high impact for society, since depression is a major cause of morbidity worldwide. In EU countries the occurrence of depressive disorders counts between 2.6 4.5% for males and 7.1 10.4% for females. Modern antidepressant drugs have a response rate only up to 65% and the response requires usually 46 weeks of treatment. Potential ability to predict response to treatment, either early in the course of therapy or before treatment even begins, can avoid trials of ineffective therapy and save patients from prolonged intervals of suffering. Also economic aspects of the possibility of early choice of an effective therapy are indisputable.

Being able to tell early whether an antidepressant will help a person with major depression could spare patients weeks of uncertainty and suffering. In this project, we showed that non-invasive brainwave recordings taken after just one week of treatment can be used to predict the likely treatment outcome with promising accuracy. Depression is a common and serious illness that affects daily life, work, and relationships. Globally, hundreds of millions of people live with depression. Although effective treatments exist, many patients do not benefit sufficiently from the first medication that is tried. In clinical practice, doctors often need about 4-6 weeks before they can confidently judge whether a medication is working, which can delay switching to a more suitable option. To address this, we analyzed electrical brain activity recordings (EEG) from patients on day 7 of antidepressant treatment. We tested different ways of describing these EEG signals, i.e. we extracted different features from the EEG recordings primarily capturing synchronization patterns between brain regions, and trained machine learning models to learn the difference between people who later improved and those who did not. In addition, we explored whether patients can be grouped into meaningful subtypes based on similarities in their brain activity patterns-an approach that may help explain why the same treatment works well for some people but not for others. The strongest results came from focusing on short, recurring signal patterns in the EEG (a "motif"-based approach). Using this method, we correctly predicted treatment outcome for 73% of patients in an independent validation group. This is a key scientific advance: it demonstrates that early EEG patterns can contain practical information about later treatment success, and it identifies a particularly effective way to extract that information. If confirmed in larger studies, this approach could support earlier, more personalized treatment decisions-helping patients reach an effective therapy sooner, reducing avoidable side effects and suffering, and potentially saving healthcare resources.