Astrocytic signatures in neuronal activity: a machine learning-based identification approach

This study investigates the expanding role of astrocytes, the predominant glial cells, in brain function, focusing on whether and how their presence influences neuronal network activity. We focus on particular network activities identified as synchronous and asynchronous. Using computational modeling to generate synthetic data, we examine these network states and find that astrocytes significantly affect synaptic communication, mainly in synchronous states. We use different methods of extracting data from a network and compare which is best for identifying glial cells, with mean firing rate emerging with higher accuracy. To reach the aforementioned conclusions, we applied various machine learning techniques, including Decision Trees, Random Forests, Bagging, Gradient Boosting, and Feedforward Neural Networks, the latter outperforming other models. Our findings reveal that glial cells play a crucial role in modulating synaptic activity, especially in synchronous networks, highlighting potential avenues for their detection with machine learning models through experimental accessible measures.

The online version contains supplementary material available at 10.1007/s11571-025-10276-4.