Brain model state space reconstruction using an LSTM neural network
Open Access
- 1 June 2023
- journal article
- research article
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 20 (3) , 036024
Abstract
Objective. Kalman filtering has previously been applied to track neural model states and parameters, particularly at the scale relevant to electroencephalography (EEG). However, this approach lacks a reliable method to determine the initial filter conditions and assumes that the distribution of states remains Gaussian. This study presents an alternative, data-driven method to track the states and parameters of neural mass models (NMMs) from EEG recordings using deep learning techniques, specifically a long short-term memory (LSTM) neural network. Approach. An LSTM filter was trained on simulated EEG data generated by a NMM using a wide range of parameters. With an appropriately customised loss function, the LSTM filter can learn the behaviour of NMMs. As a result, it can output the state vector and parameters of NMMs given observation data as the input. Main results. Test results using simulated data yielded correlations with R squared of around 0.99 and verified that the method is robust to noise and can be more accurate than a nonlinear Kalman filter when the initial conditions of the Kalman filter are not accurate. As an example of real-world application, the LSTM filter was also applied to real EEG data that included epileptic seizures, and revealed changes in connectivity strength parameters at the beginnings of seizures. Significance. Tracking the state vector and parameters of mathematical brain models is of great importance in the area of brain modelling, monitoring, imaging and control. This approach has no need to specify the initial state vector and parameters, which is very difficult to do in practice because many of the variables being estimated cannot be measured directly in physiological experiments. This method may be applied using any NMM and, therefore, provides a general, novel, efficient approach to estimate brain model variables that are often difficult to measure.Keywords
All Related Versions
Funding Information
- Australian Research Council (DP200102600)
This publication has 38 references indexed in Scilit:
- A phenomenological model of seizure initiation suggests network structure may explain seizure frequency in idiopathic generalised epilepsyThe Journal of Mathematical Neuroscience, 2012
- The Dynamic Brain: From Spiking Neurons to Neural Masses and Cortical FieldsPLOS Computational Biology, 2008
- Dynamic causal modelling for EEG and MEGCognitive Neurodynamics, 2008
- A neural mass model for MEG/EEG:NeuroImage, 2003
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- Long Short-Term MemoryNeural Computation, 1997
- Electroencephalogram and visual evoked potential generation in a mathematical model of coupled cortical columnsBiological Cybernetics, 1995
- On a measure of lack of fit in time series modelsBiometrika, 1978
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960
- A Test of Goodness of FitJournal of the American Statistical Association, 1954