Spike and wave discharges detection in genetic absence epilepsy rat from Strasbourg and patients with genetic generalized epilepsy.

OBJECTIVE: Generalised spike and wave discharges (SWDs) are pathognomonic EEG signatures for diagnosing absence seizures in patients with Genetic Generalized Epilepsy (GGE). The Genetic Absence Epilepsy Rats from Strasbourg (GAERS) is one of the best-validated animal models of GGE with absence seizures. METHODS: We developed an SWDs detector for both GAERS rodents and GGE patients with absence seizures using a neural network method. We included 192 24-hour EEG sessions recorded from 18 GAERS rats, and 24-hour scalp-EEG data collected from 11 GGE patients. RESULTS: The SWDs detection performance on GAERS showed a sensitivity of 98.01% and a false positive (FP) rate of 0.96/hour. The performance on GGE patients showed 100% sensitivity in five patients, while the remaining patients obtained over 98.9% sensitivity. Moderate FP rates were seen in our patients with 2.21/hour average FP. The detector trained within our patient cohort was validated in an independent dataset, TUH EEG Seizure Corpus (TUSZ), that showed 100% sensitivity in 11 of 12 patients and 0.56/hour averaged FP. CONCLUSIONS: We developed a robust SWDs detector that showed high sensitivity and specificity for both GAERS rats and GGE patients. SIGNIFICANCE: This detector can assist researchers and neurologists with the time-efficient and accurate quantification of SWDs.

Graph Signal Processing, Graph Neural Network and Graph Learning on Biological Data: A Systematic Review.

Graph networks can model data observed across different levels of biological systems that span from population graphs (with patients as network nodes) to molecular graphs that involve omics data. Graph-based approaches have shed light on decoding biological processes modulated by complex interactions. This paper systematically reviews graph-based analysis methods of Graph Signal Processing (GSP), Graph Neural Networks (GNNs) and graph topology inference, and their applications to biological data. This work focuses on the algorithms of graph-based approaches and the constructions of graph-based frameworks that are adapted to a broad range of biological data. We cover the Graph Fourier Transform and the graph filter developed in GSP, which provides tools to investigate biological signals in the graph domain that can potentially benefit from the underlying graph structures. We also review the node, graph, and interaction oriented applications of GNNs with inductive and transductive learning manners for various biological targets. As a key component of graph analysis, we provide a review of graph topology inference methods that incorporate assumptions for specific biological objectives. Finally, we discuss the biological application of graph analysis methods within this exhaustive literature collection, potentially providing insights for future research in biological sciences.