High-frequency oscillations (HFOs) in intracranial EEG (iEEG) recordings are critical biomarkers for localizing the seizure onset zone (SOZ) in patients with focal refractory epilepsy. Despite their clinical significance, HFO analysis is often compromised by high-frequency artifacts that bypass conventional detectors, resulting in false-positive events that dilute the reliability of the HFO pool. To address this challenge, this study aimed to develop an automated method to accurately identify and eliminate false-positive events, ensuring more robust and artifact-free HFO analysis for clinical applications. Using iEEG data from 15 patients with focal epilepsy, we implemented an attention-based cascaded residual dictionary learning framework coupled with a random forest classifier. Events passing an initial amplitude detector underwent a second-stage refinement to remove artifacts and non-neural noise that mimicked HFOs. This was achieved by evaluating event reconstruction quality using a dictionary learned from genuine HFOs. Compared to visual assessments by three human experts, the proposed method demonstrated 92.14% classification accuracy in distinguishing real HFOs from pseudo-HFOs. Additionally, the method improved SOZ localization accuracy in noisy iEEG data by 20% (p=6e-5) and in clean iEEG data by 4% (p=3.3e-3). The learned dictionary effectively captured raw HFO morphology in shallow layers, while deeper layers identified ripple and fast ripple components, all without human supervision. These findings highlight the algorithm's effectiveness in detecting pseudo-HFOs in corrupted iEEG data, thereby enhancing the clinical utility of HFOs as biomarkers for SOZ in epilepsy.

Numerous physiological processes are cyclical, but sampling these processes densely enough to perform frequency decomposition and subsequent analyses can be challenging. Mathematical approaches for decomposition and reconstruction of sparsely and irregularly sampled signals are well established but have been under-utilized in physiological applications. We developed a basis pursuit denoising with polynomial detrending (BPWP) model that recovers oscillations and trends from sparse and irregularly sampled timeseries. We validated this model on a unique dataset of long-term inter-ictal epileptiform discharge (IED) rates from human hippocampus recorded with a novel investigational device with continuous local field potential sensing. IED rates have well established circadian and multiday cycles related to sleep, wakefulness, and seizure clusters. Given sparse and irregular samples of IED rates from multi-month intracranial EEG recordings from ambulatory humans, we used BPWP to compute narrowband spectral power and polynomial trend coefficients and identify IED rate cycles in three subjects. In select cases, we propose that random and irregular sampling may be leveraged for frequency decomposition of physiological signals. Trial Registration: NCT03946618.

Single-pulse electrical stimulation in the nervous system, often called cortico-cortical evoked potential (CCEP) measurement, is an important technique to understand how brain regions interact with one another. Voltages are measured from implanted electrodes in one brain area while stimulating another with brief current impulses separated by several seconds. Historically, researchers have tried to understand the significance of evoked voltage polyphasic deflections by visual inspection, but no general-purpose tool has emerged to understand their shapes or describe them mathematically. We describe and illustrate a new technique to parameterize brain stimulation data, where voltage response traces are projected into one another using a semi-normalized dot product. The length of timepoints from stimulation included in the dot product is varied to obtain a temporal profile of structural significance, and the peak of the profile uniquely identifies the duration of the response. Using linear kernel PCA, a canonical response shape is obtained over this duration, and then single-trial traces are parameterized as a projection of this canonical shape with a residual term. Such parameterization allows for dissimilar trace shapes from different brain areas to be directly compared by quantifying cross-projection magnitudes, response duration, canonical shape projection amplitudes, signal-to-noise ratios, explained variance, and statistical significance. Artifactual trials are automatically identified by outliers in sub-distributions of cross-projection magnitude, and rejected. This technique, which we call "Canonical Response Parameterization" (CRP) dramatically simplifies the study of CCEP shapes, and may also be applied in a wide range of other settings involving event-triggered data.

Seizure clusters, i.e., seizures that occur within a short duration of each other, occur in several epilepsy patients and are associated with increased disease severity. Understanding the characteristics of seizure clusters and predicting whether a given seizure will cluster or not is valuable both from a patient’s and clinician’s perspective. We propose a novel methodology for studying seizure clusters based on bivariate intracranial EEG (iEEG) features and develop one of the first individualized seizure cluster prediction models by combining machine learning with relative entropy (a bivariate feature). Relative entropy was used to quantify interactions between brain regions and capture potential differences in interactions underlying isolated and cluster seizures. We evaluated our methodology using one of the largest ambulatory iEEG datasets, consisting of data from 15 patients with up to 2 years of recordings each. This provided us a sufficient number of seizures in each patient to enable individualized analyses and prediction. On data of 3710 seizures consisting of 3341 cluster seizures (from 427 clusters) and 369 isolated seizures, machine learning models based on relative entropy predicted seizure clusters with up to 73.6% F1-score and outperformed baseline predictors. Our results are beneficial in addressing the clinical burden of clusters.

Electrical stimulation of deep brain structures is an established therapy for drug-resistant focal epilepsy. The emerging implantable neural sensing and stimulating (INSS) technology enables simultaneous delivery of chronic deep brain stimulation (DBS) and recording of electrical brain activity from deep brain structures while patients live in their home environment. Long-term intracranial electroencephalography (iEEG) iEEG signals recorded by INSS devices represent an opportunity to investigate brain neurophysiology and how DBS affects neural circuits. However, novel algorithms and data processing pipelines need to be developed to facilitate research of these long-term iEEG signals. Early-stage analytical infrastructure development for INSS applications can be limited by lacking iEEG data that might not always be available. Here, we investigate the feasibility of utilizing the Deep Generative Adversarial Network (DCGAN) for synthetic iEEG data generation. We trained DCGAN using 3-second iEEG segments and validated synthetic iEEG usability by training a classification model, using synthetic iEEG only and providing a good classification performance on unseen real iEEG with an F1 score 0.849. Subsequently, we demonstrated the feasibility of utilizing the synthetic iEEG in the INSS application development by training a deep learning network for DBS artifact removal using synthetic data only and demonstrated the performance on real iEEG signals. The presented strategy of on-demand generating synthetic iEEG will benefit early-stage algorithm development for INSS applications.

Recent development in implantable devices for electrical brain stimulation includes sensing and embedded computing capabilities that enable adaptive stimulation strategies. Applications include stimulation triggered by pathologic brain activity and endogenous rhythms, such as circadian rhythms. We developed and tested a system that integrates an electrical brain stimulation & sensing implantable device with embedded computing and uses a distributed system with commercial electronics, smartphone and smartwatch for patient annotations, extensive behavioral testing, and adaptive stimulation in subjects in their natural environments. The system enables precise time synchronization of the external components with the brain stimulating device and is coupled with automated analysis of continuous streaming electrophysiology synchronized with patient reports. The system leverages a real-time bi-directional interface between devices and patients with epilepsy living in their natural environment.

We model Alzheimer’s disease (AD) progression by combining differential equations (DEs) and reinforcement learning (RL) with domain knowledge. DEs provide relationships between some, but not all, factors relevant to AD. We assume that the missing relationships must satisfy general criteria about the working of the brain, for e.g., maximizing cognition while minimizing the cost of supporting cognition. This allows us to extract the missing relationships by using RL to optimize an objective (reward) function that captures the above criteria. We use our model consisting of DEs (as a simulator) and the trained RL agent to predict individualized 10-year AD progression using baseline (year 0) features on synthetic and real data. The model was comparable or better at predicting 10-year cognition trajectories than state-of-the-art learning-based models. Our interpretable model demonstrated, and provided insights into, "recovery/compensatory" processes that mitigate the effect of AD, even though those processes were not explicitly encoded in the model. Our framework combines DEs with RL for modelling AD progression and has broad applicability for understanding other neurological disorders.

Deep brain stimulation (DBS) for Parkinson's disease, essential tremor and epilepsy is an established palliative treatment. DBS uses electrical neuromodulation to suppress symptoms. Most current systems provide a continuous pattern of fixed stimulation, with clinical follow-ups to refine settings constrained to normal office hours. An issue with this management strategy is that the impact of stimulation on circadian, i.e. sleep-wake, rhythms is not fully considered; either in the device design or in the clinical follow-up. Since devices can be implanted in brain targets that couple into the reticular activating network, impact on wakefulness and sleep can be significant. This issue will likely grow as new targets are explored, with the potential to create entraining signals that are uncoupled from environmental influences. To address this issue, we have designed a new brain-machine-interface for DBS that combines a slow-adaptive circadian-based stimulation pattern with a fast-acting pathway for responsive stimulation, demonstrated here for seizure management. In preparation for first-in-human research trials to explore the utility of multi-timescale automated adaptive algorithms, design and prototyping was carried out in line with ISO risk management standards, ensuring patient safety. The ultimate aim is to account for chronobiology within the algorithms embedded in brain-machine-interfaces and in neuromodulation technology more broadly.

This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7% better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10% gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives.

The ability to predict seizures may enable patients with epilepsy to better manage their medications and activities, potentially reducing side effects and improving quality of life. Forecasting epileptic seizures remains a challenging problem, but machine learning methods using intracranial electroencephalographic (iEEG) measures have shown promise. A machine-learning-based pipeline was developed to process iEEG recordings and generate seizure warnings. Results support the ability to forecast seizures at rates greater than a Poisson random predictor for all feature sets and machine learning algorithms tested. In addition, subject-specific neurophysiological changes in multiple features are reported preceding lead seizures, providing evidence supporting the existence of a distinct and identifiable preictal state.

There is a growing interest in data-analytic modeling for prediction and/or detection of epileptic seizures from EEG recording of brain activity [1-10]. Even though there is clear evidence that many patients have changes in EEG signal prior to seizures, development of robust seizure prediction methods remains elusive [1]. We argue that the main issue for development of effective EEG-based predictive models is an apparent disconnect between clinical considerations and dataanalytic modeling assumptions. We present an SVM-based system for seizure prediction, where design choices and performance metrics are clearly related to clinical objectives and constraints. This system achieves very accurate prediction of preictal and interictal EEG segments in dogs with naturally occurring epilepsy. However, our empirical results suggest that good prediction performance may be possible only if the training data set has sufficiently many preictal segments, i.e. at least 6-7 seizure episodes.

Granger causality (GC) is one of the most popular measures to reveal causality influence of time series and has been widely applied in economics and neuroscience. Especially, its counterpart in frequency domain, spectral GC, as well as other Granger-like causality measures have recently been applied to study causal interactions between brain areas in different frequency ranges during cognitive and perceptual tasks. In this paper, we show that: 1) GC in time domain cannot correctly determine how strongly one time series influences the other when there is directional causality between two time series, and 2) spectral GC and other Granger-like causality measures have inherent shortcomings and/or limitations because of the use of the transfer function (or its inverse matrix) and partial information of the linear regression model. On the other hand, we propose two novel causality measures (in time and frequency domains) for the linear regression model, called new causality and new spectral causality, respectively, which are more reasonable and understandable than GC or Granger-like measures. Especially, from one simple example, we point out that, in time domain, both new causality and GC adopt the concept of proportion, but they are defined on two different equations where one equation (for GC) is only part of the other (for new causality), thus the new causality is a natural extension of GC and has a sound conceptual/theoretical basis, and GC is not the desired causal influence at all. By several examples, we confirm that new causality measures have distinct advantages over GC or Granger-like measures. Finally, we conduct event-related potential causality analysis for a subject with intracranial depth electrodes undergoing evaluation for epilepsy surgery, and show that, in the frequency domain, all measures reveal significant directional event-related causality, but the result from new spectral causality is consistent with event-related time-frequency power spectrum activity. The spectral GC as well as other Granger-like measures are shown to generate misleading results. The proposed new causality measures may have wide potential applications in economics and neuroscience.

The degree of synchronization in electroencephalography (EEG) signals is commonly characterized by the time-series measures, namely, correlation, phase synchrony, and magnitude squared coherence (MSC). However, it is now well established that the interpretation of the results from these measures are confounded by the recording reference signal and that this problem is not mitigated by the use of other EEG montages, such as bipolar and average reference. In this paper, we analyze the impact of reference signal amplitude and power on EEG signal correlation, phase synchrony, and MSC. We show that, first, when two nonreferential signals have negative correlation, the phase synchrony and the absolute value of the correlation of the two referential signals may have two regions of behavior characterized by a monotonic decrease to zero and then a monotonic increase to one as the amplitude of the reference signal varies in [0, +∞). It is notable that even a small change of the amplitude may lead to significant impact on these two measures. Second, when two nonreferential signals have positive correlation, the correlation and phase-synchrony values of the two referential signals can monotonically increase to one (or monotonically decrease to some positive value and then monotonically increase to one) as the amplitude of the reference signal varies in [0, +∞). Third, when two nonreferential signals have negative cross-power, the MSC of the two referential signals can monotonically decrease to zero and then monotonically increase to one as reference signal power varies in [0, +∞). Fourth, when two nonreferential signals have positive cross-power, the MSC of the two referential signals can monotonically increase to one as the reference signal power varies in [0, +∞). In general, the reference signal with small amplitude or power relative to the signals of interest may decrease or increase the values of correlation, phase synchrony, and MSC. However, the reference signal with high relative amplitude or power will always increase each of the three measures. In our previous paper, we developed a method to identify and extract the reference signal contribution to intracranial EEG (iEEG) recordings. In this paper, we apply this approach to referential iEEG recorded from human subjects and directly investigate the contribution of recording reference on correlation, phase synchrony, and MSC. The experimental results demonstrate the significant impact that the recording reference may have on these bivariate measures.