Skip to content
BY 4.0 license Open Access Published online by De Gruyter May 27, 2022

Toward automated prediction of sudden unexpected death in epilepsy

Bin Gu and Hojjat Adeli


Sudden unexpected death in epilepsy (SUDEP) is a devastating yet overlooked complication of epilepsy. The rare and complex nature of SUDEP makes it challenging to study. No prediction or prevention of SUDEP is currently available in a clinical setting. In the past decade, significant advances have been made in our knowledge of the pathophysiologic cascades that lead to SUDEP. In particular, studies of brain, heart, and respiratory functions in both human patients at the epilepsy monitoring unit and animal models during fatal seizures provide critical information to integrate computational tools for SUDEP prediction. The rapid advances in automated seizure detection and prediction algorithms provide a fundamental framework for their adaption in predicting SUDEP. If a SUDEP can be predicted, then there will be a potential for medical intervention to be administered, either by their caregivers or via an implanted device automatically delivering electrical stimulation or medication, and finally save lives from fatal seizures. This article presents recent developments of SUDEP studies focusing on the pathophysiologic basis of SUDEP and computational implications of machine learning techniques that can be adapted and extended for SUDEP prediction. This article also discusses some novel ideas for SUDEP prediction and rescue including principal component analysis and closed-loop intervention.


Epilepsy is a spectrum of clinically heterogeneous neurological disorders characterized by spontaneous recurrent seizures. Over 1% of the general population have active epileptic seizures, which adversely affect patients’ life quality and increase the risk of psychiatric comorbidities, hospitalization, and mortality (Devinsky et al. 2018; Zack and Kobau 2017). Among the deaths that are attributable to seizures, sudden unexpected death in epilepsy (SUDEP) is the leading cause (Devinsky et al. 2016; Friedman 2017). SUDEP refers to deaths in people with epilepsy that are not caused by injury, drowning, or status epilepticus, in which the postmortem examination does not reveal a clear cause of death (Nashef et al. 2012). SUDEP rates vary depending on the patient cohort, and the population-based studies of SUDEP suggest a pooled estimate of 1.3–1.65/1000 epileptic individuals/year (Einarsdottir et al. 2019; Kløvgaard et al. 2021; Saetre and Abdelnoor 2018). SUDEP also constitutes to ∼30% of young adult epilepsy-related deaths (Mbizvo et al. 2021). SUDEP is considered to be the most catastrophic complication of epilepsy and poses a substantial public health burden (Thurman et al. 2014). However, the cause of SUDEP is still largely unknown, and there is no method to predict or prevent SUDEP in a clinical setting.

A computer-aided automated brain states detection and prediction system can be developed through adroit integration of signal processing methods such as EEG wavelet transforms (Moradi et al. 2020; Sharma et al. 2014) and machine-learning techniques (Li et al. 2020a, b; Liu et al. 2020; Nogay and Adeli 2020). In the past two decades, many authors have employed machine learning to develop algorithms for automated epilepsy diagnoses (Thomas et al. 2021), seizure detection (Abbasi and Goldenholz 2019; Baumgartner et al. 2018; Boonyakitanont et al. 2020; Ma et al. 2021; O’Shea et al. 2021; Zhao et al. 2021), and seizure prediction (Acharya et al. 2018; Peng et al. 2021; Zhang et al. 2020). In these studies, the electroencephalogram (EEG), brain imaging such as magnetic resonance imaging (MRI), and other forms of data collected from epileptic patients are fed into a computer model for preprocessing, featurization, model learning, testing, and validation. The good performance (>90% accuracy, sensitivity, and specificity) of many machine-learning algorithms in seizure detection and prediction provides the opportunity to adapt similar approaches for SUDEP risk assessment and prediction (Figure 1). This article presents a state-of-the-art review of recent articles studying pathophysiology and predicting algorithms of SUDEP in both humans (Table 1) and animal subjects in the past five years. The genetic, molecular, and cellular mechanisms of SUDEP have been well-reviewed elsewhere (Bagnall et al. 2017; Chahal et al. 2020; Glasscock 2014; Massey et al. 2014).

Figure 1: 
Schematic workflow of automated SUDEP risk assessment and prediction.

Figure 1:

Schematic workflow of automated SUDEP risk assessment and prediction.

Table 1:

Summary of clinical studies toward development of biomarkers for risk of SUDEP.

Authors Year Source data Features Classifiers Performance
Bauer 2017 Video-EEG of 48 GCS from 48 patients Presence and duration of postictal suppression Multiunit computational neural mass model N/A
Theeranaew 2018 EEG of 14 seizures from 12 patients (training) and 20 seizures from 20 patients (testing) Start and end of PGES Combine frequency domain features with boosting classification algorithms Better than 5/11 clinicians on difficult EEG patterns
Zibrandtsen 2018 Ear-EEG of 3 GTCS from 15 patients and scalp-EEG of 11 GTCS from 6 patients GTCS semiology Median-filtered variance estimates 100% sensitivity and no false positives compared to scalp EEG
Geertsema 2018 Video of 72 convulsive seizures from 50 patients (training) and 50 convulsive seizures from 12 patients (testing) Nocturnal convulsions An algorithm based on optical flow, extraction of global group transformation velocities, and band-pass temporal filtering 100% sensitivity with a median false detection rate of 0.78
Barbour 2019 Electronic medical records from 2000 patients each for training and testing SUDEP risk factors in electronic medical records Natural language processing >90% sensitivity for GTCS
Lamichhane 2020 EEG of 134 (training) and 34 (testing) epileptic patients End of PGES Random forest-based classification model AUC of ROC curve 0.84
Mier 2020 EEG from 134 patients for training (85%) and testing (15%) End of PGES Gradient-boosted decision trees and random forest classifiers AUC of ROC curve 0.76
Li X 2020 EEG of 116 recordings from 84 patients with GTCS Onset of the first intermittent slow-wave activity as an indication of the end of PGES Random forest classifier and time distance-based evaluation method Positive prediction rate 0.95 (artifact-free signals) and 0.68–0.81 (different artifact levels)
Zhu 2020 EEG from 80 (training), 54 (internal testing), and 36 (external testing) epileptic patients Onset of slow-wave activity as indication of end of PGES Convolutional neural network with lightweight architecture AUC of ROC curve 0.72
van Westrhenen 2020 Video of 125 convulsive seizures from eight children (testing) Nocturnal convulsions Similar to Geertsems et al. 2018 with adjustments Median sensitivity 100% with median false alarm rate of 0%
Cardenas 2020 Surface EMG of 23 GTCS from 19 epileptic patients GTCS semiology Wavelet-transform to determine the frequency components followed by an automated process incorporating a variant of cross-validation. N/A
Zhao 2021 Video-EEG of 148 GCS from 87 epileptic patients Presence and duration of PGES Random forest-based classification model Consistent with visual analysis
Chen 2022 Interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls Interictal EEG and ECG Logistic regression, support vector machine, random forest, and convolutional neural network AUC of ROC curve of logistic regression model = 0.77–0.79

  1. AUC, area under the curve; GCS, generalized convulsive seizures; GTCS, generalized tonic-clonic seizures; ROC, receiver operating characteristic; PGES, postictal generalized EEG suppression.

Pathophysiology and biomarkers of SUDEP

Human studies

Converging lines of evidence collected from limited SUDEP and near-SUDEP cases at the epilepsy monitoring unit (EMU) suggest that SUDEP primarily follows the severe impairment of respiratory and cardiac functions induced by generalized tonic-clonic seizures (GTCS), which are commonly associated with postictal generalized EEG suppression (PGES) (Lhatoo et al. 2010; Rajakulendran and Nashef 2015; Ryvlin et al. 2013). PGES has been linked to postictal sympathetic and parasympathetic dysregulations including seizure-related respiratory inhibition. Thereby, PGES is considered a major contributor to SUDEP (Bruno et al. 2020a, b, c; Kuo et al. 2016; Poh et al. 2012; Sarkis et al. 2015). However, it remains unclear whether PGES is a reliable biomarker of SUDEP. The conclusion is controversial in terms of the association between the presence or duration of PGES and SUDEP (Kang et al. 2017). The association between PGES and SUDEP also failed to be replicated in other studies (Lamberts et al. 2013; Surges et al. 2011). Hence, the measurements of duration and magnitude of PGES may not be sufficient to address the relationship between the postictal EEG state and the SUDEP risk. Beyond the time-domain analysis, frequency-domain features including cross-frequency coupling are also studied in the context of SUDEP. EEG recordings from a single SUDEP case suggested the loss of ictal phase-amplitude coupling dynamics from the frontal temporal lobe, which are consistently observed in epileptic survivors (Grigorovsky et al. 2020).

In contrast to scalp EEG routines, intracranial EEG (iEEG) allows direct recording of specific brain regions that are critical in regulating seizure-related mortality. iEEG recordings in near-SUDEP cases revealed that the onset of ictal and postictal apnea was highly correlated with seizure spreading to the amygdala (Johnson et al. 2021; Nobis et al. 2019). Consistently, electrical amygdala stimulation also produced apnea in human subjects (Nobis et al. 2018; Rhone et al. 2020). Together these studies suggest a critical role of the amygdala in regulating breathing during seizures, with implications for SUDEP pathophysiology (Vilella et al. 2019). However, in a separate iEEG study, the amygdala seizure spread was neither necessary nor sufficient to cause spontaneous seizure-related apneas, suggesting an inconsistent linkage between these two events (Park et al. 2020).

Compared to EEG, brain imaging techniques including MRI offer a better spatial resolution for deciphering structural and functional brain alterations in epilepsy. In particular, MRI allows a comprehensive examination of distinct neural structures and networks that are crucial for cardiac and respiratory regulations in patients who succumb to SUDEP (Allen et al. 2019). In serial retrospective volumetric MRI studies, SUDEP cases exhibited increased gray matter volume in the right anterior hippocampus, parahippocampus, and amygdala, whereas decreased volume in medial and lateral cerebellum, posterior thalamic gray matter, and medulla oblongata compared to controls (Mueller et al. 2018; Wandschneider et al. 2015). A postmortem volumetric MRI study found a lower volume of the rostral medulla reticular formation zone but a higher volume of the caudal medulla in SUDEP compared to epileptic and nonepileptic controls (Patodia et al. 2021). Together, these observations indicate that the anatomical alteration of specific brain regions including medulla oblongata is a potential risk factor for SUDEP.

In addition to structural changes, functional imaging tools facilitate our understanding of the physiology and network dynamics underlying this fatal event. A resting-state functional MRI study revealed multiple alterations of network properties including disrupted thalamic connectivity in SUDEP cases compared to low-risk subjects who did not experience any GTCS (La et al. 2019). Positron emission tomography studies identified several unique metabolic patterns including hypometabolism in frontal lobe, hypermetabolism in midbrain and pons in the high SUDEP risk compared to the low SUDEP risk subgroup (Kumar et al. 2021; Whatley et al. 2021). In sum, these SUDEP studies in humans unveil dysfunctional changes and interactions that can be used to further generate discriminative representations using machine-learning and deep-learning tools (Abrol et al. 2021; Davatzikos 2019).

Animal models of SUDEP

The rare and unexpected nature of SUDEP limits data from the EMU that is available for studying its pathophysiology in humans (Ryvlin et al. 2013). Animal models offer a complementary tool with rich resources to study SUDEP under the control of genetic and/or environmental variables. Currently available animal models of SUDEP not only recapitulate many key features of human cases of SUDEP including autonomic dysregulation, apnea, hypoventilation, cardiac arrhythmia, and postictal EEG suppression, but also suggest potential genetic and molecular mechanisms of SUDEP such as channelopathies and impairment of serotonergic and adenosinergic systems.

A wide range of model organisms including mice, rats, sheep, and baboons have been used to study SUDEP. Among them, the house mouse (Mus musculus) has been developed into the premier mammalian model organism of SUDEP. Several single-gene manipulations as monogenic causes of developmental and epileptic encephalopathies (e.g., SCN1A, SCN8A, SCN1B, and DEPDC5) and long-QT syndromes (e.g., KCNQ1 and KCNA1) have been used to model SUDEP in mice (Griffin et al. 2018). In these studies, transgenic mice are maintained on a single genetic background; thereby, the importance of isolated genes to SUDEP sensitivities has been demonstrated without consideration of the effect of genetic complexity (e.g., genetic modifiers and polygenicity) on SUDEP response (Goldman et al. 2016).

DBA/1J and DBA/2J mice are classic laboratory inbred mice strains commonly used in the study of SUDEP given their susceptibility to audiogenic seizure-related respiratory arrest (Pansani et al. 2016). However, their SUDEP sensitivity requires acoustic “priming” at a younger age (Faingold et al. 2010) to maximize the severity of the acoustic seizure response. Compared to DBA/1J and DBA/2J, a recent study showed that 129/SvTer mouse is a more versatile model of SUDEP because it has a wider age range of susceptibility without the need for “priming” (Martin et al. 2020). Utilizing a genetic reference population, the recombinant inbred Collaborative Cross mice, our group identified four strains of Collaborative Cross mice (i.e., CC003/Unc, CC008/GeniUnc, CC009/Unc, and CC029/Unc) that succumbed to sudden death immediately following a transient episode of generalized seizure induced by flurothyl, which is otherwise nonfatal to other inbred mouse strains (Gu et al. 2020).

In sum, these animal models of SUDEP provide basic scientists essential tools for studying mechanisms and treatment strategies of SUDEP. However, the translational value of the knowledge that we gained using animal models of SUDEP requires further evaluation.

Pathophysiology and biomarkers of SUDEP in animal models

The implementation of a time-locked behavior-brain-heart-respiratory simultaneous recording system in both anesthetized and freely moving animals offers means to investigate the alterations of the nervous, cardiac, and respiratory functions that lead to seizure-induced sudden death in greater detail. In particular, animal models allow direct recordings from brainstem — the cardiorespiratory pace-making center which is hard to access in a clinical setting.

Mounting evidence suggests that altered brainstem function is associated with respiratory and cardiac dysfunction, followed by terminal apnea and asystole leading to death in animal models of SUDEP (Lertwittayanon et al. 2020). For example, a slow, negative direct current (DC) potential shift, also known as spreading depolarization, was located in the brainstem of anesthetized mouse models of SUDEP carrying mutation in Kcna1, Scn1a, Ryr2, or Cacna1a (Aiba and Noebels 2015; Aiba et al. 2016; Loonen et al. 2019). A recent study also pinpointed superior colliculus hyperexcitability as a key regulator of brainstem spreading depolarization using diffusion-weighted MRI in a mouse model of SUDEP (Cain et al. 2022). Together, data from DC recordings point to a critical role of brainstem spreading depolarization in mediating the postictal cardiorespiratory collapse that leads to SUDEP. Negative DC field potential shifts of the brainstem were also observed following the final breath in a rat model of status epilepticus. However, the timing suggests that, in the case of a prolonged seizure, the DC shift is a consequence rather than the cause of the respiratory collapse (Jefferys et al. 2019). Although traditional alternating current (AC)-coupled techniques used in clinics are unable to reliably detect spreading depolarization, the rapid development of intracranial unfiltered DC-coupled recordings in humans improves the translational value of using spreading depolarization in SUDEP prediction (Hartings et al. 2017). A recent study from our group utilizing AC-coupled local field potential recordings directly from dorsal raphe in a mouse model of SUDEP revealed strong ictal brainstem suppression preceding asystole and death (Gu et al. 2022).

In addition to the nervous system, the importance of cardiac and respiratory functions as well as their interplay with the brain have been demonstrated using animal models of SUDEP. Peri-ictal and tonic-phase central apnea co-occurring or preceding terminal asystole was directly associated with SUDEP across DBA/1J mouse models of SUDEP and mice carrying Scn8a, Scn1a, Kcna1, or Cacna1a mutation (Dhaibar et al. 2019; Kim et al. 2018; Schilling et al. 2019; Wenker et al. 2021). A combination of electrophysiology and fast MRI scans in a rat model of seizures showed laryngospasm-preceded esophageal reflux during fatal seizures suggesting that obstructive apnea is associated with subsequent sudden death in rats (Mandal et al. 2021). Consistent with human studies, the amygdala also plays a fundamental role in respiratory regulation in the animal model of SUDEP. Electrolytic lesions of the amygdala of DBA/1J mice significantly reduced the incidence of seizure-induced respiratory arrest without affecting the seizures, baseline breathing, or chemoreception (Marincovich et al. 2021).

Besides respiratory impairments, cardiac dysfunction and failure are equally important to SUDEP pathology. Cardiac dysfunctions are common in patients with SUDEP as many SUDEP-related genetic mutations are associated with cardiac arrhythmia (Chahal et al. 2020; Friedman et al. 2018). Cardiac dysfunctions including reduced heart rate variability, cardiac myocytes hyperexcitability, increased atrioventricular conduction blocks, bradycardia, and cardiac arrhythmias have also been demonstrated in various transgenic mouse models of SUDEP (Frasier et al. 2016; Glasscock et al. 2010; Kalume et al. 2013; Lin et al. 2015).

After the demonstration of the importance of the isolated system in SUDEP, the multimodal recordings can reveal the potential interplay between each system in regulating SUDEP. Hutson et al. conducted the first directional connectivity analysis of multimodal data collected from SUDEP model mice. Their elegant work showed impairment in the afferent and efferent pathways in the holistic neuro-cardio-respiratory network in Kcna1 deletion mice compared to wild-type controls suggesting that effective connectivity measures among brain, heart, and lung could serve as novel biomarkers of SUDEP (Hutson et al. 2020).

Toward automated SUDEP prediction

Though seizure control is still the best practice for SUDEP prevention, special measures and algorithms need to be developed to prevent SUDEP when seizure control is not possible or optimal. The discovery of surrogate biomarkers that can be quantitatively measured and computed to identify individuals at risk and determine which seizure is fatal enables automated SUDEP prediction (Figures 1 and 2).

Figure 2: 
Schematic of the implementation of machine learning in SUDEP prediction. Both linear and nonlinear biopotential features linked to SUDEP and previously unknown hidden patterns can be extracted using machine-learning and deep-learning algorithms to determine whether a seizure is lethal.

Figure 2:

Schematic of the implementation of machine learning in SUDEP prediction. Both linear and nonlinear biopotential features linked to SUDEP and previously unknown hidden patterns can be extracted using machine-learning and deep-learning algorithms to determine whether a seizure is lethal.

Although it is still controversial whether PGES is an EEG biomarker for the risk of SUDEP, major efforts have been focused on automated detection of PGES as a potential SUDEP prediction practice. Serial machine-learning tools including both traditional machine-learning and deep-learning algorithms have been employed for automatic detection of the start, end, and duration of PGES based on EEG recordings (Bauer et al. 2017; Lamichhane et al. 2020; Li et al. 2020a, b; Mier et al. 2020; Theeranaew et al. 2018; Zhu et al. 2020). In addition to standard EEG routines, features extracted from other forms of data such as video, ECG, electrodermal, and muscular activities can also be used for assisting the computer-aided assessment of SUDEP risks (Chen et al. 2022; Gutierrez et al. 2018). For example, automated video-based nocturnal convulsive epileptic events detection algorithms offer a great predictive value for SUDEP (Geertsema et al. 2018; van Westrhenen et al. 2020) (Table 1).

Wearable devices open a new avenue for continuous monitoring of seizures and biological signals reflecting seizure severity in outpatients with epilepsy (Beniczky et al. 2020; Bruno et al. 2020a, b, c; Burns and Adeli 2017; Onorati et al. 2017; Ryvlin et al. 2018; van Westrhenen et al. 2021). A case study using a smartwatch to record wrist motion and an electrodermal activity revealed sympathetic hyperactivity and hypoventilation before probable SUDEP (Picard et al. 2017). The accelerometer silence detected by wearables reliably identified the postictal immobility, which has been associated with SUDEP (Bruno et al. 2020a, b). The automated processing of quantitative surface electromyography (EMG) accurately detected the key features of GTCS, which is a major risk factor for SUDEP (Beniczky et al. 2018; Cardenas et al. 2020; Zibrandtsen et al. 2018).

Besides the motion and electrophysiological signals directly collected from patients, electronic medical records contain a wealth of information that can be analyzed to predict the risks of SUDEP. Implementation of natural language processing on text search in electronic medical records was used for the automated identification of SUDEP risk factors (Barbour et al. 2019). A similar tool for individualized prediction of SUDEP was developed using a Bayesian logistic regression model based on 29 common clinical predictor variables (Jha et al. 2021).

To date, major efforts have been focused on using EEG, body motion, and medical records for SUDEP prediction. Algorithms that are specifically designed for cardiac and respiratory feature extraction and classification have not been widely explored in SUDEP prediction. Less attention has been received to other systems that also play a fundamental role in SUDEP such as arousal (Buchanan 2019), vasculature (Szczurkowska et al. 2021), and microbiome (Lum et al. 2020; Olson et al. 2018). Compared to human studies, the current automated SUDEP prediction research in animals is still in paucity and needs to receive more attention.

In sum, published literature on both humans and animal subjects suggests there is a list of surrogate biomarkers and features that can be leveraged to achieve automated SUDEP prediction via machine-learning techniques. Notably, unsupervised machine-learning algorithms can also uncover hidden structures and patterns that have not been previously associated with SUDEP (Figure 2).

Challenges and opportunities in SUDEP prevention

The central question of SUDEP prevention is why a particular seizure causes death while others do not. Many challenges including clinical variables such as genetics, treatment history, and other comorbid health conditions as well as inconsistent methodology in data collection and interpretation are inherited in the implication of machine learning in seizure and SUDEP prediction in humans. For EEG-based algorithms, in particular, the artifacts from movement, breathing, and muscle activity can negatively affect the quality of data and linear measures. To resolve this issue, artifacts from EEG signals can be filtered before signal processing or the advantages of nonlinear analyses should be robust against the noise present in the EEG signals.

Large amount of data are required to train a computer to achieve highly sensitive performance in predicting the SUDEP using a deep-learning approach, which is challenging given the rare nature of SUDEP even with the integration of near-SUDEP and high-risk SUDEP cases. To tackle the challenge of accumulating large clinical datasets, many cloud-based repositories have been established to facilitate data sharing and quality control across institutions and countries (Cui et al. 2016). The Center for SUDEP Research (CSR) is an initiative that has been established by the National Institute of Neurological Disorders and Stroke to investigate SUDEP. The major goal of CSR clinical research focuses on the examination of the complex interplay between postictal suppression of brain function, disordered peri-ictal breathing, and autonomic dysfunction (Lhatoo et al. 2015). Accumulating recordings of physiologic parameters including EEG, ECG, breathing, oxygen saturation, CO2, and biochemical measures in SUDEP and epileptic controls provide valuable information for multimodal data integration and analysis. For example, one study combined diverse elements of the dataset including EEG, blood pressure, ECG, and baroreflex sensitivity to discover temporal patterns of transitions in network connectivity as potential biomarkers of SUDEP (Threeanaew et al. 2019). In addition to connectivity analysis of multimodal data, other multivariate statistics including principal component analysis (Torres-Espín et al. 2021) can be performed for interpreting, visualizing, and studying the robustness of the main components that characterize SUDEP. Future work can extract underlying principal components that reflect disease states (i.e., SUDEP) as the center of a Venn diagram (Figure 3).

Figure 3: 
Theoretical framework of principal component analysis of SUDEP. The intersection between different outcome measures (e.g., nervous, cardiac, and respiratory) can create a multivariate measure (i.e., principal component) to explain different patterns of variance in the data.

Figure 3:

Theoretical framework of principal component analysis of SUDEP. The intersection between different outcome measures (e.g., nervous, cardiac, and respiratory) can create a multivariate measure (i.e., principal component) to explain different patterns of variance in the data.

Epileptiform activities emerge unpredictively and intermittently, and therefore, a feedback brain manipulation that leaves other normal episodes and aspects of brain functions unaffected is desirable (Berényi et al. 2012). Closed-loop therapy has been proposed for better seizure control and has been receiving increasing attention (Iasemidis 2011; Nagaraj et al. 2015). A responsive neurostimulation device has been approved by FDA for treating focal seizures using on-demand electrical brain stimulation. Similarly, the detection of triggers of SUDEP in real time will allow the development of tunable algorithms to identify and rapidly respond to fatal seizures. With better knowledge of the cellular and circuit regulation of SUDEP pathologies (Faingold et al. 2016; Petrucci et al. 2021; Zhang et al. 2016), the idea of a feedback system that can accurately detect and quickly respond to fatal seizures can be first tested in animal models of SUDEP by constructing a real-time rescuing system using the closed-loop electrical and on-demand optogenetic approaches (Armstrong et al. 2013; Tafazoli et al. 2020) (Figure 4).

Figure 4: 
Schematic of experimental design of a feedback rescue approach in a mouse model of SUDEP. A computer running automated SUDEP prediction algorithms will detect fatal seizures and automatically deliver electrical or optical stimulation to the targeted brain region or population of neurons in a real-time manner.

Figure 4:

Schematic of experimental design of a feedback rescue approach in a mouse model of SUDEP. A computer running automated SUDEP prediction algorithms will detect fatal seizures and automatically deliver electrical or optical stimulation to the targeted brain region or population of neurons in a real-time manner.

Final remarks

In this article, the authors reviewed different aspects of SUDEP pathologies in both humans and animal models, potential SUDEP prediction algorithms, and their challenges and opportunities. The rapid advances of wearable devices and machine-learning techniques provide viable tools to improve the accuracy and reliability of the SUDEP prediction, which can further revolutionize SUDEP prevention and reduce the likelihood of this tragic event and familial loss.

Corresponding author: Bin Gu, Department of Neuroscience, Ohio State University, 612 Biomedical Research Tower, 460 W 12th Avenue, Columbus, OH 43210, USA, E-mail:

  1. Author contributions: Both authors prepared the manuscript.

  2. Research funding: There is no funding for the present study.

  3. Conflict of interest statement: The authors declare that they have no competing interests.


Abbasi, B. and Goldenholz, D.M. (2019). Machine learning applications in epilepsy. Epilepsia 60: 2037–2047. in Google Scholar PubMed

Abrol, A., Fu, Z., Salman, M., Silva, R., Du, Y., Plis, S., and Calhoun, V. (2021). Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning. Nat. Commun. 12: 353. in Google Scholar PubMed PubMed Central

Acharya, U.R., Hagiwara, Y., and Adeli, H. (2018). Automated seizure prediction. Epilepsy Behav. 88: 251–261. in Google Scholar PubMed

Aiba, I. and Noebels, J.L. (2015). Spreading depolarization in the brainstem mediates sudden cardiorespiratory arrest in mouse SUDEP models. Sci. Transl. Med. 7, 282ra246. in Google Scholar PubMed PubMed Central

Aiba, I., Wehrens, X.H., and Noebels, J.L. (2016). Leaky RyR2 channels unleash a brainstem spreading depolarization mechanism of sudden cardiac death. Proc. Natl. Acad. Sci. USA 113: E4895–E4903. in Google Scholar PubMed PubMed Central

Allen, L.A., Harper, R.M., Lhatoo, S., Lemieux, L., and Diehl, B. (2019). Neuroimaging of sudden unexpected death in epilepsy (SUDEP): insights from structural and resting-state functional MRI studies. Front. Neurol. 10: 185. in Google Scholar PubMed PubMed Central

Armstrong, C., Krook-Magnuson, E., Oijala, M., and Soltesz, I. (2013). Closed-loop optogenetic intervention in mice. Nat. Protoc. 8: 1475–1493. in Google Scholar PubMed PubMed Central

Bagnall, R.D., Crompton, D.E., and Semsarian, C. (2017). Genetic basis of sudden unexpected death in epilepsy. Front. Neurol. 8: 348. in Google Scholar PubMed PubMed Central

Barbour, K., Hesdorffer, D.C., Tian, N., Yozawitz, E.G., McGoldrick, P.E., Wolf, S., McDonough, T.L., Nelson, A., Loddenkemper, T., Basma, N., et al.. (2019). Automated detection of sudden unexpected death in epilepsy risk factors in electronic medical records using natural language processing. Epilepsia 60: 1209–1220. in Google Scholar PubMed

Bauer, P.R., Thijs, R.D., Lamberts, R.J., Velis, D.N., Visser, G.H., Tolner, E.A., Sander, J.W., Lopes da Silva, F.H., and Kalitzin, S.N. (2017). Dynamics of convulsive seizure termination and postictal generalized EEG suppression. Brain 140: 655–668. in Google Scholar PubMed PubMed Central

Baumgartner, C., Koren, J.P., and Rothmayer, M. (2018). Automatic computer-based detection of epileptic seizures. Front. Neurol. 9: 639. in Google Scholar PubMed PubMed Central

Beniczky, S., Arbune, A.A., Jeppesen, J., and Ryvlin, P. (2020). Biomarkers of seizure severity derived from wearable devices. Epilepsia 61(Suppl 1): S61–S66. in Google Scholar PubMed

Beniczky, S., Conradsen, I., and Wolf, P. (2018). Detection of convulsive seizures using surface electromyography. Epilepsia 59(Suppl 1): 23–29. in Google Scholar PubMed

Berényi, A., Belluscio, M., Mao, D., and Buzsáki, G. (2012). Closed-loop control of epilepsy by transcranial electrical stimulation. Science 337: 735–737. PMID: 22879515; PMCID: PMC4908579.Search in Google Scholar PubMed PubMed Central

Boonyakitanont, P., Lek-uthai, A., Chomtho, K., and Songsiri, J. (2020). A review of feature extraction and performance evaluation in epileptic seizure detection using EEG. Biomed. Signal Process Control 57: 1–14, in Google Scholar

Bruno, E., Böttcher, S., Biondi, A., Epitashvili, N., Manyakov, N.V., Lees, S., Schulze-Bonhage, A., and Richardson, M.P. (2020a). Post-ictal accelerometer silence as a marker of post-ictal immobility. Epilepsia 61: 1397–1405. in Google Scholar PubMed

Bruno, E., Richardson, M.P., and Consortium, R.-C. (2020b). Postictal generalized EEG suppression and postictal immobility: what do we know? Epileptic Disord. 22: 245–251. in Google Scholar PubMed

Bruno, E., Viana, P.F., Sperling, M.R., and Richardson, M.P. (2020c). Seizure detection at home: do devices on the market match the needs of people living with epilepsy and their caregivers? Epilepsia 61: S11–S24. in Google Scholar PubMed

Buchanan, G.F. (2019). Impaired CO2-induced arousal in SIDS and SUDEP. Trends Neurosci. 42: 242–250. in Google Scholar PubMed PubMed Central

Burns, A. and Adeli, H. (2017). Wearable technology for patients with brain and spinal cord injuries. Rev. Neurosci. 28: 913–920. in Google Scholar PubMed

Cain, S.M., Bernier, L.P., Zhang, Y., Yung, A.C., Kass, J., Bohnet, B., Yang, Y., Gopaul, R., Kozlowski, P., MacVicar, B.A., et al.. (2022). Hyperexcitable superior colliculus and fatal brainstem spreading depolarization in a model of sudden unexpected death in epilepsy. Brain Commun. 4: 1–12, in Google Scholar

Cardenas, D.P., Halford, J.J., Whitmire, L.E., Morgan, L.C., Lie, O.V., Jetter, G.M., and Cavazos, J.E. (2020). Automated processing of single-channel surface electromyography from generalized tonic-clonic seizures to inform semiology. J. Clin. Neurophysiol. 37: 56–61. in Google Scholar

Chahal, C.A.A., Salloum, M.N., Alahdab, F., Gottwald, J.A., Tester, D.J., Anwer, L.A., So, E.L., Murad, M.H., Louis, E.K.S., Ackerman, M.J., et al.. (2020). Systematic review of the genetics of sudden unexpected death in epilepsy: potential overlap with sudden cardiac death and arrhythmia-related genes. J. Am. Heart Assoc. 9: e012264. in Google Scholar

Chen, Z.S., Hsieh, A., Sun, G., Bergey, G.K., Berkovic, S.F., Perucca, P., D’Souza, W., Elder, C.J., Farooque, P., Johnson, E.L., et al.., MS-BioS Study Group. (2022). Interictal EEG and ECG for SUDEP risk assessment: a retrospective multicenter cohort study. Front. Neurol. 13: 858333. in Google Scholar

Cui, L., Huang, Y., Tao, S., Lhatoo, S.D., and Zhang, G.Q. (2016). ODaCCI: ontology-guided data curation for multisite clinical research data integration in the NINDS center for SUDEP research. AMIA Annu. Symp. Proc. 2016: 441–450.Search in Google Scholar

Davatzikos, C. (2019). Machine learning in neuroimaging: progress and challenges. Neuroimage 197: 652–656. in Google Scholar

Devinsky, O., Hesdorffer, D.C., Thurman, D.J., Lhatoo, S., and Richerson, G. (2016). Sudden unexpected death in epilepsy: epidemiology, mechanisms, and prevention. Lancet Neurol. 15: 1075–1088. in Google Scholar

Devinsky, O., Vezzani, A., O’Brien, T.J., Jette, N., Scheffer, I.E., de Curtis, M., and Perucca, P. (2018). Epilepsy. Nat. Rev. Dis. Prim. 4: 18024. in Google Scholar PubMed

Dhaibar, H., Gautier, N.M., Chernyshev, O.Y., Dominic, P., and Glasscock, E. (2019). Cardiorespiratory profiling reveals primary breathing dysfunction in Kcna1-null mice: implications for sudden unexpected death in epilepsy. Neurobiol. Dis. 127: 502–511. in Google Scholar PubMed PubMed Central

Einarsdottir, A.B., Sveinsson, O., and Olafsson, E. (2019). Sudden unexpected death in epilepsy. A nationwide population-based study. Epilepsia 60: 2174–2181. in Google Scholar PubMed

Faingold, C.L., Randall, M., and Tupal, S. (2010). DBA/1 mice exhibit chronic susceptibility to audiogenic seizures followed by sudden death associated with respiratory arrest. Epilepsy Behav. 17: 436–440. in Google Scholar PubMed

Faingold, C.L., Randall, M., Zeng, C., Peng, S., Long, X., and Feng, H.-J. (2016). Serotonergic agents act on 5-HT(3) receptors in the brain to block seizure-induced respiratory arrest in the DBA/1 mouse model of SUDEP. Epilepsy Behav. 64: 166–170. in Google Scholar PubMed PubMed Central

Frasier, C.R., Wagnon, J.L., Bao, Y.O., McVeigh, L.G., Lopez-Santiago, L.F., Meisler, M.H., and Isom, L.L. (2016). Cardiac arrhythmia in a mouse model of sodium channel SCN8A epileptic encephalopathy. Proc. Natl. Acad. Sci. USA 113: 12838–12843. in Google Scholar PubMed PubMed Central

Friedman, D. (2017). Epilepsy: a new guideline on sudden unexpected death in epilepsy. Nat. Rev. Neurol. 13: 388–389. in Google Scholar PubMed

Friedman, D., Kannan, K., Faustin, A., Shroff, S., Thomas, C., Heguy, A., Serrano, J., Snuderl, M., and Devinsky, O. (2018). Cardiac arrhythmia and neuroexcitability gene variants in resected brain tissue from patients with sudden unexpected death in epilepsy (SUDEP). NPJ Genom. Med. 3: 9. in Google Scholar PubMed PubMed Central

Geertsema, E.E., Thijs, R.D., Gutter, T., Vledder, B., Arends, J.B., Leijten, F.S., Visser, G.H., and Kalitzin, S.N. (2018). Automated video-based detection of nocturnal convulsive seizures in a residential care setting. Epilepsia 59(Suppl 1): 53–60. in Google Scholar PubMed

Glasscock, E. (2014). Genomic biomarkers of SUDEP in brain and heart. Epilepsy Behav. 38: 172–179. in Google Scholar PubMed PubMed Central

Glasscock, E., Yoo, J.W., Chen, T.T., Klassen, T.L., and Noebels, J.L. (2010). Kv1.1 potassium channel deficiency reveals brain-driven cardiac dysfunction as a candidate mechanism for sudden unexplained death in epilepsy. J. Neurosci. 30: 5167–5175. in Google Scholar

Goldman, A.M., Behr, E.R., Semsarian, C., Bagnall, R.D., Sisodiya, S., and Cooper, P.N. (2016). Sudden unexpected death in epilepsy genetics: molecular diagnostics and prevention. Epilepsia 57(Suppl 1): 17–25. in Google Scholar PubMed PubMed Central

Griffin, A., Hamling, K.R., Hong, S., Anvar, M., Lee, L.P., and Baraban, S.C. (2018). Preclinical animal models for Dravet syndrome: seizure phenotypes, comorbidities and drug screening. Front. Pharmacol. 9, 573. in Google Scholar PubMed PubMed Central

Grigorovsky, V., Jacobs, D., Breton, V.L., Tufa, U., Lucasius, C., del Campo, J.M., Chinvarun, Y., Carlen, P.L., Wennberg, R., and Bardakjian, B.L. (2020). Delta-gamma phase-amplitude coupling as a biomarker of postictal generalized EEG suppression. Brain Commun. 2: 1–16, in Google Scholar PubMed PubMed Central

Gu, B., Levine, N.G., Xu, W., Lynch, R.M., Pardo-Manuel de Villena, F., and Philpot, B.D. (2022). Ictal neural oscillatory alterations precede sudden unexpected death in epilepsy. Brain Commun. 4: 1–11, in Google Scholar PubMed PubMed Central

Gu, B., Shorter, J.R., Williams, L.H., Bell, T.A., Hock, P., Dalton, K.A., Pan, Y., Miller, D.R., Shaw, G.D., Philpot, B.D., et al.. (2020). Collaborative Cross mice reveal extreme epilepsy phenotypes and genetic loci for seizure susceptibility. Epilepsia 61: 2010–2021. in Google Scholar PubMed PubMed Central

Gutierrez, E.G., Crone, N.E., Kang, J.Y., Carmenate, Y.I., and Krauss, G.L. (2018). Strategies for non-EEG seizure detection and timing for alerting and interventions with tonic-clonic seizures. Epilepsia 59(Suppl 1): 36–41. in Google Scholar PubMed

Hartings, J.A., Li, C., Hinzman, J.M., Shuttleworth, C.W., Ernst, G.L., Dreier, J.P., Wilson, J.A., Andaluz, N., Foreman, B., and Carlson, A.P. (2017). Direct current electrocorticography for clinical neuromonitoring of spreading depolarizations. J. Cerebr. Blood Flow Metabol. 37: 1857–1870. in Google Scholar PubMed PubMed Central

Hutson, T.N., Rezaei, F., Gautier, N.M., Indumathy, J., Glasscock, E., and Iasemidis, L. (2020). Directed connectivity analysis of the neuro-cardio- and respiratory systems reveals novel biomarkers of susceptibility to SUDEP. IEEE Open J. Eng. Med. Biol. 1: 301–311. in Google Scholar PubMed PubMed Central

Iasemidis, L.D. (2011). Seizure prediction and its applications. Neurosurg. Clin. 22: 489–506. in Google Scholar PubMed PubMed Central

Jefferys, J.G.R., Arafat, M.A., Irazoqui, P.P., and Lovick, T.A. (2019). Brainstem activity, apnea, and death during seizures induced by intrahippocampal kainic acid in anaesthetized rats. Epilepsia 60: 2346–2358. in Google Scholar PubMed

Jha, A., Oh, C., Hesdorffer, D., Diehl, B., Devore, S., Brodie, M.J., Tomson, T., Sander, J.W., Walczak, T.S., and Devinsky, O. (2021). Sudden unexpected death in epilepsy: a personalized prediction tool. Neurology 96: e2627–e2638. in Google Scholar PubMed PubMed Central

Johnson, M., Samudra, N., Gallagher, M.J., Abou-Khalil, B., and Nobis, W.P. (2021). Near SUDEP during bilateral stereo-EEG monitoring characterized by diffuse postictal EEG suppression. Epilepsia 62: e60–e64. in Google Scholar PubMed

Kalume, F., Westenbroek, R.E., Cheah, C.S., Yu, F.H., Oakley, J.C., Scheuer, T., and Catterall, W.A. (2013). Sudden unexpected death in a mouse model of Dravet syndrome. J. Clin. Invest. 123: 1798–1808. in Google Scholar

Kang, J.Y., Rabiei, A.H., Myint, L., and Nei, M. (2017). Equivocal significance of post-ictal generalized EEG suppression as a marker of SUDEP risk. Seizure Eur. J. Epilepsy 48: 28–32. in Google Scholar PubMed

Kim, Y., Bravo, E., Thirnbeck, C.K., Smith-Mellecker, L.A., Kim, S.H., Gehlbach, B.K., Laux, L.C., Zhou, X., Nordli, D.R.Jr., and Richerson, G.B. (2018). Severe peri-ictal respiratory dysfunction is common in Dravet syndrome. J. Clin. Invest. 128: 1141–1153. in Google Scholar PubMed PubMed Central

Kløvgaard, M., Lynge, T.H., Tsiropoulos, I., Uldall, P.V., Banner, J., Winkel, B.G., Ryvlin, P., Tfelt-Hansen, J., and Sabers, A. (2021). Sudden unexpected death in epilepsy in persons younger than 50 years: a retrospective nationwide cohort study in Denmark. Epilepsia 62: 2405–2415. in Google Scholar PubMed

Kumar, A., Alhourani, H., Abdelkader, A., Shah, A.K., Juhász, C., and Basha, M.M. (2021). Frontal lobe hypometabolism associated with sudden unexpected death in epilepsy (SUDEP) risk: an objective PET study. Epilepsy Behav. 122: 108185. in Google Scholar PubMed

Kuo, J., Zhao, W., Li, C.S., Kennedy, J.D., and Seyal, M. (2016). Postictal immobility and generalized EEG suppression are associated with the severity of respiratory dysfunction. Epilepsia 57: 412–417. in Google Scholar PubMed PubMed Central

La, A., Rm, H., M, G., R, K., Ja, O., Sb, V., S, O., Ca, S., Sd, L., L, L., et al.. (2019). Altered brain connectivity in sudden unexpected death in epilepsy (SUDEP) revealed using resting-state fMRI. Neuroimage Clin 24: 102060. in Google Scholar PubMed PubMed Central

Lamberts, R.J., Gaitatzis, A., Sander, J.W., Elger, C.E., Surges, R., and Thijs, R.D. (2013). Postictal generalized EEG suppression: an inconsistent finding in people with multiple seizures. Neurology 81: 1252–1256. in Google Scholar PubMed PubMed Central

Lamichhane, B., Kim, Y., Segarra, S., Zhang, G., Lhatoo, S., Hampson, J., and Jiang, X. (2020). Automated detection of activity onset after postictal generalized EEG suppression. BMC Med. Inf. Decis. Making 20: 327. in Google Scholar PubMed PubMed Central

Lertwittayanon, W., Devinsky, O., and Carlen, P.L. (2020). Cardiorespiratory depression from brainstem seizure activity in freely moving rats. Neurobiol. Dis. 134: 104628. in Google Scholar PubMed

Lhatoo, S., Noebels, J., Whittemore, V., and Research, N.C.f. S. (2015). Sudden unexpected death in epilepsy:identifying risk and preventing mortality. Epilepsia 56: 1700–1706. in Google Scholar PubMed PubMed Central

Lhatoo, S.D., Faulkner, H.J., Dembny, K., Trippick, K., Johnson, C., and Bird, J.M. (2010). An electroclinical case-control study of sudden unexpected death in epilepsy. Ann. Neurol. 68: 787–796. in Google Scholar PubMed

Li, X., Tao, S., Jamal-Omidi, S., Huang, Y., Lhatoo, S.D., Zhang, G.Q., and Cui, L. (2020a). Detection of postictal generalized electroencephalogram suppression: random forest approach. JMIR Med. Inform 8: e17061. in Google Scholar PubMed PubMed Central

Li, Y., Yu, Z., Chen, Y., Yang, C., Li, Y., Allen Li, X., and Li, B. (2020b). Automatic seizure detection using fully convolutional nested LSTM. Int. J. Neural Syst. 30: 2050019. in Google Scholar PubMed

Lin, X., O’Malley, H., Chen, C., Auerbach, D., Foster, M., Shekhar, A., Zhang, M., Coetzee, W., Jalife, J., Fishman, G.I., et al.. (2015). Scn1b deletion leads to increased tetrodotoxin-sensitive sodium current, altered intracellular calcium homeostasis and arrhythmias in murine hearts. J. Physiol. 593: 1389–1407. in Google Scholar PubMed PubMed Central

Liu, G., Zhou, W., and Geng, M. (2020). Automatic seizure detection based on S-transform and deep convolutional neural network. Int. J. Neural Syst. 30: 1950024. in Google Scholar PubMed

Loonen, I.C.M., Jansen, N.A., Cain, S.M., Schenke, M., Voskuyl, R.A., Yung, A.C., Bohnet, B., Kozlowski, P., Thijs, R.D., Ferrari, M.D., et al.. (2019). Brainstem spreading depolarization and cortical dynamics during fatal seizures in Cacna1a S218L mice. Brain 142: 412–425. in Google Scholar PubMed PubMed Central

Lum, G.R., Olson, C.A., and Hsiao, E.Y. (2020). Emerging roles for the intestinal microbiome in epilepsy. Neurobiol. Dis. 135: 104576. in Google Scholar PubMed

Ma, D., Yuan, S., Shang, J., Liu, J., Dai, L., Kong, X., and Xu, F. (2021). The automatic detection of seizure based on tensor distance and bayesian linear discriminant analysis. Int. J. Neural Syst. 31: 2150006. in Google Scholar PubMed

Mandal, R., Budde, R., Lawlor, G.L., and Irazoqui, P. (2021). Utilizing multimodal imaging to visualize potential mechanism for sudden death in epilepsy. Epilepsy Behav. 122: 108124. in Google Scholar PubMed PubMed Central

Marincovich, A., Bravo, E., Dlouhy, B., and Richerson, G.B. (2021). Amygdala lesions reduce seizure-induced respiratory arrest in DBA/1 mice. Epilepsy Behav. 121: 106440. in Google Scholar PubMed PubMed Central

Martin, B., Dieuset, G., Pawluski, J.L., Costet, N., and Biraben, A. (2020). Audiogenic seizure as a model of sudden death in epilepsy: a comparative study between four inbred mouse strains from early life to adulthood. Epilepsia 61: 342–349. in Google Scholar PubMed

Massey, C.A., Sowers, L.P., Dlouhy, B.J., and Richerson, G.B. (2014). Mechanisms of sudden unexpected death in epilepsy: the pathway to prevention. Nat. Rev. Neurol. 10: 271–282. in Google Scholar PubMed PubMed Central

Mbizvo, G.K., Schnier, C., Simpson, C.R., Chin, R.F.M., and Duncan, S.E. (2021). A national study of epilepsy-related deaths in Scotland: trends, mechanisms, and avoidable deaths. Epilepsia 62: 2667–2684. in Google Scholar PubMed

Mier, J.C., Kim, Y., Jiang, X., Zhang, G.Q., and Lhatoo, S. (2020). Categorisation of EEG suppression using enhanced feature extraction for SUDEP risk assessment. BMC Med. Inf. Decis. Making 20: 326. in Google Scholar PubMed PubMed Central

Moradi, F., Mohammadi, H., Rezaei, M., Sariaslani, P., Razazian, N., Khazaie, H., and Adeli, H. (2020). A novel method for sleep-stage classification based on sonification of sleep electroencephalogram signals using wavelet transform and recurrent neural network. Eur. Neurol. 83: 468–486. in Google Scholar PubMed

Mueller, S.G., Nei, M., Bateman, L.M., Knowlton, R., Laxer, K.D., Friedman, D., Devinsky, O., and Goldman, A.M. (2018). Brainstem network disruption: a pathway to sudden unexplained death in epilepsy? Hum. Brain Mapp. 39: 4820–4830. in Google Scholar PubMed PubMed Central

Nagaraj, V., Lee, S.T., Krook-Magnuson, E., Soltesz, I., Benquet, P., Irazoqui, P.P., and Netoff, T.I. (2015). Future of seizure prediction and intervention: closing the loop. J. Clin. Neurophysiol. 32: 194–206. in Google Scholar PubMed PubMed Central

Nashef, L., So, E.L., Ryvlin, P., and Tomson, T. (2012). Unifying the definitions of sudden unexpected death in epilepsy. Epilepsia 53: 227–233. in Google Scholar PubMed

Nobis, W.P., Gonzalez Otarula, K.A., Templer, J.W., Gerard, E.E., VanHaerents, S., Lane, G., Zhou, G., Rosenow, J.M., Zelano, C., and Schuele, S. (2019). The effect of seizure spread to the amygdala on respiration and onset of ictal central apnea. J. Neurosurg. 132: 1–11, in Google Scholar PubMed PubMed Central

Nobis, W.P., Schuele, S., Templer, J.W., Zhou, G., Lane, G., Rosenow, J.M., and Zelano, C. (2018). Amygdala-stimulation-induced apnea is attention and nasal-breathing dependent. Ann. Neurol. 83: 460–471. in Google Scholar PubMed PubMed Central

Nogay, H.S. and Adeli, H. (2020). Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning. Eur. Neurol. 83: 602–614. in Google Scholar PubMed

O’Shea, A., Ahmed, R., Lightbody, G., Pavlidis, E., Lloyd, R., Pisani, F., Marnane, W., Mathieson, S., Boylan, G., and Temko, A. (2021). Deep learning for EEG seizure detection in preterm infants. Int. J. Neural Syst. 31: 2150008. in Google Scholar PubMed

Olson, C.A., Vuong, H.E., Yano, J.M., Liang, Q.Y., Nusbaum, D.J., and Hsiao, E.Y. (2018). The gut microbiota mediates the anti-seizure effects of the ketogenic diet. Cell 173: 1728–1741, e1713. in Google Scholar PubMed PubMed Central

Onorati, F., Regalia, G., Caborni, C., Migliorini, M., Bender, D., Poh, M.Z., Frazier, C., Kovitch Thropp, E., Mynatt, E.D., Bidwell, J., et al.. (2017). Multicenter clinical assessment of improved wearable multimodal convulsive seizure detectors. Epilepsia 58: 1870–1879. in Google Scholar PubMed

Pansani, A.P., Colugnati, D.B., Scorza, C.A., de Almeida, A.C., Cavalheiro, E.A., and Scorza, F.A. (2016). Furthering our understanding of SUDEP: the role of animal models. Expert Rev. Neurother. 16: 561–572. in Google Scholar PubMed

Park, K., Kanth, K., Bajwa, S., Girgis, F., Shahlaie, K., and Seyal, M. (2020). Seizure-related apneas have an inconsistent linkage to amygdala seizure spread. Epilepsia 61: 1253–1260. in Google Scholar PubMed

Patodia, S., Tachrount, M., Somani, A., Scheffer, I., Yousry, T., Golay, X., Sisodiya, S.M., and Thom, M. (2021). MRI and pathology correlations in the medulla in sudden unexpected death in epilepsy (SUDEP): a postmortem study. Neuropathol. Appl. Neurobiol. 47: 157–170. in Google Scholar PubMed PubMed Central

Peng, P., Xie, L., and Wei, H. (2021). A deep fourier neural network for seizure prediction using convolutional neural network and ratios of spectral power. Int. J. Neural Syst. 31: 2150022. in Google Scholar

Petrucci, A.N., Joyal, K.G., Chou, J.W., Li, R., Vencer, K.M., and Buchanan, G.F. (2021). Post-ictal generalized EEG suppression is reduced by enhancing dorsal raphe serotonergic neurotransmission. Neuroscience 453: 206–221. in Google Scholar PubMed PubMed Central

Picard, R.W., Migliorini, M., Caborni, C., Onorati, F., Regalia, G., Friedman, D., and Devinsky, O. (2017). Wrist sensor reveals sympathetic hyperactivity and hypoventilation before probable SUDEP. Neurology 89: 633–635. in Google Scholar

Poh, M.Z., Loddenkemper, T., Reinsberger, C., Swenson, N.C., Goyal, S., Madsen, J.R., and Picard, R.W. (2012). Autonomic changes with seizures correlate with postictal EEG suppression. Neurology 78: 1868–1876. in Google Scholar

Rajakulendran, S. and Nashef, L. (2015). Postictal generalized EEG suppression and SUDEP: a review. J. Clin. Neurophysiol. 32: 14–20. in Google Scholar

Rhone, A.E., Kovach, C.K., Harmata, G.I., Sullivan, A.W., Tranel, D., Ciliberto, M.A., Howard, M.A., Richerson, G.B., Steinschneider, M., Wemmie, J.A., et al.. (2020). A human amygdala site that inhibits respiration and elicits apnea in pediatric epilepsy. JCI Insight 5: 1–16, in Google Scholar

Ryvlin, P., Ciumas, C., Wisniewski, I., and Beniczky, S. (2018). Wearable devices for sudden unexpected death in epilepsy prevention. Epilepsia 59(Suppl 1): 61–66. in Google Scholar

Ryvlin, P., Nashef, L., Lhatoo, S.D., Bateman, L.M., Bird, J., Bleasel, A., Boon, P., Crespel, A., Dworetzky, B.A., Høgenhaven, H., et al.. (2013). Incidence and mechanisms of cardiorespiratory arrests in epilepsy monitoring units (MORTEMUS): a retrospective study. Lancet Neurol. 12: 966–977. in Google Scholar

Saetre, E. and Abdelnoor, M. (2018). Incidence rate of sudden death in epilepsy: a systematic review and meta-analysis. Epilepsy Behav. 86: 193–199. in Google Scholar PubMed

Sarkis, R.A., Thome-Souza, S., Poh, M.-Z., Llewellyn, N., Klehm, J., Madsen, J.R., Picard, R., Pennell, P.B., Dworetzky, B.A., Loddenkemper, T., et al.. (2015). Autonomic changes following generalized tonic clonic seizures: an analysis of adult and pediatric patients with epilepsy. Epilepsy Res. 115: 113–118. in Google Scholar PubMed

Schilling, W.P., McGrath, M.K., Yang, T., Glazebrook, P.A., Faingold, C.L., and Kunze, D.L. (2019). Simultaneous cardiac and respiratory inhibition during seizure precedes death in the DBA/1 audiogenic mouse model of SUDEP. PLoS One 14: e0223468. in Google Scholar PubMed PubMed Central

Sharma, P., Khan, Y.U., Farooq, O., Tripathi, M., and Adeli, H. (2014). A wavelet-statistical features approach for nonconvulsive seizure detection. Clin. EEG Neurosci. 45: 274–284. in Google Scholar PubMed

Surges, R., Strzelczyk, A., Scott, C.A., Walker, M.C., and Sander, J.W. (2011). Postictal generalized electroencephalographic suppression is associated with generalized seizures. Epilepsy Behav. 21: 271–274. in Google Scholar PubMed

Szczurkowska, P.J., Polonis, K., Becari, C., Hoffmann, M., Narkiewicz, K., and Chrostowska, M. (2021). Epilepsy and hypertension: the possible link for sudden unexpected death in epilepsy? Cardiol. J. 28: 330–335. in Google Scholar

Tafazoli, S., MacDowell, C.J., Che, Z., Letai, K.C., Steinhardt, C.R., and Buschman, T.J. (2020). Learning to control the brain through adaptive closed-loop patterned stimulation. J. Neural. Eng. 17: 056007. in Google Scholar PubMed

Theeranaew, W., McDonald, J., Zonjy, B., Kaffashi, F., Moseley, B.D., Friedman, D., So, E., Tao, J., Nei, M., Ryvlin, P., et al.. (2018). Automated detection of postictal generalized EEG suppression. IEEE Trans. Biomed. Eng. 65: 371–377. in Google Scholar PubMed PubMed Central

Threeanaew, W., MacDonald, J., Sinha, A., Kaffashi, F., Lhatoo, S.D., and Loparo, K.A. (2019). Collection and analysis of multimodal data for SUDEP biomarker discovery. IEEE Sens Lett 3: 1–4, in Google Scholar PubMed PubMed Central

Thomas, J., Thangavel, P., Peh, W.Y., Jing, J., Yuvaraj, R., Cash, S.S., Chaudhari, R., Karia, S., Rathakrishnan, R., Saini, V., et al.. (2021). Automated adult epilepsy diagnostic tool based on interictal scalp electroencephalogram characteristics: a six-center study. Int. J. Neural Syst. 31: 2050074. in Google Scholar PubMed

Thurman, D.J., Hesdorffer, D.C., and French, J.A. (2014). Sudden unexpected death in epilepsy: assessing the public health burden. Epilepsia 55: 1479–1485. in Google Scholar PubMed

Torres-Espín, A., Chou, A., Huie, J.R., Kyritsis, N., Upadhyayula, P.S., and Ferguson, A.R. (2021). Reproducible analysis of disease space via principal components using the novel R package syndRomics. Elife 10: e61812.10.7554/eLife.61812.sa2Search in Google Scholar

van Westrhenen, A., Petkov, G., Kalitzin, S.N., Lazeron, R.H.C., and Thijs, R.D. (2020). Automated video-based detection of nocturnal motor seizures in children. Epilepsia 61(Suppl 1): S36–S40. in Google Scholar PubMed PubMed Central

van Westrhenen, A., Souhoka, T., Ballieux, M.E., and Thijs, R.D. (2021). Seizure detection devices: exploring caregivers’ needs and wishes. Epilepsy Behav. 116: 107723. in Google Scholar PubMed

Vilella, L., Lacuey, N., Hampson, J.P., Rani, M.R.S., Sainju, R.K., Friedman, D., Nei, M., Strohl, K., Scott, C., Gehlbach, B.K., et al.. (2019). Postconvulsive central apnea as a biomarker for sudden unexpected death in epilepsy (SUDEP). Neurology 92: e171–e182. in Google Scholar PubMed PubMed Central

Wandschneider, B., Koepp, M., Scott, C., Micallef, C., Balestrini, S., Sisodiya, S.M., Thom, M., Harper, R.M., Sander, J.W., Vos, S.B., et al.. (2015). Structural imaging biomarkers of sudden unexpected death in epilepsy. Brain 138: 2907–2919. in Google Scholar PubMed PubMed Central

Wenker, I.C., Teran, F.A., Wengert, E.R., Wagley, P.K., Panchal, P.S., Blizzard, E.A., Saraf, P., Wagnon, J.L., Goodkin, H.P., Meisler, M.H., et al.. (2021). Postictal death is associated with tonic phase apnea in a mouse model of sudden unexpected death in epilepsy. Ann. Neurol. 89: 1023–1035. in Google Scholar PubMed PubMed Central

Whatley, B.P., Winston, J.S., Allen, L.A., Vos, S.B., Jha, A., Scott, C.A., Smith, A.-L., Chowdhury, F.A., Bomanji, J.B., Lhatoo, S.D., et al.. (2021). Distinct patterns of brain metabolism in patients at risk of sudden unexpected death in epilepsy. Front. Neurol. 12: 1–9, in Google Scholar

Zack, M.M. and Kobau, R. (2017). National and state estimates of the numbers of adults and children with active epilepsy – United States, 2015. MMWR Morb. Mortal. Wkly. Rep. 66: 821–825. in Google Scholar PubMed PubMed Central

Zhang, H., Zhao, H., Yang, X., Xue, Q., Cotten, J.F., and Feng, H.-J. (2016). 5-Hydroxytryptophan, a precursor for serotonin synthesis, reduces seizure-induced respiratory arrest. Epilepsia 57: 1228–1235. in Google Scholar PubMed PubMed Central

Zhang, Y., Yang, R., and Zhou, W. (2020). Roughness-length-based characteristic analysis of intracranial EEG and epileptic seizure prediction. Int. J. Neural Syst. 30: 2050072. in Google Scholar PubMed

Zhao, Y., Zhang, G., Dong, C., Yuan, Q., Xu, F., and Zheng, Y. (2021). Graph attention network with focal loss for seizure detection on electroencephalography signals. Int. J. Neural Syst. 31: 2150027. in Google Scholar

Zhu, C., Kim, Y., Jiang, X., Lhatoo, S., Jaison, H., and Zhang, G.Q. (2020). A lightweight convolutional neural network for assessing an EEG risk marker for sudden unexpected death in epilepsy. BMC Med. Inf. Decis. Making 20: 329. in Google Scholar PubMed PubMed Central

Zibrandtsen, I.C., Kidmose, P., and Kjaer, T.W. (2018). Detection of generalized tonic-clonic seizures from ear-EEG based on EMG analysis. Seizure 59: 54–59. in Google Scholar PubMed

Received: 2022-03-01
Accepted: 2022-04-19
Published Online: 2022-05-27

© 2022 Bin Gu and Hojjat Adeli, published by De Gruyter, Berlin/Boston

This work is licensed under the Creative Commons Attribution 4.0 International License.