Early Seizure Detection Based on Cardiac Autonomic Regulation Dynamics

Pavei, Jonatas; Heinzen, Renan G.; Nováková, Barbora; Walz, Roger; Serra, Andrey Jorge; Reuber, Markus; Ponnusamy, Athi; Marques, Jefferson Luiz Brum

doi:10.3389/fphys.2017.00765

Cited by 53 publications

(45 citation statements)

References 41 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, a combination of both decreased SampEn and suppressed time-domain measures of HRV has been observed in the early stages of neonatal sepsis (Lake et al 2002). In contrast, epileptic seizures in adults are associated with a decrease in SampEn, but an increase in time domain measures of HRV (Pavei et al 2017). In the present study, we observed a third combination during the early latent phase, of increased SampEn in association with suppression of VLF power across all three HI groups.…”

Section: Figure 3 Spectral Power and Sample Entropy Of Fetal Heart Rsupporting

confidence: 65%

See 1 more Smart Citation

Early sinusoidal heart rate patterns and heart rate variability to assess hypoxia–ischaemia in near‐term fetal sheep

Kasai

Lear

Davidson

et al. 2019

The Journal of Physiology

View full text Add to dashboard Cite

Key points •Therapeutic hypothermia needs to be started as early as possible in the first 6 h after acute injury caused by hypoxia–ischaemia (HI), but the severity and timing of HI are often unclear. In this study we evaluated whether measures of heart rate variability (HRV) might provide early biomarkers of HI. •The duration but not magnitude of suppression of HRV power and conversely increased sample entropy of the heart rate were associated with severity of HI, such that changes in the first 3 h did not discriminate between groups. •Relative changes in HRV power bands showed different patterns between groups and therefore may have the potential to evaluate the severity of HI. •Aberrant fetal heart rate patterns and increased arginine vasopressin levels in the first hour after moderate and severe HI were correlated with loss of EEG power after 3 days’ recovery, suggesting potential utility as early biomarkers of outcome. Abstract Therapeutic hypothermia is partially neuroprotective after acute injury caused by hypoxia–ischaemia (HI), likely because the timing and severity of HI are often unclear, making timely recruitment for treatment challenging. We evaluated the utility of changes in heart rate variability (HRV) after HI as biomarkers of the timing and severity of acute HI. Chronically instrumented fetal sheep at 0.85 gestational age were exposed to different durations of umbilical cord occlusion to produce mild (n = 6), moderate (n = 8) or severe HI (n = 8) or to sham occlusion (n = 5). Heart rate (HR) and HRV indices were assessed until 72 h after HI. All HI groups showed suppressed very low frequency HRV power and elevated sample entropy for the first 3 h; more prolonged changes were associated with greater severity of HI. Analysis of relative changes in spectral power showed that the moderate and severe groups showed a shift towards higher HRV frequencies, which was most marked after severe HI. This shift was associated with abnormal rhythmic HR patterns including sinusoidal patterns in the first hour after HI, and with elevated plasma levels of arginine vasopressin, which were correlated with subsequent loss of EEG power by day 3. In conclusion, absolute changes in HRV power in the first 3 h after acute HI were not significantly related to the severity of HI. The intriguing relative shift in spectral power towards higher frequencies likely reflects greater autonomic dysfunction after severe HI. However, sinusoidal HR patterns and elevated vasopressin levels may have utility as biomarkers of severe HI.

show abstract

Section: Figure 3 Spectral Power and Sample Entropy Of Fetal Heart Rsupporting

confidence: 65%

“…In contrast, epileptic seizures in adults are associated with a decrease in SampEn, but an increase in time domain measures of HRV (Pavei et al . ). In the present study, we observed a third combination during the early latent phase, of increased SampEn in association with suppression of VLF power across all three HI groups.…”

Section: Discussionmentioning

confidence: 97%

Early sinusoidal heart rate patterns and heart rate variability to assess hypoxia–ischaemia in near‐term fetal sheep

Kasai

Lear

Davidson

et al. 2019

The Journal of Physiology

View full text Add to dashboard Cite

show abstract

“…They reported sensitivity of 91% percent with a false positive rate of 0.7 per hour (24). On the other hand, Pavei et al (25) used a different approach. The HRV was analyzed using Eigen Decomposition of covariance matrices to create input for support vector machine (SVM) based algorithm.…”

Section: Hrv In Prediction Of Seizure Onsetmentioning

confidence: 99%

“…Furthermore, the false positive rate was tested on 123.6 h of ECG recordings from non-epilepsy patients. The false positive rate was 0.19 per hour for non-epilepsy and 0.49 per hour in epilepsy patients (25). Vandecasteele et al did one of the first studies to compare hospital ECG vs. wearable ECG vs. photpletismography (PPG) devices in seizure prediction.…”

Section: Hrv In Prediction Of Seizure Onsetmentioning

confidence: 99%

Heart rate variability processing in epilepsy: The role in detection and prediction of seizures and SUDEP

Vorkapić¹,

Useinović²,

Janković³

et al. 2018

Medicinski podmladak

View full text Add to dashboard Cite

Epilepsy is a very prevalent neurological disorder. The gold standard in diagnosis of epilepsy is the EEG signal recorded during a seizure with characteristic ictal pattern. Automated systems for detection of seizures are a field of intensive research, in an attempt to create a reproducible, observer-independent mechanism for epilepsy diagnosis. Chronic therapy is a cornerstone of the epilepsy treatment, but the possibility to predict seizure onset and, consequently, to act with medications right before the seizure, instead of relying on everyday medications, is considered the holy grail of epilepsy research. Significant element of morbidity and mortality in epilepsy is sudden unexpected death in epilepsy (SUDEP) that occurs in roughly 1% of patients. Signal analysis techniques for EEG have been a staple in epilepsy research, but recently, with the rise of telemetric systems, heart rate variability (HRV) analysis derived from the ECG signal has been gaining importance. It has been found that perturbations in autonomic nervous system (ANS) regulation occur during, and even up to several minutes before, seizure onset allowing for changes in HRV to act in prediction, as well as detection, of seizures. Also, there is a compelling research exploring the extent of autonomic disbalance during seizures, as well as in the interictal periods in patients at risk for or that have had SUDEP. The focus of this review is to give a short crossection of research involving the utility HRV has in prediction and detection of seizure onset, as well as determining etiology classification and risk evaluation in SUDEP.

show abstract

“…In these studies, epileptic seizures of 13 out of 17 patients (76.47%) are detected, which still lacks the performance required for a reliable seizure detection system. To reach higher seizure detection performance, in [15], the authors combine heart-rate variability and Lorenz-plot features but they do not take into account the battery lifetime required for real-time monitoring of patients on a long-term basis. Despite all these efforts to have low energy consumption while achieving better detection performance, the state-of-theart wearable technologies still suffer from insufficient battery lifetime and detection quality.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Self-Aware Wearable Systems in Epileptic Seizure Detection

Forooghifar

Aminifar

Alonso

2018

2018 21st Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

Today, wearable systems are facing fundamental barriers in terms of battery lifetime and quality of their results. The main challenge in wearable systems is to increase the battery lifetime, while maintaining the machine-learning performance of the system. A recently proposed concept for overcoming this challenge is self-awareness, which increases system's knowledge of itself and the surrounding environment. This is precisely what health monitoring wearable systems require to adapt to different situations. To demonstrate the impact of introducing self-awareness in wearable technologies, we consider the epileptic seizure detection problem, as a case study. Epilepsy affects around 1% of the world's population, which can dramatically degrade the quality of life and represents a major public health issue. As a result, detection of epileptic seizures has become more important over the past decades. In this paper, we aim to introduce a new generation of self-aware wearable systems to decrease energy consumption and improve their seizures detection capabilities by introducing the notion of self-awareness in such systems. These techniques include switching to low-power mode to reduce the energy consumption and machine-learning model enhancement to improve detection quality. We incorporated our proposed techniques in the machine learning module, which detects epileptic seizures by monitoring the cardiac and respiratory systems. We evaluated the performance of our approach based on an epilepsy database of more than 141 hours, provided by the Lausanne University Hospital (CHUV). Our self-aware wearable system achieves 36% reduction in computational complexity and 10.51% improvement in detection performance.

show abstract

Early Seizure Detection Based on Cardiac Autonomic Regulation Dynamics

Cited by 53 publications

References 41 publications

Early sinusoidal heart rate patterns and heart rate variability to assess hypoxia–ischaemia in near‐term fetal sheep

Early sinusoidal heart rate patterns and heart rate variability to assess hypoxia–ischaemia in near‐term fetal sheep

Heart rate variability processing in epilepsy: The role in detection and prediction of seizures and SUDEP

Self-Aware Wearable Systems in Epileptic Seizure Detection

Contact Info

Product

Resources

About