Pre-ictal autonomic changes

AI in ECG: Validating an ambulatory semiology labeller and predictor

OBJECTIVES

Early prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques.

METHODS

We used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance.

RESULTS

Our final system using the Temple University Hospital's Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8-15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively.

CONCLUSIONS

The seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction.

SIGNIFICANCE

EEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient's quality of life.

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

An Effective Dual Self-Attention Residual Network for Seizure Prediction

As one of the most challenging data analysis tasks in chronic brain diseases, epileptic seizure prediction has attracted extensive attention from many researchers. Seizure prediction, can greatly improve patients' quality of life in many ways, such as preventing accidents and reducing harm that may occur during epileptic seizures. This work aims to develop a general method for predicting seizures in specific patients through exploring the time-frequency correlation of features obtained from multi-channel EEG signals. We convert the original EEG signals into spectrograms that represent time-frequency characteristics by applying short-time Fourier transform (STFT) to the EEG signals. For the first time, we propose a dual self-attention residual network (RDANet) that combines a spectrum attention module integrating local features with global features, with a channel attention module mining the interdependence between channel mappings to achieve better forecasting performance. Our proposed approach achieved a sensitivity of 89.33%, a specificity of 93.02%, an AUC of 91.26% and an accuracy of 92.07% on 13 patients from the public CHB-MIT scalp EEG dataset. Our experiments show that different EEG signal prediction segment lengths are an important factor affecting prediction performance. Our proposed method is competitive and achieves good robustness without patient-specific engineering.

Heart rate variability analysis for the identification of the preictal interval in patients with drug-resistant epilepsy

Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure's clinical manifestation. The preictal interval has not yet been clinically parametrized. Furthermore, the duration of this interval varies for seizures both among patients and from the same patient. In this study, we performed a heart rate variability (HRV) analysis to investigate the discriminative power of the features of HRV in the identification of the preictal interval. HRV information extracted from the linear time and frequency domains as well as from nonlinear dynamics were analysed. We inspected data from 238 temporal lobe seizures recorded from 41 patients with drug-resistant epilepsy from the EPILEPSIAE database. Unsupervised methods were applied to the HRV feature dataset, thus leading to a new perspective in preictal interval characterization. Distinguishable preictal behaviour was exhibited by 41% of the seizures and 90% of the patients. Half of the preictal intervals were identified in the 40 min before seizure onset. The results demonstrate the potential of applying clustering methods to HRV features to deepen the current understanding of the preictal state.

Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability

A warning prior to seizure onset can help improve the quality of life for epilepsy patients. The feasibility of a wearable system for predicting epileptic seizures using anomaly detection based on machine learning is evaluated. An original telemeter is developed for continuous measurement of R-R intervals derived from an electrocardiogram. A bespoke smartphone app calculates the indices of heart rate variability in real time from the R-R intervals, and the indices are monitored using multivariate statistical process control by the smartphone app. The proposed system was evaluated on seven epilepsy patients. The accuracy and reliability of the R-R interval measurement, which was examined in comparison with the reference electrocardiogram, showed sufficient performance for heart rate variability analysis. The results obtained using the proposed system were compared with those obtained using the existing video and electroencephalogram assessments; it was noted that the proposed method has a sensitivity of 85.7% in detecting heart rate variability change prior to seizures. The false positive rate of 0.62 times/h was not significantly different from the healthy controls. The prediction performance and practical advantages of portability and real-time operation are demonstrated in this study.

Photoplethysmographic evaluation of generalized tonic-clonic seizures

OBJECTIVE

Photoplethysmography (PPG) is an optical technique measuring variations of blood perfusion in peripheral tissues. We evaluated alterations in PPG signals in relationship to the occurrence of generalized tonic-clonic seizures (GTCSs) in patients with epilepsy to evaluate the feasibility of seizure detection.

METHODS

During electroencephalographic (EEG) long-term monitoring, patients wore portable wristband sensor(s) on their wrists or ankles recording PPG signals. We analyzed PPG signals during three time periods, which were defined with respect to seizures detected on EEG: (1) baseline (>30 minutes prior to seizure), (2) preseizure period, and (3) postseizure period. Furthermore, we selected five random control segments during seizure-free periods. PPG features, including frequency, amplitude, duration, slope, smoothness, and area under the curve, were automatically calculated. We used a linear mixed-effect model to evaluate changes in PPG features between different time periods in an attempt to identify signal changes that detect seizures.

RESULTS

We prospectively enrolled 174 patients from the epilepsy monitoring unit at Boston Children's Hospital. Twenty-five GTCSs were recorded from 13 patients. Data from the first recorded GTCS of each patient were included in the analysis. We observed an increase in PPG frequency during pre- and postseizure periods that was higher than the changes during seizure-free periods (frequency increase: preseizure = 0.22 Hz, postseizure = 0.58 Hz vs changes during seizure-free period = 0.05 Hz). The PPG slope decreased significantly by 56.71 nW/s during preseizure periods compared to seizure-free periods. Additionally, the smoothness increased significantly by 0.22 nW/s during the postseizure period compared to seizure-free periods.

SIGNIFICANCE

Monitoring of PPG signals may assist in the detection of GTCSs in patients with epilepsy. PPG may serve as a promising biomarker for future seizure detection systems and may contribute to future seizure prediction systems.

Personalizing Heart Rate-Based Seizure Detection Using Supervised SVM Transfer Learning

Objective: Automated seizure detection is a key aspect of wearable seizure warning systems. As a result, the quality of life of refractory epilepsy patients could be improved. Most state-of-the-art algorithms for heart rate-based seizure detection use a so-called patient-independent approach, which do not take into account patient-specific data during algorithm training. Although such systems are easy to use in practice, they lead to many false detections as the ictal heart rate changes are patient-dependent. In practice, only a limited amount of accurately annotated patient data is typically available, which makes it difficult to create fully patient-specific algorithms.

Methods: In this context, this study proposes for the first time a new transfer learning approach that allows to personalize heart rate-based seizure detection by using only a couple of days of data per patient. The algorithm was evaluated on 2,172 h of single-lead ECG data from 24 temporal lobe epilepsy patients including 227 focal impaired awareness seizures.

Results: The proposed personalized approach resulted in an overall sensitivity of 71% with 1.9 false detections per hour. This is an average decrease in false detection rate of 37% compared to the reference patient-independent algorithm using only a limited amount of personal seizure data. The proposed transfer learning approach adapts faster and more robustly to patient-specific characteristics than other alternatives for personalization in the literature.

Conclusion: The proposed method allows an easy implementable solution to personalize heart rate-based seizure detection, which can improve the quality of life of refractory epilepsy patients when used as part of a multimodal seizure detection system.

Ictal autonomic changes as a tool for seizure detection: a systematic review

Purpose

Adequate epileptic seizure detection may have the potential to minimize seizure-related complications and improve treatment evaluation. Autonomic changes often precede ictal electroencephalographic discharges and therefore provide a promising tool for timely seizure detection. We reviewed the literature for seizure detection algorithms using autonomic nervous system parameters.

Methods

The PubMed and Embase databases were systematically searched for original human studies that validate an algorithm for automatic seizure detection based on autonomic function alterations. Studies on neonates only and pilot studies without performance data were excluded. Algorithm performance was compared for studies with a similar design (retrospective vs. prospective) reporting both sensitivity and false alarm rate (FAR). Quality assessment was performed using QUADAS-2 and recently reported quality standards on reporting seizure detection algorithms.

Results

Twenty-one out of 638 studies were included in the analysis. Fifteen studies presented a single-modality algorithm based on heart rate variability (n = 10), heart rate (n = 4), or QRS morphology (n = 1), while six studies assessed multimodal algorithms using various combinations of HR, corrected QT interval, oxygen saturation, electrodermal activity, and accelerometry. Most studies had small sample sizes and a short follow-up period. Only two studies performed a prospective validation. A tendency for a lower FAR was found for retrospectively validated algorithms using multimodal autonomic parameters compared to those using single modalities (mean sensitivity per participant 71–100% vs. 64–96%, and mean FAR per participant 0.0–2.4/h vs. 0.7–5.4/h).

Conclusions

The overall quality of studies on seizure detection using autonomic parameters is low. Unimodal autonomic algorithms cannot reach acceptable performance as false alarm rates are still too high. Larger prospective studies are needed to validate multimodal automatic seizure detection.

Electronic supplementary material

The online version of this article (10.1007/s10286-018-0568-1) contains supplementary material, which is available to authorized users.

Online detection of tonic-clonic seizures in pediatric patients using ECG and low-complexity incremental novelty detection

Home monitoring of refractory epilepsy patients has become of more interest the last couple of decades. A biomedical signal that can be used for online seizure detection at home is the electrocardiogram. Previous studies have shown that tonic-clonic seizures are most often accompanied with a strong heart rate increase. The main issue however is the strong patient-specific behavior of the ictal heart rate features, which makes it hard to make a patient-independent seizure detection algorithm. A patient-specific algorithm might be a solution, but existing methods require the availability of data of several seizures, which would make them inefficient in case the first seizure only occurs after a couple of days. Therefore an online method is described here that automatically converts from a patient-independent towards a patient-specific algorithm as more patient-specific data become available. This is done by using online feedback from the users to previously given alarms. By using a simplified one-class classifier, no seizure training data needs to be available for a good performance. The method is already able to adapt to the patient-specific characteristics after a couple of hours, and is able to detect 23 of 24 seizures longer than 10s, with an average of 0.38 false alarms per hour. Due to its low-complexity, it can be easily used for wearable seizure detection at home.

Multimodality peak lctal vital signs during video-EEG monitoring

PURPOSE

To assess and compare peak, multimodal ictal vital signs (iVS) during epileptic seizures (ES) and psychogenic nonepileptic seizures (PNES).

METHODS

Between 4/1/2010 and 4/1/2011, 183 adults had video-EEG monitoring, with 96 consecutive patients meeting inclusion criteria. Heart rate (HR), oxygen saturation (SaO2), and blood pressure (BP) were obtained at baseline and during an ictus. The motor semiology of each ES and PNES was also assessed. Student t-test, Fischer's Test, Wilcoxon Test (p=<0.05), and linear regression provided statistical correlation.

RESULTS

The 46 patients with ES and 50 patients with PNES had similar baseline VS. Generalized tonic-clonic ES had the highest absolute iVS. ES yielded a higher absolute ictal HR (p=0.0004) and lower SaO2 nadir (p=0.003) than PNES. Systolic and diastolic BP did not differ between groups (p=NS). The upper ranges of iS-BP attained a maximum value of 195/135mm Hg in ES and 208/128mmHg in PNES. For ES, the change in ictal HR was inversely correlated with a reduction in ictal SaO2 (CC= -0.4; p=0.003). In PNES, ictal HR correlated with systolic BP (CC=0.6; p=<0.0001), but not ictal SaO2.

CONCLUSION

The inverse relationship between ictal HR and ictal SaO2 in ES suggests a neurobiological difference, and the concept of intrinsic cardio-respiratory dysfunction in patients with epilepsy. The significantly raised peak elevations in ictal HR and ictal systolic BP during PNES demonstrates the potential for serious adverse outcomes if attacks are prolonged.

The role of stress as a trigger for epileptic seizures: a narrative review of evidence from human and animal studies

Stress is one of the most frequently self-identified seizure triggers in patients with epilepsy; however, most previous publications on stress and epilepsy have focused on the role of stress in the initial development of epilepsy. This narrative review explores the causal role of stress in triggering seizures in patients with existing epilepsy. Findings from human studies of psychological stress, as well as of physiologic stress responses in humans and animals, and evidence from nonpharmacologic interventions for epilepsy are considered. The evidence from human studies for stress as a trigger of epileptic seizures is inconclusive. Although retrospective self-report studies show that stress is the most common patient-perceived seizure precipitant, prospective studies have yielded mixed results and studies of life events suggest that stressful experiences only trigger seizures in certain individuals. There is limited evidence suggesting that autonomic arousal can precede seizures. Interventions designed to improve coping with stress reduce seizures in some individuals. Studies of physiologic stress using animal epilepsy models provide more convincing evidence. Exposure to exogenous and endogenous stress mediators has been found to increase epileptic activity in the brain and trigger overt seizures, especially after repeated exposure. In conclusion, stress is likely to exacerbate the susceptibility to epileptic seizures in a subgroup of individuals with epilepsy and may play a role in triggering "spontaneous" seizures. However, there is currently no strong evidence for a close link between stress and seizures in the majority of people with epilepsy, although animal research suggests that such links are likely. Further research is needed into the relationship between stress and seizures and into interventions designed to reduce perceived stress and improve quality of life with epilepsy.