Machine learning from wristband sensor data for wearable, noninvasive seizure forecasting

Autonomic biosignals, seizure detection, and forecasting

Wearable devices have attracted significant attention in epilepsy research in recent years for their potential to enhance patient care through improved seizure monitoring and forecasting. This narrative review presents a detailed overview of the current clinical state of the art while addressing how devices that assess autonomic nervous system (ANS) function reflect seizures and central nervous system (CNS) state changes. This includes a description of the interactions between the CNS and the ANS, including physiological and epilepsy-related changes affecting their dynamics. We first discuss technical aspects of measuring autonomic biosignals and considerations for using ANS sensors in clinical practice. We then review recent seizure detection and seizure forecasting studies, highlighting their performance and capability for seizure detection and forecasting using devices measuring ANS biomarkers. Finally, we address the field's challenges and provide an outlook for future developments.

Artificial intelligence in epilepsy - applications and pathways to the clinic

Artificial intelligence (AI) is rapidly transforming health care, and its applications in epilepsy have increased exponentially over the past decade. Integration of AI into epilepsy management promises to revolutionize the diagnosis and treatment of this complex disorder. However, translation of AI into neurology clinical practice has not yet been successful, emphasizing the need to consider progress to date and assess challenges and limitations of AI. In this Review, we provide an overview of AI applications that have been developed in epilepsy using a variety of data modalities: neuroimaging, electroencephalography, electronic health records, medical devices and multimodal data integration. For each, we consider potential applications, including seizure detection and prediction, seizure lateralization, localization of the seizure-onset zone and assessment for surgical or neurostimulation interventions, and review the performance of AI tools developed to date. We also discuss methodological considerations and challenges that must be addressed to successfully integrate AI into clinical practice. Our goal is to provide an overview of the current state of the field and provide guidance for leveraging AI in future to improve management of epilepsy.

Detection of focal to bilateral tonic-clonic seizures using a connected shirt

OBJECTIVE

This study was undertaken to develop and evaluate a machine learning-based algorithm for the detection of focal to bilateral tonic-clonic seizures (FBTCS) using a novel multimodal connected shirt.

METHODS

We prospectively recruited patients with epilepsy admitted to our epilepsy monitoring unit and asked them to wear the connected shirt while under simultaneous video-electroencephalographic monitoring. Electrocardiographic (ECG) and accelerometric (ACC) signals recorded with the connected shirt were used for the development of the seizure detection algorithm. First, we used a sliding window to extract linear and nonlinear features from both ECG and ACC signals. Then, we trained an extreme gradient boosting algorithm (XGBoost) to detect FBTCS according to seizure onset and offset annotated by three board-certified epileptologists. Finally, we applied a postprocessing step to regularize the classification output. A patientwise nested cross-validation was implemented to evaluate the performances in terms of sensitivity, false alarm rate (FAR), time in false warning (TiW), detection latency, and receiver operating characteristic area under the curve (ROC-AUC).

RESULTS

We recorded 66 FBTCS from 42 patients who wore the connected shirt for a total of 8067 continuous hours. The XGBoost algorithm reached a sensitivity of 84.8% (56/66 seizures), with a median FAR of .55/24 h and a median TiW of 10 s/alarm. ROC-AUC was .90 (95% confidence interval = .88-.91). Median detection latency from the time of progression to the bilateral tonic-clonic phase was 25.5 s.

SIGNIFICANCE

The novel connected shirt allowed accurate detection of FBTCS with a low false alarm rate in a hospital setting. Prospective studies in a residential setting with a real-time and online seizure detection algorithm are required to validate the performance and usability of this device.

Comparison between epileptic seizure prediction and forecasting based on machine learning

Epilepsy affects around 1% of the population worldwide. Anti-epileptic drugs are an excellent option for controlling seizure occurrence but do not work for around one-third of patients. Warning devices employing seizure prediction or forecasting algorithms could bring patients new-found comfort and quality of life. These algorithms would attempt to detect a seizure's preictal period, a transitional moment between regular brain activity and the seizure, and relay this information to the user. Over the years, many seizure prediction studies using Electroencephalogram-based methodologies have been developed, triggering an alarm when detecting the preictal period. Recent studies have suggested a shift in view from prediction to forecasting. Seizure forecasting takes a probabilistic approach to the problem in question instead of the crisp approach of seizure prediction. In this field of study, the triggered alarm to symbolize the detection of a preictal period is substituted by a constant risk assessment analysis. The present work aims to explore methodologies capable of seizure forecasting and establish a comparison with seizure prediction results. Using 40 patients from the EPILEPSIAE database, we developed several patient-specific prediction and forecasting algorithms with different classifiers (a Logistic Regression, a 15 Support Vector Machines ensemble, and a 15 Shallow Neural Networks ensemble). Results show an increase of the seizure sensitivity in forecasting relative to prediction of up to 146% and in the number of patients that displayed an improvement over chance of up to 300%. These results suggest that a seizure forecasting methodology may be more suitable for seizure warning devices than a seizure prediction one.

Leveraging Machine Learning for Personalized Wearable Biomedical Devices: A Review

This review investigates the convergence of artificial intelligence (AI) and personalized health monitoring through wearable devices, classifying them into three distinct categories: bio-electrical, bio-impedance and electro-chemical, and electro-mechanical. Wearable devices have emerged as promising tools for personalized health monitoring, utilizing machine learning to distill meaningful insights from the expansive datasets they capture. Within the bio-electrical category, these devices employ biosignal data, such as electrocardiograms (ECGs), electromyograms (EMGs), electroencephalograms (EEGs), etc., to monitor and assess health. The bio-impedance and electro-chemical category focuses on devices measuring physiological signals, including glucose levels and electrolytes, offering a holistic understanding of the wearer's physiological state. Lastly, the electro-mechanical category encompasses devices designed to capture motion and physical activity data, providing valuable insights into an individual's physical activity and behavior. This review critically evaluates the integration of machine learning algorithms within these wearable devices, illuminating their potential to revolutionize healthcare. Emphasizing early detection, timely intervention, and the provision of personalized lifestyle recommendations, the paper outlines how the amalgamation of advanced machine learning techniques with wearable devices can pave the way for more effective and individualized healthcare solutions. The exploration of this intersection promises a paradigm shift, heralding a new era in healthcare innovation and personalized well-being.

Ultradian rhythms in accelerometric and autonomic data vary based on seizure occurrence in paediatric epilepsy patients

Ultradian rhythms are physiological oscillations that resonate with period lengths shorter than 24 hours. This study examined the expression of ultradian rhythms in patients with epilepsy, a disease defined by an enduring seizure risk that may vary cyclically. Using a wearable device, we recorded heart rate, body temperature, electrodermal activity and limb accelerometry in patients admitted to the paediatric epilepsy monitoring unit. In our case-control design, we included recordings from 29 patients with tonic-clonic seizures and 29 non-seizing controls. We spectrally decomposed each signal to identify cycle lengths of interest and compared average spectral power- and period-related markers between groups. Additionally, we related seizure occurrence to the phase of ultradian rhythm in patients with recorded seizures. We observed prominent 2- and 4-hour-long ultradian rhythms of accelerometry, as well as 4-hour-long oscillations in heart rate. Patients with seizures displayed a higher peak power in the 2-hour accelerometry rhythm (U = 287, P = 0.038) and a period-lengthened 4-hour heart rate rhythm (U = 291.5, P = 0.037). Those that seized also displayed greater mean rhythmic electrodermal activity (U = 261; P = 0.013). Most seizures occurred during the falling-to-trough quarter phase of accelerometric rhythms (13 out of 27, χ2 = 8.41, P = 0.038). Fluctuations in seizure risk or the occurrence of seizures may interrelate with ultradian rhythms of movement and autonomic function. Longitudinal assessments of ultradian patterns in larger patient samples may enable us to understand how such rhythms may improve the temporal precision of seizure forecasting models.

Feasibility of cardiac-based seizure detection and prediction: A systematic review of non-invasive wearable sensor-based studies

A reliable seizure detection or prediction device can potentially reduce the morbidity and mortality associated with epileptic seizures. Previous findings indicating alterations in cardiac activity during seizures suggest the usefulness of cardiac parameters for seizure detection or prediction. This study aims to examine available studies on seizure detection and prediction based on cardiac parameters using non-invasive wearable devices. The Embase, PubMed, and Scopus databases were used to systematically search according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Human studies that evaluated seizure detection or prediction based on cardiac parameters collected using wearable devices were included. The QUADAS-2 tool and proposed standards for validation for seizure detection devices were used for quality assessment. Twenty-four articles were identified and included in the analysis. Twenty studies evaluated seizure detection algorithms, and four studies focused on seizure prediction. Most studies used either a wrist-worn or chest-worn device for data acquisition. Among the seizure detection studies, cardiac parameters utilized for the algorithms mainly included heart rate (HR) (n = 11) or a combination of HR and heart rate variability (HRV) (n = 6). HR-based seizure detection studies collectively reported a sensitivity range of 56%-100% and a false alarm rate (FAR) of 0.02-8/h, with most studies performing retrospective validation of the algorithms. Three of the seizure prediction studies retrospectively validated multimodal algorithms, combining cardiac features with other physiological signals. Only one study prospectively validated their seizure prediction algorithm using HRV extracted from ECG data collected from a custom wearable device. These studies have demonstrated the feasibility of using cardiac parameters for seizure detection and prediction with wearable devices, with varying algorithmic performance. Many studies are in the proof-of-principle stage, and evidence for real-time detection or prediction is currently limited. Future studies should prioritize further refinement of the algorithm performance with prospective validation using large-scale longitudinal data. PLAIN LANGUAGE SUMMARY: This systematic review highlights the potential use of wearable devices, like wristbands, for detecting and predicting seizures via the measurement of heart activity. By reviewing 24 articles, it was found that most studies focused on using heart rate and changes in heart rate for seizure detection. There was a lack of studies looking at seizure prediction. The results were promising but most studies were not conducted in real-time. Therefore, more real-time studies are needed to verify the usage of heart activity-related wearable devices to detect seizures and even predict them, which will be beneficial to people with epilepsy.

SmartWear body sensors for neurological and neurosurgical patients: A review of current and future technologies

Background/objective

Recent technological advances have allowed for the development of smart wearable devices (SmartWear) which can be used to monitor various aspects of patient healthcare. These devices provide clinicians with continuous biometric data collection for patients in both inpatient and outpatient settings. Although these devices have been widely used in fields such as cardiology and orthopedics, their use in the field of neurosurgery and neurology remains in its infancy.

Methods

A comprehensive literature search for the current and future applications of SmartWear devices in the above conditions was conducted, focusing on outpatient monitoring.

Findings

Through the integration of sensors which measure parameters such as physical activity, hemodynamic variables, and electrical conductivity - these devices have been applied to patient populations such as those at risk for stroke, suffering from epilepsy, with neurodegenerative disease, with spinal cord injury and/or recovering from neurosurgical procedures. Further, these devices are being tested in various clinical trials and there is a demonstrated interest in the development of new technologies.

Conclusion

This review provides an in-depth evaluation of the use of SmartWear in selected neurological diseases and neurosurgical applications. It is clear that these devices have demonstrated efficacy in a variety of neurological and neurosurgical applications, however challenges such as data privacy and management must be addressed.

Seizure forecasting: Bifurcations in the long and winding road

To date, the unpredictability of seizures remains a source of suffering for people with epilepsy, motivating decades of research into methods to forecast seizures. Originally, only few scientists and neurologists ventured into this niche endeavor, which, given the difficulty of the task, soon turned into a long and winding road. Over the past decade, however, our narrow field has seen a major acceleration, with trials of chronic electroencephalographic devices and the subsequent discovery of cyclical patterns in the occurrence of seizures. Now, a burgeoning science of seizure timing is emerging, which in turn informs best forecasting strategies for upcoming clinical trials. Although the finish line might be in view, many challenges remain to make seizure forecasting a reality. This review covers the most recent scientific, technical, and medical developments, discusses methodology in detail, and sets a number of goals for future studies.

Seizure forecasting using minimally invasive, ultra-long-term subcutaneous electroencephalography: Individualized intrapatient models

OBJECTIVE

One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG.

METHODS

We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation.

RESULTS

Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence.

SIGNIFICANCE

This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.

Seizure forecasting: Where do we stand?

A lot of mileage has been made recently on the long and winding road toward seizure forecasting. Here we briefly review some selected milestones passed along the way, which were discussed at the International Conference for Technology and Analysis of Seizures-ICTALS 2022-convened at the University of Bern, Switzerland. Major impetus was gained recently from wearable and implantable devices that record not only electroencephalography, but also data on motor behavior, acoustic signals, and various signals of the autonomic nervous system. This multimodal monitoring can be performed for ultralong timescales covering months or years. Accordingly, features and metrics extracted from these data now assess seizure dynamics with a greater degree of completeness. Most prominently, this has allowed the confirmation of the long-suspected cyclical nature of interictal epileptiform activity, seizure risk, and seizures. The timescales cover daily, multi-day, and yearly cycles. Progress has also been fueled by approaches originating from the interdisciplinary field of network science. Considering epilepsy as a large-scale network disorder yielded novel perspectives on the pre-ictal dynamics of the evolving epileptic brain. In addition to discrete predictions that a seizure will take place in a specified prediction horizon, the community broadened the scope to probabilistic forecasts of a seizure risk evolving continuously in time. This shift of gears triggered the incorporation of additional metrics to quantify the performance of forecasting algorithms, which should be compared to the chance performance of constrained stochastic null models. An imminent task of utmost importance is to find optimal ways to communicate the output of seizure-forecasting algorithms to patients, caretakers, and clinicians, so that they can have socioeconomic impact and improve patients' well-being.

Artificial Intelligence-Powered Electronic Skin

Skin-interfaced electronics is gradually changing medical practices by enabling continuous and noninvasive tracking of physiological and biochemical information. With the rise of big data and digital medicine, next-generation electronic skin (e-skin) will be able to use artificial intelligence (AI) to optimize its design as well as uncover user-personalized health profiles. Recent multimodal e-skin platforms have already employed machine learning (ML) algorithms for autonomous data analytics. Unfortunately, there is a lack of appropriate AI protocols and guidelines for e-skin devices, resulting in overly complex models and non-reproducible conclusions for simple applications. This review aims to present AI technologies in e-skin hardware and assess their potential for new inspired integrated platform solutions. We outline recent breakthroughs in AI strategies and their applications in engineering e-skins as well as understanding health information collected by e-skins, highlighting the transformative deployment of AI in robotics, prosthetics, virtual reality, and personalized healthcare. We also discuss the challenges and prospects of AI-powered e-skins as well as predictions for the future trajectory of smart e-skins.

Artificial intelligence-enhanced epileptic seizure detection by wearables

OBJECTIVE

Wrist- or ankle-worn devices are less intrusive than the widely used electroencephalographic (EEG) systems for monitoring epileptic seizures. Using custom-developed deep-learning seizure detection models, we demonstrate the detection of a broad range of seizure types by wearable signals.

METHODS

Patients admitted to the epilepsy monitoring unit were enrolled and asked to wear wearable sensors on either wrists or ankles. We collected patients' electrodermal activity, accelerometry (ACC), and photoplethysmography, from which blood volume pulse (BVP) is derived. Board-certified epileptologists determined seizure onset, offset, and types using video and EEG recordings per the International League Against Epilepsy 2017 classification. We applied three neural network models-a convolutional neural network (CNN) and a CNN-long short-term memory (LSTM)-based generalized detection model and an autoencoder-based personalized detection model-to the raw time-series sensor data to detect seizures and utilized performance measures, including sensitivity, false positive rate (the number of false alarms divided by the total number of nonseizure segments), number of false alarms per day, and detection delay. We applied a 10-fold patientwise cross-validation scheme to the multisignal biosensor data and evaluated model performance on 28 seizure types.

RESULTS

We analyzed 166 patients (47.6% female, median age = 10.0 years) and 900 seizures (13 254 h of sensor data) for 28 seizure types. With a CNN-LSTM-based seizure detection model, ACC, BVP, and their fusion performed better than chance; ACC and BVP data fusion reached the best detection performance of 83.9% sensitivity and 35.3% false positive rate. Nineteen of 28 seizure types could be detected by at least one data modality with area under receiver operating characteristic curve > .8 performance.

SIGNIFICANCE

Results from this in-hospital study contribute to a paradigm shift in epilepsy care that entails noninvasive seizure detection, provides time-sensitive and accurate data on additional clinical seizure types, and proposes a novel combination of an out-of-the-box monitoring algorithm with an individualized person-oriented seizure detection approach.

Learning to generalize seizure forecasts

OBJECTIVE

Epilepsy is characterized by spontaneous seizures that recur at unexpected times. Nonetheless, using years-long electroencephalographic (EEG) recordings, we previously found that patient-reported seizures consistently occur when interictal epileptiform activity (IEA) cyclically builds up over days. This multidien (multiday) interictal-ictal relationship, which is shared across patients, may bear phasic information for forecasting seizures, even if individual patterns of seizure timing are unknown. To test this rigorously in a large retrospective dataset, we pretrained algorithms on data recorded from a group of patients, and forecasted seizures in other, previously unseen patients.

METHODS

We used retrospective long-term data from participants (N = 159) in the RNS System clinical trials, including intracranial EEG recordings (icEEG), and from two participants in the UNEEG Medical clinical trial of a subscalp EEG system (sqEEG). Based on IEA detections, we extracted instantaneous multidien phases and trained generalized linear models (GLMs) and recurrent neural networks (RNNs) to forecast the probability of seizure occurrence at a 24-h horizon.

RESULTS

With GLMs and RNNs, seizures could be forecasted above chance in 79% and 81% of previously unseen subjects with a median discrimination of area under the curve (AUC) = .70 and .69 and median Brier skill score (BSS) = .07 and .08. In direct comparison, individualized models had similar median performance (AUC = .67, BSS = .08), but for fewer subjects (60%). Moreover, calibration of pretrained models could be maintained to accommodate different seizure rates across subjects.

SIGNIFICANCE

Our findings suggest that seizure forecasting based on multidien cycles of IEA can generalize across patients, and may drastically reduce the amount of data needed to issue forecasts for individuals who recently started collecting chronic EEG data. In addition, we show that this generalization is independent of the method used to record seizures (patient-reported vs. electrographic) or IEA (icEEG vs. sqEEG).

Seizure forecasting using minimally invasive, ultra-long-term subcutaneous EEG: Generalizable cross-patient models

This study describes a generalized cross-patient seizure-forecasting approach using recurrent neural networks with ultra-long-term subcutaneous EEG (sqEEG) recordings. Data from six patients diagnosed with refractory epilepsy and monitored with an sqEEG device were used to develop a generalized algorithm for seizure forecasting using long short-term memory (LSTM) deep-learning classifiers. Electrographic seizures were identified by a board-certified epileptologist. One-minute data segments were labeled as preictal or interictal based on their relationship to confirmed seizures. Data were separated into training and testing data sets, and to compensate for the unbalanced data ratio in training, noise-added copies of preictal data segments were generated to expand the training data set. The mean and standard deviation (SD) of the training data were used to normalize all data, preserving the pseudo-prospective nature of the analysis. Different architecture classifiers were trained and tested using a leave-one-patient-out cross-validation method, and the area under the receiver-operating characteristic (ROC) curve (AUC) was used to evaluate the performance classifiers. The importance of each input signal was evaluated using a leave-one-signal-out method with repeated training and testing for each classifier. Cross-patient classifiers achieved performance significantly better than chance in four of the six patients and an overall mean AUC of 0.602 ± 0.126 (mean ± SD). A time in warning of 37.386% ± 5.006% (mean ± std) and sensitivity of 0.691 ± 0.068 (mean ± std) were observed for patients with better than chance results. Analysis of input channels showed a significant contribution (p < .05) by the Fourier transform of signals channels to overall classifier performance. The relative contribution of input signals varied among patients and architectures, suggesting that the inclusion of all signals contributes to robustness in a cross-patient classifier. These early results show that it is possible to forecast seizures training with data from different patients using two-channel ultra-long-term sqEEG.

Can heart rate variability identify a high-risk state of upcoming seizure?

Heart rate variability (HRV) is an accessible and convenient means to assess the sympathetic/parasympathetic balance. Autonomic dysfunctions may reflect a pro-ictal state and occur before the seizure onset. Previous studies have reported HRV-based models to identify preictal states in continuous electrocardiogram (EKG) monitoring. Here, we evaluated the ability of HRV metrics extracted from daily single resting-state periods to estimate the risk of upcoming seizure(s) using probabilistic forecasts. Daily standardized 10-min vigilance-controlled EKG periods were recorded in 15 patients with drug-resistant focal epilepsy who underwent intracerebral electroencephalography (EEG). Analyses of a total of 156 periods, based on machine learning approaches, suggested that HRV features can identify preictal states with a median AUC of 0.75 [0.68;0.99]. Pseudoprospective daily forecasts yielded a median Brier score of 0.3 [0.18;0.48]. About 60% of preictal days were correctly forecasted, while false positive predictions were noticed in 24% of interictal days. Daily resting HRV seems to capture information on autonomic variations that may reflect a pro-ictal state. The method could be embedded in an ambulatory clinical seizure prediction device, but additional modalities (prodromes, EEG-based features, etc.) should be associated to improve its performance.

Development of a Multivariable Seizure Likelihood Assessment Based on Clinical Information and Short Autonomic Activity Recordings for Children With Epilepsy

BACKGROUND

Predicting seizure likelihood for the following day would enable clinicians to extend or potentially schedule video-electroencephalography (EEG) monitoring when seizure risk is high. Combining standardized clinical data with short-term recordings of wearables to predict seizure likelihood could have high practical relevance as wearable data is easy and fast to collect. As a first step toward seizure forecasting, we classified patients based on whether they had seizures or not during the following recording.

METHODS

Pediatric patients admitted to the epilepsy monitoring unit wore a wearable that recorded the heart rate (HR), heart rate variability (HRV), electrodermal activity (EDA), and peripheral body temperature. We utilized short recordings from 9:00 to 9:15 pm and compared mean values between patients with and without impending seizures. In addition, we collected clinical data: age, sex, age at first seizure, generalized slowing, focal slowing, and spikes on EEG, magnetic resonance imaging findings, and antiseizure medication reduction. We used conventional machine learning techniques with cross-validation to classify patients with and without impending seizures.

RESULTS

We included 139 patients: 78 had no seizures and 61 had at least one seizure after 9 pm during the concurrent video-EEG and E4 recordings. HR (P < 0.01) and EDA (P < 0.01) were lower and HRV (P = 0.02) was higher for patients with than for patients without impending seizures. The average accuracy of group classification was 66%, and the mean area under the receiver operating characteristics was 0.72.

CONCLUSIONS

Short-term wearable recordings in combination with clinical data have great potential as an easy-to-use seizure likelihood assessment tool.

PreEpiSeizures: description and outcomes of physiological data acquisition using wearable devices during video-EEG monitoring in people with epilepsy

The PreEpiSeizures project was created to better understand epilepsy and seizures through wearable technologies. The motivation was to capture physiological information related to epileptic seizures, besides Electroencephalography (EEG) during video-EEG monitorings. If other physiological signals have reliable information of epileptic seizures, unobtrusive wearable technology could be used to monitor epilepsy in daily life. The development of wearable solutions for epilepsy is limited by the nonexistence of datasets which could validate these solutions. Three different form factors were developed and deployed, and the signal quality was assessed for all acquired biosignals. The wearable data acquisition was performed during the video-EEG of patients with epilepsy. The results achieved so far include 59 patients from 2 hospitals totaling 2,721 h of wearable data and 348 seizures. Besides the wearable data, the Electrocardiogram of the hospital is also useable, totalling 5,838 h of hospital data. The quality ECG signals collected with the proposed wearable is equated with the hospital system, and all other biosignals also achieved state-of-the-art quality. During the data acquisition, 18 challenges were identified, and are presented alongside their possible solutions. Though this is an ongoing work, there were many lessons learned which could help to predict possible problems in wearable data collections and also contribute to the epilepsy community with new physiological information. This work contributes with original wearable data and results relevant to epilepsy research, and discusses relevant challenges that impact wearable health monitoring.

EpilepsyNet: Novel automated detection of epilepsy using transformer model with EEG signals from 121 patient population

BACKGROUND

Epilepsy is one of the most common neurological conditions globally, and the fourth most common in the United States. Recurrent non-provoked seizures characterize it and have huge impacts on the quality of life and financial impacts for affected individuals. A rapid and accurate diagnosis is essential in order to instigate and monitor optimal treatments. There is also a compelling need for the accurate interpretation of epilepsy due to the current scarcity in neurologist diagnosticians and a global inequity in access and outcomes. Furthermore, the existing clinical and traditional machine learning diagnostic methods exhibit limitations, warranting the need to create an automated system using deep learning model for epilepsy detection and monitoring using a huge database.

METHOD

The EEG signals from 35 channels were used to train the deep learning-based transformer model named (EpilepsyNet). For each training iteration, 1-min-long data were randomly sampled from each participant. Thereafter, each 5-s epoch was mapped to a matrix using the Pearson Correlation Coefficient (PCC), such that the bottom part of the triangle was discarded and only the upper triangle of the matrix was vectorized as input data. PCC is a reliable method used to measure the statistical relationship between two variables. Based on the 5 s of data, single embedding was performed thereafter to generate a 1-dimensional array of signals. In the final stage, a positional encoding with learnable parameters was added to each correlation coefficient's embedding before being fed to the developed EpilepsyNet as input data to epilepsy EEG signals. The ten-fold cross-validation technique was used to generate the model.

RESULTS

Our transformer-based model (EpilepsyNet) yielded high classification accuracy, sensitivity, specificity and positive predictive values of 85%, 82%, 87%, and 82%, respectively.

CONCLUSION

The proposed method is both accurate and robust since ten-fold cross-validation was employed to evaluate the performance of the model. Compared to the deep models used in existing studies for epilepsy diagnosis, our proposed method is simple and less computationally intensive. This is the earliest study to have uniquely employed the positional encoding with learnable parameters to each correlation coefficient's embedding together with the deep transformer model, using a huge database of 121 participants for epilepsy detection. With the training and validation of the model using a larger dataset, the same study approach can be extended for the detection of other neurological conditions, with a transformative impact on neurological diagnostics worldwide.

Forecasting seizure likelihood from cycles of self-reported events and heart rate: a prospective pilot study

BACKGROUND

Seizure risk forecasting could reduce injuries and even deaths in people with epilepsy. There is great interest in using non-invasive wearable devices to generate forecasts of seizure risk. Forecasts based on cycles of epileptic activity, seizure times or heart rate have provided promising forecasting results. This study validates a forecasting method using multimodal cycles recorded from wearable devices.

METHOD

Seizure and heart rate cycles were extracted from 13 participants. The mean period of heart rate data from a smartwatch was 562 days, with a mean of 125 self-reported seizures from a smartphone app. The relationship between seizure onset time and phases of seizure and heart rate cycles was investigated. An additive regression model was used to project heart rate cycles. The results of forecasts using seizure cycles, heart rate cycles, and a combination of both were compared. Forecasting performance was evaluated in 6 of 13 participants in a prospective setting, using long-term data collected after algorithms were developed.

FINDINGS

The results showed that the best forecasts achieved a mean area under the receiver-operating characteristic curve (AUC) of 0.73 for 9/13 participants showing performance above chance during retrospective validation. Subject-specific forecasts evaluated with prospective data showed a mean AUC of 0.77 with 4/6 participants showing performance above chance.

INTERPRETATION

The results of this study demonstrate that cycles detected from multimodal data can be combined within a single, scalable seizure risk forecasting algorithm to provide robust performance. The presented forecasting method enabled seizure risk to be estimated for an arbitrary future period and could be generalised across a range of data types. In contrast to earlier work, the current study evaluated forecasts prospectively, in subjects blinded to their seizure risk outputs, representing a critical step towards clinical applications.

FUNDING

This study was funded by an Australian Government National Health & Medical Research Council and BioMedTech Horizons grant. The study also received support from the Epilepsy Foundation of America's 'My Seizure Gauge' grant.

Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

BACKGROUND

Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity.

OBJECTIVE

This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers.

METHODS

This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed.

RESULTS

This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials.

CONCLUSION

mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.

Systemic inflammation as a biomarker of seizure propensity and a target for treatment to reduce seizure propensity

People with diabetes can wear a device that measures blood glucose and delivers just the amount of insulin needed to return the glucose level to within bounds. Currently, people with epilepsy do not have access to an equivalent wearable device that measures a systemic indicator of an impending seizure and delivers a rapidly acting medication or other intervention (e.g., an electrical stimulus) to terminate or prevent a seizure. Given that seizure susceptibility is reliably increased in systemic inflammatory states, we propose a novel closed-loop device where release of a fast-acting therapy is governed by sensors that quantify the magnitude of systemic inflammation. Here, we review the evidence that patients with epilepsy have raised levels of systemic indicators of inflammation than controls, and that some anti-inflammatory drugs have reduced seizure occurrence in animals and humans. We then consider the options of what might be incorporated into a responsive anti-seizure system.

Epileptic Prodromes: Insights from Surveying 196 Patients and 150 Caregivers

OBJECTIVE

Uncontrolled epilepsy creates a constant source of worry for patients and puts them at a high risk of injury. Identifying recurrent "premonitory" symptoms of seizures and using them to recalibrate seizure prediction algorithms may improve prediction performances. This study aimed to investigate patients' ability to predict oncoming seizures based on preictal symptoms.

METHODS

Through an online survey, demographics and clinical characteristics (e.g., seizure frequency, epilepsy duration, and postictal symptom duration) were collected from people with epilepsy and caregivers across Canada. Respondents were asked to answer questions regarding their ability to predict seizures through warning symptoms. A total of 196 patients and 150 caregivers were included and were separated into three groups: those who reported warning symptoms within the 5 minutes preceding a seizure, prodromes (symptoms earlier than 5 minutes before seizure), and no warning symptoms.

RESULTS

Overall, 12.2% of patients and 12.0% of caregivers reported predictive prodromes ranging from 5 minutes to more than 24 hours before the seizures (median of 2 hours). The most common were dizziness/vertigo (28%), mood changes (26%), and cognitive changes (21%). Statistical testing showed that respondents who reported prodromes also reported significantly longer postictal recovery periods compared to those who did not report predictive prodromes (P < 0.05).

CONCLUSION

Findings suggest that patients who present predictive seizure prodromes may be characterized by longer patient-reported postictal recovery periods. Studying the correlation between seizure severity and predictability and investigating the electrical activity underlying prodromes may improve our understanding of preictal mechanisms and ability to predict seizures.

Longitudinally tracking personal physiomes for precision management of childhood epilepsy

Our current understanding of human physiology and activities is largely derived from sparse and discrete individual clinical measurements. To achieve precise, proactive, and effective health management of an individual, longitudinal, and dense tracking of personal physiomes and activities is required, which is only feasible by utilizing wearable biosensors. As a pilot study, we implemented a cloud computing infrastructure to integrate wearable sensors, mobile computing, digital signal processing, and machine learning to improve early detection of seizure onsets in children. We recruited 99 children diagnosed with epilepsy and longitudinally tracked them at single-second resolution using a wearable wristband, and prospectively acquired more than one billion data points. This unique dataset offered us an opportunity to quantify physiological dynamics (e.g., heart rate, stress response) across age groups and to identify physiological irregularities upon epilepsy onset. The high-dimensional personal physiome and activity profiles displayed a clustering pattern anchored by patient age groups. These signatory patterns included strong age and sex-specific effects on varying circadian rhythms and stress responses across major childhood developmental stages. For each patient, we further compared the physiological and activity profiles associated with seizure onsets with the personal baseline and developed a machine learning framework to accurately capture these onset moments. The performance of this framework was further replicated in another independent patient cohort. We next referenced our predictions with the electroencephalogram (EEG) signals on selected patients and demonstrated that our approach could detect subtle seizures not recognized by humans and could detect seizures prior to clinical onset. Our work demonstrated the feasibility of a real-time mobile infrastructure in a clinical setting, which has the potential to be valuable in caring for epileptic patients. Extension of such a system has the potential to be leveraged as a health management device or longitudinal phenotyping tool in clinical cohort studies.

Seizure count forecasting to aid diagnostic testing in epilepsy

OBJECTIVE

Epilepsy monitoring unit (EMU) admissions are critical for presurgical evaluation of drug-resistant epilepsy but may be nondiagnostic if an insufficient number of seizures are recorded. Seizure forecasting algorithms have shown promise for estimating the likelihood of seizures as a binary event in individual patients, but methods to predict how many seizures will occur remain elusive. Such methods could increase the diagnostic yield of EMU admissions and help patients mitigate seizure-related morbidity. Here, we evaluated the performance of a state-space method that uses prior seizure count data to predict future counts.

METHODS

A Bayesian negative-binomial dynamic linear model (DLM) was developed to forecast daily electrographic seizure counts in 19 patients implanted with a responsive neurostimulation (RNS) device. Holdout validation was used to evaluate performance in predicting the number of electrographic seizures for forecast horizons ranging 1-7 days ahead.

RESULTS

One-day-ahead prediction of the number of electrographic seizures using a negative-binomial DLM resulted in improvement over chance in 73.1% of time segments compared to a random chance forecaster and remained >50% for forecast horizons of up to 7 days. Superior performance (mean error = .99) was obtained in predicting the number of electrographic seizures in the next day compared to three traditional methods for count forecasting (integer-valued generalized autoregressive conditional heteroskedasticity model or INGARCH, 1.10; Croston, 1.06; generalized linear autoregressive moving average model or GLARMA, 2.00). Number of electrographic seizures in the preceding day and laterality of electrographic pattern detections had highest predictive value, with greater number of electrographic seizures and RNS magnet swipes in the preceding day associated with a higher number of electrographic seizures the next day.

SIGNIFICANCE

This study demonstrates that DLMs can predict the number of electrographic seizures a patient will experience days in advance with above chance accuracy. This study represents an important step toward the translation of seizure forecasting methods into the optimization of EMU admissions.

Ambulantes Langzeit-Video-EEG als neuer diagnostischer Ansatz in Deutschland: Ergebnisse einer Machbarkeitsstudie

Das Langzeit-Video-EEG als Goldstandarddiagnostik bei Epilepsie und anderen Anfallsleiden ist in Deutschland derzeit nur in wenigen spezialisierten Zentren zur stationären Überwachung verfügbar. Diese begrenzten Überwachungskapazitäten und der damit verbundene hohe Zeit- und Arbeitsaufwand führen bundesweit zu einer erheblichen Wartezeit für diese wichtige Diagnostik. Neue, tragbare Sensortechnologien und automatisierte Datenanalysemethoden schaffen Möglichkeiten für Video-EEG-Langzeituntersuchungen nach dem Goldstandard im ambulanten Bereich, die dazu beitragen können, diese Barriere zu überwinden. Hier berichten wir über die Ergebnisse einer Machbarkeitsstudie an einem Zentrum, in der das ambulante Langzeit-Video-EEG (ALVEEG) als diagnostischer Weg in Deutschland eingeführt wurde. In dem neuen Diagnostikpfad soll der Einsatz innovativer, tragbarer Video-EEG-Monitoringsysteme zusammen mit einer durch künstliche Intelligenz unterstützten Datenanalyse den von Anfallsleiden betroffenen Patienten einen schnelleren, effizienteren und sektorübergreifenden Zugang zu einer Goldstandarddiagnostik in der häuslichen Umgebung ermöglichen. Die Diagnostik wurde von Patienten und Klinikern gut angenommen und könnte eine ergänzende Option zur stationären Überwachung darstellen, um die derzeitigen Engpässe in Diagnostik und Versorgung zu beseitigen.

Utilizing Data from Wearable Technologies in the Era of Telemedicine to Assess Patient Function and Outcomes in Neurosurgery: Systematic Review and Time-Trend Analysis of the Literature

BACKGROUND

The COVID-19 pandemic has driven the increased use of telemedicine and the adoption of wearable technology in neurosurgery. We reviewed studies exploring the use of wearables on neurosurgical patients and analyzed wearables' scientific production trends.

METHODS

The review encompassed PubMed, EMBASE, Web of Science, and Cochrane Library. Bibliometric analysis was performed using citation data of the included studies through Elsevier's Scopus database. Linear regression was utilized to understand scientific production trends. All analyses were performed on R 4.1.2.

RESULTS

We identified 979 studies. After screening, 49 studies were included. Most studies evaluated wearable technology use for patients with spinal pathology (n = 31). The studies were published over a 24-year period (1998-2021). Forty-seven studies involved wearable device use relevant to telemedicine. Bibliometric analysis revealed a compounded annual growth rate of 7.3%, adjusted for inflation, in annual scientific production from 1998 to 2021 (coefficient=1.3; 95% Confidence Interval = [0.7, 1.9], P < 0.01). Scientific production steadily increased in 2014 (n = 1) and peaked from 2019 (n = 8) to 2021 (n = 13) in correlation with the COVID-19 pandemic. Publications spanned 34 journals, averaged 24.4 citations per article, 3.0 citations per year per article, and 8.3 authors per article.

CONCLUSION

Wearables can provide clinicians with objective measurements to determine patient function and quality of life. The rise in articles related to wearables in neurosurgery demonstrates the increased adoption of wearable devices during the COVID-19 pandemic. Wearable devices appear to be a key component in this era of telemedicine and their positive utility and practicality are increasingly being realized in neurosurgery.

Seizure-related differences in biosignal 24-h modulation patterns

A seizure likelihood biomarker could improve seizure monitoring and facilitate adjustment of treatments based on seizure risk. Here, we tested differences in patient-specific 24-h-modulation patterns of electrodermal activity (EDA), peripheral body temperature (TEMP), and heart rate (HR) between patients with and without seizures. We enrolled patients who underwent continuous video-EEG monitoring at Boston Children's Hospital to wear a biosensor. We divided patients into two groups: those with no seizures and those with at least one seizure during the recording period. We assessed the 24-h modulation level and amplitude of EDA, TEMP, and HR. We performed machine learning including physiological and clinical variables. Subsequently, we determined classifier performance by cross-validated machine learning. Patients with seizures (n = 49) had lower EDA levels (p = 0.031), EDA amplitudes (p = 0.045), and trended toward lower HR levels (p = 0.060) compared to patients without seizures (n = 68). Averaged cross-validated classification accuracy was 69% (AUC-ROC: 0.75). Our results show the potential to monitor and forecast risk for epileptic seizures based on changes in 24-h patterns in wearable recordings in combination with clinical variables. Such biomarkers might be applicable to inform care, such as treatment or seizure injury risk during specific periods, scheduling diagnostic tests, such as admission to the epilepsy monitoring unit, and potentially other neurological and chronic conditions.

Sub-scalp electroencephalography: A next-generation technique to study human neurophysiology

Sub-scalp electroencephalography (ssEEG) is emerging as a promising technology in ultra-long-term electroencephalography (EEG) recordings. Given the diversity of devices available in this nascent field, uncertainty persists about its utility in epilepsy evaluation. This review critically dissects the many proposed utilities of ssEEG devices including (1) seizure quantification, (2) seizure characterization, (3) seizure lateralization, (4) seizure localization, (5) seizure alarms, (6) seizure forecasting, (7) biomarker discovery, (8) sleep medicine, and (9) responsive stimulation. The different ssEEG devices in development have individual design philosophies with unique strengths and limitations. There are devices offering primarily unilateral recordings (24/7 EEG^TM SubQ, Neuroview^TM, Soenia® UltimateEEG™), bilateral recordings (Minder™, Epios™), and even those with responsive stimulation capability (EASEE®). We synthesize the current knowledge of these ssEEG systems. We review the (1) ssEEG devices, (2) use case scenarios, (3) challenges and (4) suggest a roadmap for ideal ssEEG designs.

Future Opportunities for Research in Rescue Treatments

Clinical studies of rescue medications for seizure clusters are limited and are designed to satisfy regulatory requirements, which may not fully consider the needs of the diverse patient population that experiences seizure clusters or utilize rescue medication. The purpose of this narrative review is to examine the factors that contribute to, or may influence the quality of, seizure cluster research with a goal of improving clinical practice. We address five areas of unmet needs and provide advice for how they could enhance future trials of seizure cluster treatments. The topics addressed in this article are: (1) unaddressed end points to pursue in future studies, (2) roles for devices to enhance rescue medication clinical development programs, (3) tools to study seizure cluster prediction and prevention, (4) the value of other designs for seizure cluster studies, and (5) unique challenges of future trial paradigms for seizure clusters. By focusing on novel end points and technologies with value to patients, caregivers, and clinicians, data obtained from future studies can benefit the diverse patient population that experiences seizure clusters, providing more effective, appropriate care as well as alleviating demands on health care resources.

Seizures detection using multimodal signals: a scoping review

INTRODUCTION

Epileptic seizures are common neurological disorders in the world, impacting 50 million people globally. Around 30% of patients with seizures suffer from refractory epilepsy, where seizures are not controlled by medications. The unpredictability of seizures makes it essential to have a continuous seizure monitoring system outside clinical settings for the purpose of minimizing patients' injuries and providing additional pathways for evaluation and treatment follow-up. Autonomic changes related to seizure events have been extensively studied and attempts made to apply them for seizure detection and prediction tasks. This scoping review aims to depict current research activities associated with the implementation of portable, wearable devices for seizure detection or prediction and inform future direction in continuous seizure tracking in ambulatory settings.

METHODS

Overall methodology framework includes 5 essential stages: research questions identification, relevant studies identification, selection of studies, data charting and summarizing the findings. A systematic searching strategy guided by systematic reviews and meta-analysis (PRISMA) was implemented to identify relevant records on two databases (PubMed, IEEE).

RESULTS

A total of 30 articles were included in our final analysis. Most of the studies were conducted off-line and employed consumer-graded wearable device. ACM is the dominant modality to be used in seizure detection, and widely deployed algorithms entail Support Vector Machine, Random Forest and threshold-based approach. The sensitivity ranged from 33.2% to 100% for single modality with a false alarm rate (FAR) ranging from 0.096 /day to 14.8 /day. Multimodality has a sensitivity ranging from 51% to 100% with FAR ranging from 0.12/day - 17.7/day.

CONCLUSION

The overall performance in seizure detection system based on non-cerebral physiological signals is promising, especially for the detection of motor seizures and seizures accompanied with intense ictal autonomic changes.

Machine Learning for Healthcare Wearable Devices: The Big Picture

Using artificial intelligence and machine learning techniques in healthcare applications has been actively researched over the last few years. It holds promising opportunities as it is used to track human activities and vital signs using wearable devices and assist in diseases' diagnosis, and it can play a great role in elderly care and patient's health monitoring and diagnostics. With the great technological advances in medical sensors and miniaturization of electronic chips in the recent five years, more applications are being researched and developed for wearable devices. Despite the remarkable growth of using smart watches and other wearable devices, a few of these massive research efforts for machine learning applications have found their way to market. In this study, a review of the different areas of the recent machine learning research for healthcare wearable devices is presented. Different challenges facing machine learning applications on wearable devices are discussed. Potential solutions from the literature are presented, and areas open for improvement and further research are highlighted.

Wearable device assessments of antiseizure medication effects on diurnal patterns of electrodermal activity, heart rate, and heart rate variability

Patient-generated health data provide a great opportunity for more detailed ambulatory monitoring and more personalized treatments in many diseases. In epilepsy, robust diagnostics applicable to the ambulatory setting are needed as diagnosis and treatment decisions in current clinical practice are primarily reliant on patient self-reports, which are often inaccurate. Recent work using wearable devices has focused on methods to detect and forecast epileptic seizures. Whether wearable device signals may also contain information about the effect of antiseizure medications (ASMs), which may ultimately help to better monitor their efficacy, has not been evaluated yet. Here we systematically investigated the effect of ASMs on different data modalities (electrodermal activity, EDA, heart rate, HR, and heart rate variability, HRV) simultaneously recorded by a wearable device in 48 patients with epilepsy over several days in the epilepsy long-term monitoring unit at a tertiary hospital. All signals exhibited characteristic diurnal variations. HRV, but not HR or EDA-based metrics, were reduced by ASMs. By assessing multiple signals related to the autonomic nervous system simultaneously, our results provide novel insights into the effects of ASMs on the sympathetic and parasympathetic interplay in the setting of epilepsy and indicate the potential of easy-to-wear wearable devices for monitoring ASM action. Future work using longer data may investigate these metrics on multidien cycles and their utility for detecting seizures, assessing seizure risk, or informing treatment interventions.

Measurement-Based and Data-Informed Psychological Therapy

Outcome measurement in the field of psychotherapy has developed considerably in the last decade. This review discusses key issues related to outcome measurement, modeling, and implementation of data-informed and measurement-based psychological therapy. First, an overview is provided, covering the rationale of outcome measurement by acknowledging some of the limitations of clinical judgment. Second, different models of outcome measurement are discussed, including pre-post, session-by-session, and higher-resolution intensive outcome assessments. Third, important concepts related to modeling patterns of change are addressed, including early response, dose-response, and nonlinear change. Furthermore, rational and empirical decision tools are discussed as the foundation for measurement-based therapy. Fourth, examples of clinical applications are presented, which show great promise to support the personalization of therapy and to prevent treatment failure. Finally, we build on continuous outcome measurement as the basis for a broader understanding of clinical concepts and data-driven clinical practice in the future. Expected final online publication date for the Annual Review of Clinical Psychology, Volume 18 is May 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Power efficient refined seizure prediction algorithm based on an enhanced benchmarking

Deep learning techniques have led to significant advancements in seizure prediction research. However, corresponding used benchmarks are not uniform in published results. Moreover, inappropriate training and evaluation processes used in various work create overfitted models, making prediction performance fluctuate or unreliable. In this study, we analyzed the various data preparation methods, dataset partition methods in related works, and explained the corresponding impacts to the prediction algorithms. Then we applied a robust processing procedure that considers the appropriate sampling parameters and the leave-one-out cross-validation method to avoid possible overfitting and provide prerequisites for ease benchmarking. Moreover, a deep learning architecture takes advantage of a one-dimension convolutional neural network and a bi-directional long short-term memory network is proposed for seizure prediction. The architecture achieves 77.6% accuracy, 82.7% sensitivity, and 72.4% specificity, and it outperforms the indicators of other prior-art works. The proposed model is also hardware friendly; it has 6.274 k parameters and requires only 12.825 M floating-point operations, which is advantageous for memory and power constrained device implementations.

Ambulatory seizure forecasting with a wrist-worn device using long-short term memory deep learning

The ability to forecast seizures minutes to hours in advance of an event has been verified using invasive EEG devices, but has not been previously demonstrated using noninvasive wearable devices over long durations in an ambulatory setting. In this study we developed a seizure forecasting system with a long short-term memory (LSTM) recurrent neural network (RNN) algorithm, using a noninvasive wrist-worn research-grade physiological sensor device, and tested the system in patients with epilepsy in the field, with concurrent invasive EEG confirmation of seizures via an implanted recording device. The system achieved forecasting performance significantly better than a random predictor for 5 of 6 patients studied, with mean AUC-ROC of 0.80 (range 0.72–0.92). These results provide the first clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many patients with epilepsy.

The Challenging Path to Developing a Mobile Health Device for Epilepsy: The Current Landscape and Where We Go From Here

Seizure detection, and more recently seizure forecasting, represent important avenues of clinical development in epilepsy, promoted by progress in wearable devices and mobile health (mHealth), which might help optimizing seizure control and prevention of seizure-related mortality and morbidity in persons with epilepsy. Yet, very long-term continuous monitoring of seizure-sensitive biosignals in the ambulatory setting presents a number of challenges. We herein provide an overview of these challenges and current technological landscape of mHealth devices for seizure detection. Specifically, we display, which types of sensor modalities and analytical methods are available, and give insight into current clinical practice guidelines, main outcomes of clinical validation studies, and discuss how to evaluate device performance at point-of-care facilities. We then address pitfalls which may arise in patient compliance and the need to design solutions adapted to user experience.

Multiday cycles of heart rate are associated with seizure likelihood: An observational cohort study

Background

Circadian and multiday rhythms are found across many biological systems, including cardiology, endocrinology, neurology, and immunology. In people with epilepsy, epileptic brain activity and seizure occurrence have been found to follow circadian, weekly, and monthly rhythms. Understanding the relationship between these cycles of brain excitability and other physiological systems can provide new insight into the causes of multiday cycles. The brain-heart link has previously been considered in epilepsy research, with potential implications for seizure forecasting, therapy, and mortality (i.e., sudden unexpected death in epilepsy).

Methods

We report the results from a non-interventional, observational cohort study, Tracking Seizure Cycles. This study sought to examine multiday cycles of heart rate and seizures in adults with diagnosed uncontrolled epilepsy (N=31) and healthy adult controls (N=15) using wearable smartwatches and mobile seizure diaries over at least four months (M=12.0, SD=5.9; control M=10.6, SD=6.4). Cycles in heart rate were detected using a continuous wavelet transform. Relationships between heart rate cycles and seizure occurrence were measured from the distributions of seizure likelihood with respect to underlying cycle phase.

Findings

Heart rate cycles were found in all 46 participants (people with epilepsy and healthy controls), with circadian (N=46), about-weekly (N=25) and about-monthly (N=13) rhythms being the most prevalent. Of the participants with epilepsy, 19 people had at least 20 reported seizures, and 10 of these had seizures significantly phase locked to their multiday heart rate cycles.

Interpretation

Heart rate cycles showed similarities to multiday epileptic rhythms and may be comodulated with seizure likelihood. The relationship between heart rate and seizures is relevant for epilepsy therapy, including seizure forecasting, and may also have implications for cardiovascular disease. More broadly, understanding the link between multiday cycles in the heart and brain can shed new light on endogenous physiological rhythms in humans.

Funding

This research received funding from the Australian Government National Health and Medical Research Council (investigator grant 1178220), the Australian Government BioMedTech Horizons program, and the Epilepsy Foundation of America's ‘My Seizure Gauge’ grant.

Seizure Forecasting: Patient and Caregiver Perspectives

Accurate seizure forecasting is emerging as a near-term possibility due to recent advancements in machine learning and EEG technology improvements. Large-scale data curation and new data element collection through consumer wearables and digital health tools such as longitudinal seizure diary data has uncovered new possibilities for personalized algorithm development that may be used to predict the likelihood of future seizures. The Epilepsy Foundation recognized the unmet need for development in seizure forecasting following a 2016 survey where an overwhelming majority of respondents across all seizure types and frequencies reported that unpredictability of seizures had the strongest impact on their life while living with or caring for someone living with epilepsy. In early 2021, the Epilepsy Foundation conducted an updated survey among those living with epilepsies and/or their caregivers to better understand the use-cases that best suit the needs of our community as seizure forecast research advances. These results will provide researchers with insight into user-acceptance of using a forecasting tool and incorporation into their daily life. Ultimately, this input from people living with epilepsy and caregivers will provide timely feedback on what the community needs are and ensure researchers and companies first and foremost consider these needs in seizure forecasting tools/product development.

Seizure Forecasting Using a Novel Sub-Scalp Ultra-Long Term EEG Monitoring System

Accurate identification of seizure activity, both clinical and subclinical, has important implications in the management of epilepsy. Accurate recognition of seizure activity is essential for diagnostic, management and forecasting purposes, but patient-reported seizures have been shown to be unreliable. Earlier work has revealed accurate capture of electrographic seizures and forecasting is possible with an implantable intracranial device, but less invasive electroencephalography (EEG) recording systems would be optimal. Here, we present preliminary results of seizure detection and forecasting with a minimally invasive sub-scalp device that continuously records EEG. Five participants with refractory epilepsy who experience at least two clinically identifiable seizures monthly have been implanted with sub-scalp devices (Minder®), providing two channels of data from both hemispheres of the brain. Data is continuously captured via a behind-the-ear system, which also powers the device, and transferred wirelessly to a mobile phone, from where it is accessible remotely via cloud storage. EEG recordings from the sub-scalp device were compared to data recorded from a conventional system during a 1-week ambulatory video-EEG monitoring session. Suspect epileptiform activity (EA) was detected using machine learning algorithms and reviewed by trained neurophysiologists. Seizure forecasting was demonstrated retrospectively by utilizing cycles in EA and previous seizure times. The procedures and devices were well-tolerated and no significant complications have been reported. Seizures were accurately identified on the sub-scalp system, as visually confirmed by periods of concurrent conventional scalp EEG recordings. The data acquired also allowed seizure forecasting to be successfully undertaken. The area under the receiver operating characteristic curve (AUC score) achieved (0.88), which is comparable to the best score in recent, state-of-the-art forecasting work using intracranial EEG.

Video-Based Detection of Generalized Tonic-Clonic Seizures Using Deep Learning

Timely detection of seizures is crucial to implement optimal interventions, and may help reduce the risk of sudden unexpected death in epilepsy (SUDEP) in patients with generalized tonic-clonic seizures (GTCSs). While video-based automated seizure detection systems may be able to provide seizure alarms in both in-hospital and at-home settings, earlier studies have primarily employed hand-designed features for such a task. In contrast, deep learning-based approaches do not rely on prior feature selection and have demonstrated outstanding performance in many data classification tasks. Despite these advantages, neural network-based video classification has rarely been attempted for seizure detection. We here assessed the feasibility and efficacy of automated GTCSs detection from videos using deep learning. We retrospectively identified 76 GTCS videos from 37 participants who underwent long-term video-EEG monitoring (LTM) along with interictal video data from the same patients, and 10 full-night seizure-free recordings from additional patients. Using a leave-one-subject-out cross-validation approach (LOSO-CV), we evaluated the performance to detect seizures based on individual video frames (convolutional neural networks, CNNs) or video sequences [CNN+long short-term memory (LSTM) networks]. CNN+LSTM networks based on video sequences outperformed GTCS detection based on individual frames yielding a mean sensitivity of 88% and mean specificity of 92% across patients. The average detection latency after presumed clinical seizure onset was 22 seconds. Detection performance increased as a function of training dataset size. Collectively, we demonstrated that automated video-based GTCS detection with deep learning is feasible and efficacious. Deep learning-based methods may be able to overcome some limitations associated with traditional approaches using hand-crafted features, serve as a benchmark for future methods and analyses, and improve further with larger datasets.

Forecasting Seizure Likelihood With Wearable Technology

The unpredictability of epileptic seizures exposes people with epilepsy to potential physical harm, restricts day-to-day activities, and impacts mental well-being. Accurate seizure forecasters would reduce the uncertainty associated with seizures but need to be feasible and accessible in the long-term. Wearable devices are perfect candidates to develop non-invasive, accessible forecasts but are yet to be investigated in long-term studies. We hypothesized that machine learning models could utilize heart rate as a biomarker for well-established cycles of seizures and epileptic activity, in addition to other wearable signals, to forecast high and low risk seizure periods. This feasibility study tracked participants' (n = 11) heart rates, sleep, and step counts using wearable smartwatches and seizure occurrence using smartphone seizure diaries for at least 6 months (mean = 14.6 months, SD = 3.8 months). Eligible participants had a diagnosis of refractory epilepsy and reported at least 20 seizures (mean = 135, SD = 123) during the recording period. An ensembled machine learning and neural network model estimated seizure risk either daily or hourly, with retraining occurring on a weekly basis as additional data was collected. Performance was evaluated retrospectively against a rate-matched random forecast using the area under the receiver operating curve. A pseudo-prospective evaluation was also conducted on a held-out dataset. Of the 11 participants, seizures were predicted above chance in all (100%) participants using an hourly forecast and in ten (91%) participants using a daily forecast. The average time spent in high risk (prediction time) before a seizure occurred was 37 min in the hourly forecast and 3 days in the daily forecast. Cyclic features added the most predictive value to the forecasts, particularly circadian and multiday heart rate cycles. Wearable devices can be used to produce patient-specific seizure forecasts, particularly when biomarkers of seizure and epileptic activity cycles are utilized.

The Contribution of Machine Learning in the Validation of Commercial Wearable Sensors for Gait Monitoring in Patients: A Systematic Review

Gait, balance, and coordination are important in the development of chronic disease, but the ability to accurately assess these in the daily lives of patients may be limited by traditional biased assessment tools. Wearable sensors offer the possibility of minimizing the main limitations of traditional assessment tools by generating quantitative data on a regular basis, which can greatly improve the home monitoring of patients. However, these commercial sensors must be validated in this context with rigorous validation methods. This scoping review summarizes the state-of-the-art between 2010 and 2020 in terms of the use of commercial wearable devices for gait monitoring in patients. For this specific period, 10 databases were searched and 564 records were retrieved from the associated search. This scoping review included 70 studies investigating one or more wearable sensors used to automatically track patient gait in the field. The majority of studies (95%) utilized accelerometers either by itself (N = 17 of 70) or embedded into a device (N = 57 of 70) and/or gyroscopes (51%) to automatically monitor gait via wearable sensors. All of the studies (N = 70) used one or more validation methods in which “ground truth” data were reported. Regarding the validation of wearable sensors, studies using machine learning have become more numerous since 2010, at 17% of included studies. This scoping review highlights the current state of the ability of commercial sensors to enhance traditional methods of gait assessment by passively monitoring gait in daily life, over long periods of time, and with minimal user interaction. Considering our review of the last 10 years in this field, machine learning approaches are algorithms to be considered for the future. These are in fact data-based approaches which, as long as the data collected are numerous, annotated, and representative, allow for the training of an effective model. In this context, commercial wearable sensors allowing for increased data collection and good patient adherence through efforts of miniaturization, energy consumption, and comfort will contribute to its future success.

[Use of machine learning for the prediction of stress using the example of logistics]

Stress und seine komplexen Wirkungen werden bereits seit Anfang des 20. Jahrhunderts erforscht. Die vielfältigen psychischen und physischen Stressoren in der Arbeitswelt können in Summe zu Störungen des Organismus und zu Erkrankungen führen. Da die Ausprägung körperlicher und subjektiver Folgen von Stress individuell unterschiedlich ist, lassen sich keine absoluten Grenzwerte ermitteln. Zur Erforschung der systematischen Mustererkennung physiologischer und subjektiver Stressparameter sowie einer Stressvorhersage, werden in dem vorliegenden Beitrag Methoden des maschinellen Lernens (ML) eingesetzt. Als praktischer Anwendungsfall dient die Logistikbranche, in der Belastungsfaktoren häufig in der Tätigkeit und der Arbeitsorganisation begründet liegen. Ein Gestaltungselement bei der Prävention von Stress ist die Arbeitspause. Mit ML-Methoden wird untersucht, inwieweit Stress auf Basis physiologischer und subjektiver Parameter vorhergesagt werden kann, um Pausen individuell zu empfehlen. Im Beitrag wird der Zwischenstand einer Softwarelösung für ein dynamisches Pausenmanagement für die Logistik vorgestellt.

Praktische Relevanz: Das Ziel der Softwarelösung „Dynamische Pause“ besteht darin, Stress in Folge mentaler und physischer Belastungsfaktoren in der Logistik präventiv vorzubeugen und die Beschäftigten auf lange Sicht gesund, zufrieden, arbeitsfähig und produktiv zu halten. Infolge individualisierter Erholungspausen als Gestaltungselement, können Unternehmen unterstützt werden, Personalressourcen entsprechend der dynamischen Anforderungen der Logistik flexibler einzusetzen.

Seizure Diaries and Forecasting With Wearables: Epilepsy Monitoring Outside the Clinic

It is a major challenge in clinical epilepsy to diagnose and treat a disease characterized by infrequent seizures based on patient or caregiver reports and limited duration clinical testing. The poor reliability of self-reported seizure diaries for many people with epilepsy is well-established, but these records remain necessary in clinical care and therapeutic studies. A number of wearable devices have emerged, which may be capable of detecting seizures, recording seizure data, and alerting caregivers. Developments in non-invasive wearable sensors to measure accelerometry, photoplethysmography (PPG), electrodermal activity (EDA), electromyography (EMG), and other signals outside of the traditional clinical environment may be able to identify seizure-related changes. Non-invasive scalp electroencephalography (EEG) and minimally invasive subscalp EEG may allow direct measurement of seizure activity. However, significant network and computational infrastructure is needed for continuous, secure transmission of data. The large volume of data acquired by these devices necessitates computer-assisted review and detection to reduce the burden on human reviewers. Furthermore, user acceptability of such devices must be a paramount consideration to ensure adherence with long-term device use. Such devices can identify tonic–clonic seizures, but identification of other seizure semiologies with non-EEG wearables is an ongoing challenge. Identification of electrographic seizures with subscalp EEG systems has recently been demonstrated over long (>6 month) durations, and this shows promise for accurate, objective seizure records. While the ability to detect and forecast seizures from ambulatory intracranial EEG is established, invasive devices may not be acceptable for many individuals with epilepsy. Recent studies show promising results for probabilistic forecasts of seizure risk from long-term wearable devices and electronic diaries of self-reported seizures. There may also be predictive value in individuals' symptoms, mood, and cognitive performance. However, seizure forecasting requires perpetual use of a device for monitoring, increasing the importance of the system's acceptability to users. Furthermore, long-term studies with concurrent EEG confirmation are lacking currently. This review describes the current evidence and challenges in the use of minimally and non-invasive devices for long-term epilepsy monitoring, the essential components in remote monitoring systems, and explores the feasibility to detect and forecast impending seizures via long-term use of these systems.

Epileptic heart: A clinical syndromic approach

Prevention of premature death in patients with chronic epilepsy remains a major challenge. Multiple pathophysiologic factors have been implicated, with intense investigation of cardiorespiratory mechanisms. Up to four in five patients with chronic epilepsy exhibit cardiovascular comorbidities. These findings led us to propose the concept of an "epileptic heart," defined as "a heart and coronary vasculature damaged by chronic epilepsy as a result of repeated surges in catecholamines and hypoxemia leading to electrical and mechanical dysfunction." Among the most prominent changes documented in the literature are high incidence of myocardial infarction and arrhythmia, altered autonomic tone, diastolic dysfunction, hyperlipidemia, and accelerated atherosclerosis. This suite of pathologic changes prompted us to propose for the first time in this review a syndromic approach for improved clinical detection of the epileptic heart condition. In this review, we discuss the key pathophysiologic mechanisms underlying the candidate criteria along with standard and novel techniques that permit evaluation of each of these factors. Specifically, we present evidence of the utility of standard 12-lead, ambulatory, and multiday patch-based electrocardiograms, along with measures of cardiac electrical instability, including T-wave alternans, heart rate variability to detect altered autonomic tone, echocardiography to detect diastolic dysfunction, and plasma biomarkers for assessing hyperlipidemia and accelerated atherosclerosis. Ultimately, the proposed clinical syndromic approach is intended to improve monitoring and evaluation of cardiac risk in patients with chronic epilepsy to foster improved therapeutic strategies to reduce premature cardiac death.

Epileptic Seizures Detection Using Deep Learning Techniques: A Review

A variety of screening approaches have been proposed to diagnose epileptic seizures, using electroencephalography (EEG) and magnetic resonance imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning (DL). Before the rise of DL, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in DL, the extraction of features and classification are entirely automated. The advent of these techniques in many areas of medicine, such as in the diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented. Various methods proposed to diagnose epileptic seizures automatically using EEG and MRI modalities are described. In addition, rehabilitation systems developed for epileptic seizures using DL have been analyzed, and a summary is provided. The rehabilitation tools include cloud computing techniques and hardware required for implementation of DL algorithms. The important challenges in accurate detection of automated epileptic seizures using DL with EEG and MRI modalities are discussed. The advantages and limitations in employing DL-based techniques for epileptic seizures diagnosis are presented. Finally, the most promising DL models proposed and possible future works on automated epileptic seizure detection are delineated.

Personalized EEG Feature Selection for Low-Complexity Seizure Monitoring

Approximately, one third of patients with epilepsy are refractory to medical therapy and thus can be at high risk of injuries and sudden unexpected death. A low-complexity electroencephalography (EEG)-based seizure monitoring algorithm is critically important for daily use, especially for wearable monitoring platforms. This paper presents a personalized EEG feature selection approach, which is the key to achieve a reliable seizure monitoring with a low computational cost. We advocate a two-step, personalized feature selection strategy to enhance monitoring performances for each patient. In the first step, linear discriminant analysis (LDA) is applied to find a few seizure-indicative channels. Then in the second step, least absolute shrinkage and selection operator (LASSO) method is employed to select a discriminative subset of both frequency and time domain features (spectral powers and entropy). A personalization strategy is further customized to find the best settings (number of channels and features) that yield the highest classification scores for each subject. Experimental results of analyzing 23 subjects in CHB-MIT database are quite promising. We have achieved an average F-1 score of 88% with excellent sensitivity and specificity using not more than 7 features extracted from at most 3 channels.