Machine learning to support triage of children at risk for epileptic seizures in the pediatric intensive care unit.

Objective.Epileptic seizures are relatively common in critically-ill children admitted to the pediatric intensive care unit (PICU) and thus serve as an important target for identification and treatment. Most of these seizures have no discernible clinical manifestation but still have a significant impact on morbidity and mortality. Children that are deemed at risk for seizures within the PICU are monitored using continuous-electroencephalogram (cEEG). cEEG monitoring cost is considerable and as the number of available machines is always limited, clinicians need to resort to triaging patients according to perceived risk in order to allocate resources. This research aims to develop a computer aided tool to improve seizures risk assessment in critically-ill children, using an ubiquitously recorded signal in the PICU, namely the electrocardiogram (ECG).Approach.A novel data-driven model was developed at a patient-level approach, based on features extracted from the first hour of ECG recording and the clinical data of the patient.Main results.The most predictive features were the age of the patient, the brain injury as coma etiology and the QRS area. For patients without any prior clinical data, using one hour of ECG recording, the classification performance of the random forest classifier reached an area under the receiver operating characteristic curve (AUROC) score of 0.84. When combining ECG features with the patients clinical history, the AUROC reached 0.87.Significance.Taking a real clinical scenario, we estimated that our clinical decision support triage tool can improve the positive predictive value by more than 59% over the clinical standard.

The power of ECG in multimodal patient-specific seizure monitoring: Added value to an EEG-based detector using limited channels.

OBJECTIVE: Wearable seizure detection devices could provide more reliable seizure documentation outside the hospital compared to seizure self-reporting by patients, which is the current standard. Previously, during the SeizeIT1 project, we studied seizure detection based on behind-the-ear electroencephalography (EEG). However, the obtained sensitivities were too low for practical use, because not all seizures are associated with typical ictal EEG patterns. Therefore, in this paper, we aim to develop a multimodal automated seizure detection algorithm integrating behind-the-ear EEG and electrocardiography (ECG) for detecting focal seizures. In this framework, we quantified the added value of ECG to behind-the-ear EEG. METHODS: This study analyzed three multicenter databases consisting of 135 patients having focal epilepsy and a total of 896 seizures. A patient-specific multimodal automated seizure detection algorithm was developed using behind-the-ear/temporal EEG and single-lead ECG. The EEG and ECG data were processed separately using machine learning methods. A late integration approach was applied for fusing those predictions. RESULTS: The multimodal algorithm outperformed the EEG-based algorithm in two of three databases, with an increase of 11% and 8% in sensitivity for the same false alarm rate. SIGNIFICANCE: ECG can be of added value to an EEG-based seizure detection algorithm using only behind-the-ear/temporal lobe electrodes for patients with focal epilepsy.

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.

Visual seizure annotation and automated seizure detection using behind-the-ear electroencephalographic channels.

OBJECTIVE: Seizure diaries kept by patients are unreliable. Automated electroencephalography (EEG)-based seizure detection systems are a useful support tool to objectively detect and register seizures during long-term video-EEG recording. However, this standard full scalp-EEG recording setup is of limited use outside the hospital, and a discreet, wearable device is needed for capturing seizures in the home setting. We are developing a wearable device that records EEG with behind-the-ear electrodes. In this study, we determined whether the recognition of ictal patterns using only behind-the-ear EEG channels is possible. Second, an automated seizure detection algorithm was developed using only those behind-the-ear EEG channels. METHODS: Fifty-four patients with a total of 182 seizures, mostly temporal lobe epilepsy (TLE), and 5284 hours of data, were recorded with a standard video-EEG at University Hospital Leuven. In addition, extra behind-the-ear EEG channels were recorded. First, a neurologist was asked to annotate behind-the-ear EEG segments containing selected seizure and nonseizure fragments. Second, a data-driven algorithm was developed using only behind-the-ear EEG. This algorithm was trained using data from other patients (patient-independent model) or from the same patient (patient-specific model). RESULTS: The visual recognition study resulted in 65.7% sensitivity and 94.4% specificity. By using those seizure annotations, the automated algorithm obtained 64.1% sensitivity and 2.8 false-positive detections (FPs)/24 hours with the patient-independent model. The patient-specific model achieved 69.1% sensitivity and 0.49 FPs/24 hours. SIGNIFICANCE: Visual recognition of ictal EEG patterns using only behind-the-ear EEG is possible in a significant number of patients with TLE. A patient-specific seizure detection algorithm using only behind-the-ear EEG was able to detect more seizures automatically than what patients typically report, with 0.49 FPs/24 hours. We conclude that a large number of refractory TLE patients can benefit from using this device.

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.

Adaptive nocturnal seizure detection using heart rate and low-complexity novelty detection.

PURPOSE: Automated seizure detection at home is mostly done using either patient-independent algorithms or manually personalized algorithms. Patient-independent algorithms, however, lead to too many false alarms, whereas the manually personalized algorithms typically require manual input from an experienced clinician for each patient, which is a costly and unscalable procedure and it can only be applied when the patient had a sufficient amount of seizures. We therefore propose a nocturnal heart rate based seizure detection algorithm that automatically adapts to the patient without requiring seizure labels. METHODS: The proposed method initially starts with a patient-independent algorithm. After a very short initialization period, the algorithm already adapts to the patients' characteristics by using a low-complex novelty detection classifier. The algorithm is evaluated on 28 pediatric patients with 107 convulsive and clinical subtle seizures during 695 h of nocturnal multicenter data in a retrospective study that mimics a real-time analysis. RESULTS: By using the adaptive seizure detection algorithm, the overall performance was 77.6% sensitivity with on average 2.56 false alarms per night. This is 57% less false alarms than a patient-independent algorithm with a similar sensitivity. Patients with tonic-clonic seizures showed a 96% sensitivity with on average 1.84 false alarms per night. CONCLUSION: The proposed method shows a strongly improved detection performance over patient-independent performance, without requiring manual adaptation by a clinician. Due to the low-complexity of the algorithm, it can be easily implemented on wearables as part of a (multimodal) seizure alarm system.

Adaptive heart rate-based epileptic seizure detection using real-time user feedback.

OBJECTIVE: Automated seizure detection in the home environment has attracted increasing interest in recent decades. Heart rate-based seizure detection is a way to detect temporal lobe epilepsy seizures at home, but patient-independent classifiers have been shown to be insufficiently accurate. This is due to the high patient-dependence of heart rate features, whereas this method does not use patient-specific data. Patient-specific classifiers take into account patient-specific data, but often not enough patient data are available for a fully robust patient-specific classifier. Therefore a real-time adaptive seizure detection algorithm is proposed here. APPROACH: The algorithm starts with a patient-independent classifier, but gradually adapts to the patient-specific characteristics while they are obtained 'on the go'. This is done by using real-time user feedback to annotate previously generated alarms, causing an immediate update to the used support vector machine classifier. Data annotated as seizures are automatically removed from the updating procedure if their detection would lead to too many false alarms. This is done in order to cope with potentially incorrect feedback. MAIN RESULTS: The adaptive classifier resulted in an overall sensitivity of 77.12% and 1.24 false alarms per hour when applied to over 2833 h of heart rate data from 19 patients with 153 clinical seizures. This is around 30% fewer false alarms compared to a patient-independent classifier with a similar sensitivity. SIGNIFICANCE: This low-complexity adaptive algorithm is able to deal well with incorrect feedback, making it ideal for a seizure warning system, and in the future it will also include complementary modalities to improve its performance.

Automated Epileptic Seizure Detection Based on Wearable ECG and PPG in a Hospital Environment.

Electrocardiography has added value to automatically detect seizures in temporal lobe epilepsy (TLE) patients. The wired hospital system is not suited for a long-term seizure detection system at home. To address this need, the performance of two wearable devices, based on electrocardiography (ECG) and photoplethysmography (PPG), are compared with hospital ECG using an existing seizure detection algorithm. This algorithm classifies the seizures on the basis of heart rate features, extracted from the heart rate increase. The algorithm was applied to recordings of 11 patients in a hospital setting with 701 h capturing 47 (fronto-)temporal lobe seizures. The sensitivities of the hospital system, the wearable ECG device and the wearable PPG device were respectively 57%, 70% and 32%, with corresponding false alarms per hour of 1.92, 2.11 and 1.80. Whereas seizure detection performance using the wrist-worn PPG device was considerably lower, the performance using the wearable ECG is proven to be similar to that of the hospital ECG.

Online Automated Seizure Detection in Temporal Lobe Epilepsy Patients Using Single-lead ECG.

Automated seizure detection in a home environment has been of increased interest the last couple of decades. The electrocardiogram is one of the signals that is suited for this application. In this paper, a new method is described that classifies different heart rate characteristics in order to detect seizures from temporal lobe epilepsy patients. The used support vector machine classifier is trained on data from other patients, so that the algorithm can be used directly from the start of each new recording. The algorithm was tested on a dataset of more than 918[Formula: see text]h of data coming from 17 patients containing 127 complex partial and generalized partial seizures. The algorithm was able to detect 81.89% of the seizures, with on average 1.97 false alarms per hour. These results show a strong drop in the number of false alarms of more than 50% compared to other heart rate-based patient-independent algorithms from the literature, at the expense of a slightly higher detection delay of 17.8s on average.

Heart beat detection in multimodal data using automatic relevant signal detection.

Accurate R peak detection in the electrocardiogram (ECG) is a well-known and highly explored problem in biomedical signal processing. Although a lot of progress has been made in this area, current methods are still insufficient in the presence of extreme noise and/or artifacts such as loose electrodes. Often, however, not only the ECG is recorded, but multiple signals are simultaneously acquired from the patient. Several of these signals, such as blood pressure, can help to improve the heart beat detection. These signals of interest can be detected automatically by analyzing their power spectral density or by using the available signal type identifiers. Individual peaks from the signals of interest are combined using majority voting, heart beat location estimation and Hjorth's mobility of the resulting RR intervals. Both multimodal algorithms showed significant increases in performance of up to 8.65% for noisy multimodal datasets compared to when only the ECG signal is used. A maximal performance of 90.02% was obtained on the hidden test set of the Physionet/Computing in Cardiology Challenge 2014: Robust Detection of Heart Beats in Multimodal Data.

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.