Discriminative and Generative Classification Techniques Applied to Automated Neonatal Seizure Detection

An EEG analysis framework through AI and sonification on low power IoT edge devices

This study explores the feasibility of implementation of an analysis framework of neonatal EEG, including ML, sonification and intuitive visualization, on a low power IoT edge device. Electroencephalography (EEG) analysis is a very important tool to detect brain disorders. Neonatal seizure detection is a known, challenging problem. Under-resourced communities across the globe are particularly affected by the cost associated with EEG analysis and interpretation. Machine learning (ML) techniques have been successfully utilized to automate seizure detection in neonatal EEG, in order to assist a healthcare professional in visual analysis. Several usage scenarios are reviewed in this study. It is shown that both sonification and ML can be efficiently implemented on low-power edge platforms without any loss of accuracy. The developed platform can be easily expanded to address EEG analysis applications in neonatal and adult population.

Machine learning based intelligent automated neonatal epileptic seizure detection

Epilepsy is found to be the fourth most common chronic neurological disorder that tends to abnormal and unpredictable brain activity and seizure states. According to statistics, 70% of the epilepsy patients can be cured if identified and treated with anti-epileptic drugs or shock stimulations. Only about 7% to 8% need to be operated. Electroencephalogram (EEG) is a cheap and effective way to record the prolonged activities of the brain through electrical impulses between neural cells. Seizure is difficult to detect in neonates as the signal involves a lot of disturbances and the existing high accuracy system for adults can’t be used for neonates. In an attempt to build an impregnable system to detect seizure in early stages, EEG signals of neonates procured from Neonatal Intensive Care Unit (NICU) at the Helsinki University Hospital. These signals were processed and fed into three different robust algorithms –Support Vector Machine (SVM), Artificial Neural Network (ANN) and 1-Dimensional Convolutional Neural Network (1D-CNN). The experimental results were compared and the proposed CNN model with 95.99% accuracy outperforms all the state-of-art models for automated Epileptic Seizure prediction in Neonates. Deep CNN has been a powerful tool in extracting robust features from EEG signals. This generalized system can be used by medical experts for detecting Seizure in neonates with better accuracy and reliability.

Seizure Detection Algorithms in Critically Ill Children: A Comparative Evaluation

OBJECTIVES

To evaluate the performance of commercially available seizure detection algorithms in critically ill children.

DESIGN

Diagnostic accuracy comparison between commercially available seizure detection algorithms referenced to electroencephalography experts using quantitative electroencephalography trends.

SETTING

Multispecialty quaternary children's hospital in Canada.

SUBJECTS

Critically ill children undergoing electroencephalography monitoring.

INTERVENTIONS

Continuous raw electroencephalography recordings (n = 19) were analyzed by a neurophysiologist to identify seizures. Those recordings were then converted to quantitative electroencephalography displays (amplitude-integrated electroencephalography and color density spectral array) and evaluated by six independent electroencephalography experts to determine the sensitivity and specificity of the amplitude-integrated electroencephalography and color density spectral array displays for seizure identification in comparison to expert interpretation of raw electroencephalography data. Those evaluations were then compared with four commercial seizure detection algorithms: ICTA-S (Stellate Harmonie Version 7; Natus Medical, San Carlos, CA), NB (Stellate Harmonie Version 7; Natus Medical), Persyst 11 (Persyst Development, Prescott, AZ), and Persyst 13 (Persyst Development) to determine sensitivity and specificity in comparison to amplitude-integrated electroencephalography and color density spectral array.

MEASUREMENTS AND MAIN RESULTS

Of the 379 seizures identified on raw electroencephalography, ICTA-S detected 36.9%, NB detected 92.3%, Persyst 11 detected 75.9%, and Persyst 13 detected 74.4%, whereas electroencephalography experts identified 76.5% of seizures using color density spectral array and 73.7% using amplitude-integrated electroencephalography. Daily false-positive rates averaged across all recordings were 4.7 with ICTA-S, 126.3 with NB, 5.1 with Persyst 11, 15.5 with Persyst 13, 1.7 with color density spectral array, and 1.5 with amplitude-integrated electroencephalography. Both Persyst 11 and Persyst 13 had sensitivity comparable to that of electroencephalography experts using amplitude-integrated electroencephalography and color density spectral array. Although Persyst 13 displayed the highest sensitivity for seizure count and seizure burden detected, Persyst 11 exhibited the best trade-off between sensitivity and false-positive rate among all seizure detection algorithms.

CONCLUSIONS

Some commercially available seizure detection algorithms demonstrate performance for seizure detection that is comparable to that of electroencephalography experts using quantitative electroencephalography displays. These algorithms may have utility as early warning systems that prompt review of quantitative electroencephalography or raw electroencephalography tracings, potentially leading to more timely seizure identification in critically ill patients.

Automatic Seizure Detection Based on Nonlinear Dynamical Analysis of EEG Signals and Mutual Information

Introduction:

In this paper, nonlinear dynamical analysis based on Recurrence Quantification Analysis (RQA) is employed to characterize the nonlinear EEG dynamics. RQA can provide useful quantitative information on the regular, chaotic, or stochastic property of the underlying dynamics.

Methods:

We use the RQA-based measures as the quantitative features of the nonlinear EEG dynamics. Mutual Information (MI) was used to find the most relevant feature subset out of RQA-based features. The selected features were fed into an artificial neural network for grouping of EEG recordings to detect ictal, interictal, and healthy states. The performance of the proposed procedure was evaluated using a database for different classification cases.

Results:

The combination of five selected features based on MI achieved 100% accuracy, which demonstrates the superiority of the proposed method.

Conclusion:

The results showed that the nonlinear dynamical analysis based on Rcurrence Quantification Analysis (RQA) can be employed as a suitable approach for characterizing the nonlinear EEG dynamics and detecting the seizure.

Investigating the Impact of CNN Depth on Neonatal Seizure Detection Performance

This study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep convolutional networks are compared with a shallow SVMbased neonatal seizure detector, which relies on the extraction of hand-crafted features. On a large clinical dataset, of over 800 hours of multichannel unedited EEG, containing 1389 seizure events, the deep 11-layer architecture significantly outperforms the shallower architectures, improving the AUC90 from 82.6% to 86.8%. Combining the end-to-end deep architecture with the feature-based shallow SVM further improves the AUC90 to 87.6%. The fusion of classifiers of different depths gives greatly improved performance and reduced variability, making the combined classifier more clinically reliable.

A Hybrid Approach Based on Higher Order Spectra for Clinical Recognition of Seizure and Epilepsy Using Brain Activity

Introduction

This paper proposes a reliable and efficient technique to recognize different epilepsy states, including healthy, interictal, and ictal states, using Electroencephalogram (EEG) signals.

Methods

The proposed approach consists of pre-processing, feature extraction by higher order spectra, feature normalization, feature selection by genetic algorithm and ranking method, and classification by support vector machine with Gaussian and polynomial radial basis function kernels. The proposed approach is validated on a public benchmark dataset to compare it with previous studies.

Results

The results indicate that the combined use of above elements can effectively decipher the cognitive process of epilepsy and seizure recognition. There are several bispectrum and bicoherence peaks at every bi-frequency plane, which reveal the location of the quadratic phase coupling. The proposed approach can reach, in almost all of the experiments, up to 100% performance in terms of sensitivity, specificity, and accuracy.

Conclusion

Comparing between the obtained results and previous approaches approves the effectiveness of the proposed approach for seizure and epilepsy recognition.

Toward a Personalized Real-Time Diagnosis in Neonatal Seizure Detection

The problem of creating a personalized seizure detection algorithm for newborns is tackled in this paper. A probabilistic framework for semi-supervised adaptation of a generic patient-independent neonatal seizure detector is proposed. A system that is based on a combination of patient-adaptive (generative) and patient-independent (discriminative) classifiers is designed and evaluated on a large database of unedited continuous multichannel neonatal EEG recordings of over 800 h in duration. It is shown that an improvement in the detection of neonatal seizures over the course of long EEG recordings is achievable with on-the-fly incorporation of patient-specific EEG characteristics. In the clinical setting, the employment of the developed system will maintain a seizure detection rate at 70% while halving the number of false detections per hour, from 0.4 to 0.2 FD/h. This is the first study to propose the use of online adaptation without clinical labels, to build a personalized diagnostic system for the detection of neonatal seizures.

Accurate Heart Rate Monitoring During Physical Exercises Using PPG

OBJECTIVE

The challenging task of heart rate (HR) estimation from the photoplethysmographic (PPG) signal, during intensive physical exercises, is tackled in this paper.

METHODS

The study presents a detailed analysis of a novel algorithm (WFPV) that exploits a Wiener filter to attenuate the motion artifacts, a phase vocoder to refine the HR estimate and user-adaptive post-processing to track the subject physiology. Additionally, an offline version of the HR estimation algorithm that uses Viterbi decoding is designed for scenarios that do not require online HR monitoring (WFPV+VD). The performance of the HR estimation systems is rigorously compared with existing algorithms on the publically available database of 23 PPG recordings.

RESULTS

On the whole dataset of 23 PPG recordings, the algorithms result in average absolute errors of 1.97 and 1.37 BPM in the online and offline modes, respectively. On the test dataset of 10 PPG recordings which were most corrupted with motion artifacts, WFPV has an error of 2.95 BPM on its own and 2.32 BPM in an ensemble with two existing algorithms.

CONCLUSION

The error rate is significantly reduced when compared with the state-of-the art PPG-based HR estimation methods.

SIGNIFICANCE

The proposed system is shown to be accurate in the presence of strong motion artifacts and in contrast to existing alternatives has very few free parameters to tune. The algorithm has a low computational cost and can be used for fitness tracking and health monitoring in wearable devices. The MATLAB implementation of the algorithm is provided online.

Clinical implementation of a neonatal seizure detection algorithm

Technologies for automated detection of neonatal seizures are gradually moving towards cot-side implementation. The aim of this paper is to present different ways to visualize the output of a neonatal seizure detection system and analyse their influence on performance in a clinical environment. Three different ways to visualize the detector output are considered: a binary output, a probabilistic trace, and a spatio-temporal colormap of seizure observability. As an alternative to visual aids, audified neonatal EEG is also considered. Additionally, a survey on the usefulness and accuracy of the presented methods has been performed among clinical personnel. The main advantages and disadvantages of the presented methods are discussed. The connection between information visualization and different methods to compute conventional metrics is established. The results of the visualization methods along with the system validation results indicate that the developed neonatal seizure detector with its current level of performance would unambiguously be of benefit to clinicians as a decision support system. The results of the survey suggest that a suitable way to visualize the output of neonatal seizure detection systems in a clinical environment is a combination of a binary output and a probabilistic trace. The main healthcare benefits of the tool are outlined. The decision support system with the chosen visualization interface is currently undergoing pre-market European multi-centre clinical investigation to support its regulatory approval and clinical adoption.

Detection of seizures in intracranial EEG: UPenn and Mayo Clinic's Seizure Detection Challenge

A system for detection of seizures in intracranial EEG is presented that is based on a combination of generative, discriminative and hybrid approaches. We present a methodology to effectively benefit from the advantages each classifier offers. In particular, Gaussian mixture models, Support Vector Machines, hybrid likelihood ratio and Gaussian supervector approaches are developed and combined for the task. This system participated in the UPenn and Mayo Clinic's Seizure Detection Challenge, ranking in the top 5 of over 200 participants. The drawbacks of the proposed method with respect to the winning solutions are critically assessed.

Automated detection of perturbed cardiac physiology during oral food allergen challenge in children

This paper investigates the fully automated computer-based detection of allergic reaction in oral food challenges using pediatric ECG signals. Nonallergic background is modeled using a mixture of Gaussians during oral food challenges, and the model likelihoods are used to determine whether a subject is allergic to a food type. The system performance is assessed on the dataset of 24 children (15 allergic and 9 nonallergic) totaling 34 h of data. The proposed detector correctly classified all nonallergic subjects (100% specificity) and 12 allergic subjects (80% sensitivity) and is capable of detecting allergy on average 17 min earlier than trained clinicians during oral food challenges, the gold standard of allergy diagnosis. Inclusion of the developed allergy classification platform during oral food challenges recorded would result in a 30% reduction of doses administered to allergic subjects. The results of study introduce the possibility to halt challenges earlier which can safely advance the state of clinical art of allergy diagnosis by reducing the overall exposure to the allergens.