Automated diagnosis of EEG abnormalities with different classification techniques

Automatic seizure detection and prediction using clinical Electroencephalograms (EEGs) are challenging tasks due to factors such as low Signal-to-Noise Ratios (SNRs), high variance in epileptic seizures among patients, and limited clinical data constraints. To overcome these challenges, this paper presents two approaches for EEG signal classification. One of these approaches depends on Machine Learning (ML) tools. The used features are different types of entropy, higher-order statistics, and sub-band energies in the Hilbert Marginal Spectrum (HMS) domain. The classification is performed using Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbor (KNN) classifiers. Both seizure detection and prediction scenarios are considered. The second approach depends on spectrograms of EEG signal segments and a Convolutional Neural Network (CNN)-based residual learning model. We use 10000 spectrogram images for each class. In this approach, it is possible to perform both seizure detection and prediction in addition to a 3-state classification scenario. Both approaches are evaluated on the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) dataset, which contains 24 EEG recordings for 6 males and 18 females. The results obtained for the HMS-based model showed an accuracy of 100%. The CNN-based model achieved accuracies of 97.66%, 95.59%, and 94.51% for Seizure (S) versus Pre-Seizure (PS), Non-Seizure (NS) versus S, and NS versus S versus PS classes, respectively. These results demonstrate that the proposed approaches can be effectively used for seizure detection and prediction. They outperform the state-of-the-art techniques for automatic seizure detection and prediction. Block diagram of proposed epileptic seizure detection method using HMS with different classifiers.

Semisupervised Seizure Prediction in Scalp EEG Using Consistency Regularization

Early prediction of epilepsy seizures can warn the patients to take precautions and improve their lives significantly. In recent years, deep learning has become increasingly predominant in seizure prediction. However, existing deep learning-based approaches in this field require a great deal of labeled data to guarantee performance. At the same time, labeling EEG signals does require the expertise of an experienced pathologist and is incredibly time-consuming. To address this issue, we propose a novel Consistency-based Semisupervised Seizure Prediction Model (CSSPM), where only a fraction of training data is labeled. Our method is based on the principle of consistency regularization, which underlines that a robust model should maintain consistent results for the same input under extra perturbations. Specifically, by using stochastic augmentation and dropout, we consider the entire neural network as a stochastic model and apply a consistency constraint to penalize the difference between the current prediction and previous predictions. In this way, unlabeled data could be fully utilized to improve the decision boundary and enhance prediction performance. Compared with existing studies requiring all training data to be labeled, the proposed method only needs a small portion of data to be labeled while still achieving satisfactory results. Our method provides a promising solution to alleviate the labeling cost for real-world applications.

E-drug delivery: a futuristic approach

Drug delivery systems are undergoing technology changes to enhance patient comfort and compliance. Electronic drug delivery (E-drug delivery) systems are being developed to regulate drug dose delivery by easy monitoring of doses, especially in chronic and age-related diseases. E-drug delivery can monitor the correct dose of anesthesia, could be used in GI tracking by E-capsules, in epilepsy, insulin drug delivery, cardiac ailments and cancer therapy. Wearable E-drug delivery systems and Smartphone apps are the new additions. In this review, the authors attempt to highlight how technology is changing for improved patient comfort and treatment. Personalized drug delivery systems will be the future treatment process in healthcare.

Ultra-low-field magneto-elastocaloric cooling in a multiferroic composite device

The advent of caloric materials for magnetocaloric, electrocaloric, and elastocaloric cooling is changing the landscape of solid state cooling technologies with potentials for high-efficiency and environmentally friendly residential and commercial cooling and heat-pumping applications. Given that caloric materials are ferroic materials that undergo first (or second) order phase transitions near room temperature, they open up intriguing possibilities for multiferroic devices with hitherto unexplored functionalities coupling their thermal properties with different fields (magnetic, electric, and stress) through composite configurations. Here we demonstrate a magneto-elastocaloric effect with ultra-low magnetic field (0.16 T) in a compact geometry to generate a cooling temperature change as large as 4 K using a magnetostriction/superelastic alloy composite. Such composite systems can be used to circumvent shortcomings of existing technologies such as the need for high-stress actuation mechanism for elastocaloric materials and the high magnetic field requirement of magnetocaloric materials, while enabling new applications such as compact remote cooling devices.

The broad use of elastocaloric materials in cooling applications is hindered by the need to exert large forces onto the material. Compressing a magnetostrictive-elastocaloric composite using a low magnetic field of 0.16 T, temperature changes up to 4 K are achieved without applying external forces.

Laminated pyroelectric generator with spin coated transparent poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:PSS) electrodes for a flexible self-powered stimulator

A laminated pyroelectric generator with spray coated transparent PEDOT:PSS electrodes has been designed for use as a flexible self-powered stimulator.

Detection of seizure and epilepsy using higher order statistics in the EMD domain

In this paper, a method using higher order statistical moments of EEG signals calculated in the empirical mode decomposition (EMD) domain is proposed for detecting seizure and epilepsy. The appropriateness of these moments in distinguishing the EEG signals is investigated through an extensive analysis in the EMD domain. An artificial neural network is employed as the classifier of the EEG signals wherein these moments are used as features. The performance of the proposed method is studied using a publicly available benchmark database for various classification cases that include healthy, interictal (seizure-free interval) and ictal (seizure), healthy and seizure, nonseizure and seizure, and interictal and ictal, and compared with that of several recent methods based on time-frequency analysis and statistical moments. It is shown that the proposed method can provide, in almost all the cases, 100% accuracy, sensitivity, and specificity, especially in the case of discriminating seizure activities from the nonseizure ones for patients with epilepsy while being much faster as compared to the time-frequency analysis-based techniques.

Wireless recording systems: from noninvasive EEG-NIRS to invasive EEG devices

In this paper, we present the design and implementation of a wireless wearable electronic system dedicated to remote data recording for brain monitoring. The reported wireless recording system is used for a) simultaneous near-infrared spectrometry (NIRS) and scalp electro-encephalography (EEG) for noninvasive monitoring and b) intracerebral EEG (icEEG) for invasive monitoring. Bluetooth and dual radio links were introduced for these recordings. The Bluetooth-based device was embedded in a noninvasive multichannel EEG-NIRS system for easy portability and long-term monitoring. On the other hand, the 32-channel implantable recording device offers 24-bit resolution, tunable features, and a sampling frequency up to 2 kHz per channel. The analog front-end preamplifier presents low input-referred noise of 5 μ VRMS and a signal-to-noise ratio of 112 dB. The communication link is implemented using a dual-band radio frequency transceiver offering a half-duplex 800 kb/s data rate, 16.5 mW power consumption and less than 10(-10) post-correction Bit-Error Rate (BER). The designed system can be accessed and controlled by a computer with a user-friendly graphical interface. The proposed wireless implantable recording device was tested in vitro using real icEEG signals from two patients with refractory epilepsy. The wirelessly recorded signals were compared to the original signals recorded using wired-connection, and measured normalized root-mean square deviation was under 2%.

A Smart Biological Signal-Responsive Focal Drug Delivery System for Treatment of Refractory Epilepsy

In this paper, we propose a new biological signal-responsive implantable device that triggers direct an anticonvulsive drug into the epileptogenic zone at electrographic seizure onset. We describe the high-performance seizure-onset detection algorithm, low-power circuit technique and focal drug delivery system. The implantable device is composed of a preamplifier, a signal processor, a seizure detector and a micropump. The device records high quality intracerebral electroencephalographic (icEEG) signals using high conductive electrodes and a low noise preamplifier. The recorded signal is processed continuously using low-power technique to detect onset of seizures accurately. The low-power miniaturized micropump is able to deliver sufficient amount of anticonvulsive drug in a short duration (50µL/sec) to epileptogenic zone. The detection algorithm was validated with Matlab tools and a prototype device was assembled with discrete components in a circular (Ø 40 mm) printed circuit board. The device was validated offline using the icEEG recordings obtained from 3 drug-resistant epilepsy patients. The average seizure detection delay was 10 sec from electrographic seizure onset, well before seizure progression to adjacent functional cortex.

A novel low-power-implantable epileptic seizure-onset detector

A novel implantable low-power integrated circuit is proposed for real-time epileptic seizure detection. The presented chip is part of an epilepsy prosthesis device that triggers focal treatment to disrupt seizure progression. The proposed chip integrates a front-end preamplifier, voltage-level detectors, digital demodulators, and a high-frequency detector. The preamplifier uses a new chopper stabilizer topology that reduces instrumentation low-frequency and ripple noises by modulating the signal in the analog domain and demodulating it in the digital domain. Moreover, each voltage-level detector consists of an ultra-low-power comparator with an adjustable threshold voltage. The digitally integrated high-frequency detector is tunable to recognize the high-frequency activities for the unique detection of seizure patterns specific to each patient. The digitally controlled circuits perform accurate seizure detection. A mathematical model of the proposed seizure detection algorithm was validated in Matlab and circuits were implemented in a 2 mm(2) chip using the CMOS 0.18- μm process. The proposed detector was tested by using intracerebral electroencephalography (icEEG) recordings from seven patients with drug-resistant epilepsy. The seizure signals were assessed by the proposed detector and the average seizure detection delay was 13.5 s, well before the onset of clinical manifestations. The measured total power consumption of the detector is 51 μW.