Evaluating the Window Size's Role in Automatic EEG Epilepsy Detection.

Electroencephalography is one of the most commonly used methods for extracting information about the brain's condition and can be used for diagnosing epilepsy. The EEG signal's wave shape contains vital information about the brain's state, which can be challenging to analyse and interpret by a human observer. Moreover, the characteristic waveforms of epilepsy (sharp waves, spikes) can occur randomly through time. Considering all the above reasons, automatic EEG signal extraction and analysis using computers can significantly impact the successful diagnosis of epilepsy. This research explores the impact of different window sizes on EEG signals' classification accuracy using four machine learning classifiers. The machine learning methods included a neural network with ten hidden nodes trained using three different training algorithms and the k-nearest neighbours classifier. The neural network training methods included the Broyden-Fletcher-Goldfarb-Shanno algorithm, the multistart method for global optimization problems, and a genetic algorithm. The current research utilized the University of Bonn dataset containing EEG data, divided into epochs having 50% overlap and window lengths ranging from 1 to 24 s. Then, statistical and spectral features were extracted and used to train the above four classifiers. The outcome from the above experiments showed that large window sizes with a length of about 21 s could positively impact the classification accuracy between the compared methods.

Assessing Electroencephalography as a Stress Indicator: A VR High-Altitude Scenario Monitored through EEG and ECG.

Over the last decade, virtual reality (VR) has become an increasingly accessible commodity. Head-mounted display (HMD) immersive technologies allow researchers to simulate experimental scenarios that would be unfeasible or risky in real life. An example is extreme heights exposure simulations, which can be utilized in research on stress system mobilization. Until recently, electroencephalography (EEG)-related research was focused on mental stress prompted by social or mathematical challenges, with only a few studies employing HMD VR techniques to induce stress. In this study, we combine a state-of-the-art EEG wearable device and an electrocardiography (ECG) sensor with a VR headset to provoke stress in a high-altitude scenarios while monitoring EEG and ECG biomarkers in real time. A robust pipeline for signal clearing is implemented to preprocess the noise-infiltrated (due to movement) EEG data. Statistical and correlation analysis is employed to explore the relationship between these biomarkers with stress. The participant pool is divided into two groups based on their heart rate increase, where statistically important EEG biomarker differences emerged between them. Finally, the occipital-region band power changes and occipital asymmetry alterations were found to be associated with height-related stress and brain activation in beta and gamma bands, which correlates with the results of the self-reported Perceived Stress Scale questionnaire.

Alzheimer's Disease and Frontotemporal Dementia: A Robust Classification Method of EEG Signals and a Comparison of Validation Methods.

Dementia is the clinical syndrome characterized by progressive loss of cognitive and emotional abilities to a degree severe enough to interfere with daily functioning. Alzheimer's disease (AD) is the most common neurogenerative disorder, making up 50-70% of total dementia cases. Another dementia type is frontotemporal dementia (FTD), which is associated with circumscribed degeneration of the prefrontal and anterior temporal cortex and mainly affects personality and social skills. With the rapid advancement in electroencephalogram (EEG) sensors, the EEG has become a suitable, accurate, and highly sensitive biomarker for the identification of neuronal and cognitive dynamics in most cases of dementia, such as AD and FTD, through EEG signal analysis and processing techniques. In this study, six supervised machine-learning techniques were compared on categorizing processed EEG signals of AD and FTD cases, to provide an insight for future methods on early dementia diagnosis. K-fold cross validation and leave-one-patient-out cross validation were also compared as validation methods to evaluate their performance for this classification problem. The proposed methodology accuracy scores were 78.5% for AD detection with decision trees and 86.3% for FTD detection with random forests.

Modelling Hydrocortisone Pharmacokinetics on a Subcutaneous Pulsatile Infusion Replacement Strategy in Patients with Adrenocortical Insufficiency.

In the context of glucocorticoid (GC) therapeutics, recent studies have utilised a subcutaneous hydrocortisone (HC) infusion pump programmed to deliver multiple HC pulses throughout the day, with the purpose of restoring normal circadian and ultradian GC rhythmicity. A key challenge for the advancement of novel HC replacement therapies is the calibration of infusion pumps against cortisol levels measured in blood. However, repeated blood sampling sessions are enormously labour-intensive for both examiners and examinees. These sessions also have a cost, are time consuming and are occasionally unfeasible. To address this, we developed a pharmacokinetic model approximating the values of plasma cortisol levels at any point of the day from a limited number of plasma cortisol measurements. The model was validated using the plasma cortisol profiles of 9 subjects with disrupted endogenous GC synthetic capacity. The model accurately predicted plasma cortisol levels (mean absolute percentage error of 14%) when only four plasma cortisol measurements were provided. Although our model did not predict GC dynamics when HC was administered in a way other than subcutaneously or in individuals whose endogenous capacity to produce GCs is intact, it was found to successfully be used to support clinical trials (or practice) involving subcutaneous HC delivery in patients with reduced endogenous capacity to synthesize GCs.

IoT Micro-Blockchain Fundamentals.

In this paper we investigate the essential minimum functionality of the autonomous blockchain, and the minimum hardware and software required to support it in the micro-scale in the IoT world. The application of deep-blockchain operation in the lower-level activity of the IoT ecosystem, is expected to bring profound clarity and constitutes a unique challenge. Setting up and operating bit-level blockchain mechanisms on minimal IoT elements like smart switches and active sensors, mandates pushing blockchain engineering to the limits. "How deep can blockchain actually go?" "Which is the minimum Thing of the IoT world that can actually deliver autonomous blockchain functionality?" To answer, an experiment based on IoT micro-controllers was set. The "Witness Protocol" was defined to set the minimum essential micro-blockchain functionality. The protocol was developed and installed on a peer, ad-hoc, autonomous network of casual, real-life IoT micro-devices. The setup was tested, benchmarked, and evaluated in terms of computational needs, efficiency, and collective resistance against malicious attacks. The leading considerations are highlighted, and the results of the experiment are presented. Findings are intriguing and prove that fully autonomous, private micro-blockchain networks are absolutely feasible in the smart dust world, utilizing the capacities of the existing low-end IoT devices.

Machine Learning Algorithms and Statistical Approaches for Alzheimer's Disease Analysis Based on Resting-State EEG Recordings: A Systematic Review.

Alzheimer's Disease (AD) is a neurodegenerative disorder and the most common type of dementia with a great prevalence in western countries. The diagnosis of AD and its progression is performed through a variety of clinical procedures including neuropsychological and physical examination, Electroencephalographic (EEG) recording, brain imaging and blood analysis. During the last decades, analysis of the electrophysiological dynamics in AD patients has gained great research interest, as an alternative and cost-effective approach. This paper summarizes recent publications focusing on (a) AD detection and (b) the correlation of quantitative EEG features with AD progression, as it is estimated by Mini Mental State Examination (MMSE) score. A total of 49 experimental studies published from 2009 until 2020, which apply machine learning algorithms on resting state EEG recordings from AD patients, are reviewed. Results of each experimental study are presented and compared. The majority of the studies focus on AD detection incorporating Support Vector Machines, while deep learning techniques have not yet been applied on large EEG datasets. Promising conclusions for future studies are presented.

Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation.

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor's accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method's outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area-resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM).

EEG Window Length Evaluation for the Detection of Alzheimer's Disease over Different Brain Regions.

Alzheimer's Disease (AD) is a neurogenerative disorder and the most common type of dementia with a rapidly increasing world prevalence. In this paper, the ability of several statistical and spectral features to detect AD from electroencephalographic (EEG) recordings is evaluated. For this purpose, clinical EEG recordings from 14 patients with AD (8 with mild AD and 6 with moderate AD) and 10 healthy, age-matched individuals are analyzed. The EEG signals are initially segmented in nonoverlapping epochs of different lengths ranging from 5 s to 12 s. Then, a group of statistical and spectral features calculated for each EEG rhythm (δ, θ, α, ß, and γ) are extracted, forming the feature vector that trained and tested a Random Forests classifier. Six classification problems are addressed, including the discrimination from whole-brain dynamics and separately from specific brain regions in order to highlight any alterations of the cortical regions. The results indicated a high accuracy ranging from 88.79% to 96.78% for whole-brain classification. Also, the classification accuracy was higher at the posterior and central regions than at the frontal area and the right side of temporal lobe for all classification problems.

A methodology for automated CPA extraction using liver biopsy image analysis and machine learning techniques.

BACKGROUND AND OBJECTIVE: Collagen proportional area (CPA) extraction in liver biopsy images provides the degree of fibrosis expansion in liver tissue, which is the most characteristic histological alteration in hepatitis C virus (HCV). Assessment of the fibrotic tissue is currently based on semiquantitative staging scores such as Ishak and Metavir. Since its introduction as a fibrotic tissue assessment technique, CPA calculation based on image analysis techniques has proven to be more accurate than semiquantitative scores. However, CPA has yet to reach everyday clinical practice, since the lack of standardized and robust methods for computerized image analysis for CPA assessment have proven to be a major limitation. METHODS: The current work introduces a three-stage fully automated methodology for CPA extraction based on machine learning techniques. Specifically, clustering algorithms have been employed for background-tissue separation, as well as for fibrosis detection in liver tissue regions, in the first and the third stage of the methodology, respectively. Due to the existence of several types of tissue regions in the image (such as blood clots, muscle tissue, structural collagen, etc.), classification algorithms have been employed to identify liver tissue regions and exclude all other non-liver tissue regions from CPA computation. RESULTS: For the evaluation of the methodology, 79 liver biopsy images have been employed, obtaining 1.31% mean absolute CPA error, with 0.923 concordance correlation coefficient. CONCLUSIONS: The proposed methodology is designed to (i) avoid manual threshold-based and region selection processes, widely used in similar approaches presented in the literature, and (ii) minimize CPA calculation time.

A clustering based method for collagen proportional area extraction in liver biopsy images.

Collagen Proportional Area (CPA) extraction using digital image analysis (DIA) in liver biopsies provides an effective way to estimate the liver disease staging. CPA represents accurately fibrosis expansion in liver tissue. This paper presents an automated clustering-based method for fibrosis detection and CPA computation. Initially, a k-means based approach is employed to detect the liver tissue and eliminate the background. Next, the method decides about the adequacy of current biopsy, according to the size of liver tissue. Biopsies which contain small and segmented specimens must be repeated. Since the tissue has been detected, fibrosis areas are also found in the tissue. Finally, CPA is computed. For the evaluation of the proposed method 25 images are employed and the percentage errors of CPA are computed for each image. In the majority of the cases, small variation of CPA is computed, comparing to the expert's annotation.

PERFORM: a system for monitoring, assessment and management of patients with Parkinson's disease.

In this paper, we describe the PERFORM system for the continuous remote monitoring and management of Parkinson's disease (PD) patients. The PERFORM system is an intelligent closed-loop system that seamlessly integrates a wide range of wearable sensors constantly monitoring several motor signals of the PD patients. Data acquired are pre-processed by advanced knowledge processing methods, integrated by fusion algorithms to allow health professionals to remotely monitor the overall status of the patients, adjust medication schedules and personalize treatment. The information collected by the sensors (accelerometers and gyroscopes) is processed by several classifiers. As a result, it is possible to evaluate and quantify the PD motor symptoms related to end of dose deterioration (tremor, bradykinesia, freezing of gait (FoG)) as well as those related to over-dose concentration (Levodopa-induced dyskinesia (LID)). Based on this information, together with information derived from tests performed with a virtual reality glove and information about the medication and food intake, a patient specific profile can be built. In addition, the patient specific profile with his evaluation during the last week and last month, is compared to understand whether his status is stable, improving or worsening. Based on that, the system analyses whether a medication change is needed--always under medical supervision--and in this case, information about the medication change proposal is sent to the patient. The performance of the system has been evaluated in real life conditions, the accuracy and acceptability of the system by the PD patients and healthcare professionals has been tested, and a comparison with the standard routine clinical evaluation done by the PD patients' physician has been carried out. The PERFORM system is used by the PD patients and in a simple and safe non-invasive way for long-term record of their motor status, thus offering to the clinician a precise, long-term and objective view of patient's motor status and drug/food intake. Thus, with the PERFORM system the clinician can remotely receive precise information for the PD patient's status on previous days and define the optimal therapeutical treatment.

Wearability assessment of a wearable system for Parkinson's disease remote monitoring based on a body area network of sensors.

Wearable technologies for health monitoring have become a reality in the last few years. So far, most research studies have focused on assessments of the technical performance of these systems, as well as the validation of the clinical outcomes. Nevertheless, the success in the acceptance of these solutions depends not only on the technical and clinical effectiveness, but on the final user acceptance. In this work the compliance of a telehealth system for the remote monitoring of Parkinson's disease (PD) patients is presented with testing in 32 PD patients. This system, called PERFORM, is based on a Body Area Network (BAN) of sensors which has already been validated both from the technical and clinical point for view. Diverse methodologies (REBA, Borg and CRS scales in combination with a body map) are employed to study the comfort, biomechanical and physiological effects of the system. The test results allow us to conclude that the acceptance of this system is satisfactory with all the levels of effect on each component scoring in the lowest ranges. This study also provided useful insights and guidelines to lead to redesign of the system to improve patient compliance.

Modeling and simulation of speed selection on left ventricular assist devices.

The control problem for LVADs is to set pump speed such that cardiac output and pressure perfusion are within acceptable physiological ranges. However, current technology of LVADs cannot provide for a closed-loop control scheme that can make adjustments based on the patient's level of activity. In this context, the SensorART Speed Selection Module (SSM) integrates various hardware and software components in order to improve the quality of the patients' treatment and the workflow of the specialists. It enables specialists to better understand the patient-device interactions, and improve their knowledge. The SensorART SSM includes two tools of the Specialist Decision Support System (SDSS); namely the Suction Detection Tool and the Speed Selection Tool. A VAD Heart Simulation Platform (VHSP) is also part of the system. The VHSP enables specialists to simulate the behavior of a patient׳s circulatory system, using different LVAD types and functional parameters. The SDSS is a web-based application that offers specialists with a plethora of tools for monitoring, designing the best therapy plan, analyzing data, extracting new knowledge and making informative decisions. In this paper, two of these tools, the Suction Detection Tool and Speed Selection Tool are presented. The former allows the analysis of the simulations sessions from the VHSP and the identification of issues related to suction phenomenon with high accuracy 93%. The latter provides the specialists with a powerful support in their attempt to effectively plan the treatment strategy. It allows them to draw conclusions about the most appropriate pump speed settings. Preliminary assessments connecting the Suction Detection Tool to the VHSP are presented in this paper.

Adverse event prediction in patients with left ventricular assist devices.

This work presents the Treatment Tool, which is a component of the Specialist's Decision Support Framework (SDSS) of the SensorART platform. The SensorART platform focuses on the management of heart failure (HF) patients, which are treated with implantable, left ventricular assist devices (LVADs). SDSS supports the specialists on various decisions regarding patients with LVADs including decisions on the best treatment strategy, suggestion of the most appropriate candidates for LVAD weaning, configuration of the pump speed settings, while also provides data analysis tools for new knowledge extraction. The Treatment Tool is a web-based component and its functionality includes the calculation of several acknowledged risk scores along with the adverse events appearance prediction for treatment assessment.

Automatic detection of freezing of gait events in patients with Parkinson's disease.

The aim of this study is to detect freezing of gait (FoG) events in patients suffering from Parkinson's disease (PD) using signals received from wearable sensors (six accelerometers and two gyroscopes) placed on the patients' body. For this purpose, an automated methodology has been developed which consists of four stages. In the first stage, missing values due to signal loss or degradation are replaced and then (second stage) low frequency components of the raw signal are removed. In the third stage, the entropy of the raw signal is calculated. Finally (fourth stage), four classification algorithms have been tested (Naïve Bayes, Random Forests, Decision Trees and Random Tree) in order to detect the FoG events. The methodology has been evaluated using several different configurations of sensors in order to conclude to the set of sensors which can produce optimal FoG episode detection. Signals recorded from five healthy subjects, five patients with PD who presented the symptom of FoG and six patients who suffered from PD but they do not present FoG events. The signals included 93 FoG events with 405.6s total duration. The results indicate that the proposed methodology is able to detect FoG events with 81.94% sensitivity, 98.74% specificity, 96.11% accuracy and 98.6% area under curve (AUC) using the signals from all sensors and the Random Forests classification algorithm.

An automated methodology for levodopa-induced dyskinesia: assessment based on gyroscope and accelerometer signals.

OBJECTIVE: In this study, a methodology is presented for an automated levodopa-induced dyskinesia (LID) assessment in patients suffering from Parkinson's disease (PD) under real-life conditions. METHODS AND MATERIAL: The methodology is based on the analysis of signals recorded from several accelerometers and gyroscopes, which are placed on the subjects' body while they were performing a series of standardised motor tasks as well as voluntary movements. Sixteen subjects were enrolled in the study. The recordings were analysed in order to extract several features and, based on these features, a classification technique was used for LID assessment, i.e. detection of LID symptoms and classification of their severity. RESULTS: The results were compared with the clinical annotation of the signals, provided by two expert neurologists. The analysis was performed related to the number and topology of sensors used; several different experimental settings were evaluated while a 10-fold stratified cross validation technique was employed in all cases. Moreover, several different classification techniques were examined. The ability of the methodology to be generalised was also evaluated using leave-one-patient-out cross validation. The sensitivity and positive predictive values (average for all LID severities) were 80.35% and 76.84%, respectively. CONCLUSIONS: The proposed methodology can be applied in real-life conditions since it can perform LID assessment in recordings which include various PD symptoms (such as tremor, dyskinesia and freezing of gait) of several motor tasks and random voluntary movements.

Assessment of tremor activity in the Parkinson's disease using a set of wearable sensors.

Tremor is the most common motor disorder of Parkinson's disease (PD) and consequently its detection plays a crucial role in the management and treatment of PD patients. The current diagnosis procedure is based on subject-dependent clinical assessment, which has a difficulty in capturing subtle tremor features. In this paper, an automated method for both resting and action/postural tremor assessment is proposed using a set of accelerometers mounted on different patient's body segments. The estimation of tremor type (resting/action postural) and severity is based on features extracted from the acquired signals and hidden Markov models. The method is evaluated using data collected from 23 subjects (18 PD patients and 5 control subjects). The obtained results verified that the proposed method successfully: 1) quantifies tremor severity with 87 % accuracy, 2) discriminates resting from postural tremor, and 3) discriminates tremor from other Parkinsonian motor symptoms during daily activities.

Spot addressing for microarray images structured in hexagonal grids.

In this work, an efficient method for spot addressing in images, which are generated by the scanning of hexagonal structured microarrays, is proposed. Initially, the blocks of the image are separated using the projections of the image. Next, all the blocks of the image are processed separately for the detection of each spot. The spot addressing procedure begins with the detection of the high intensity objects, which are probably the spots of the image. Next, the Growing Concentric Hexagon algorithm, which uses the properties of the hexagonal grid, is introduced for the detection of the non-hybridized spots. Finally, the Voronoi diagram is applied to the centers of the detected spots for the gridding of the image. The method is evaluated using spots generated from the scanning of the Beadchip of Illumina, which is used for the detection of Single Nucleotide Polymorphisms in the human genome, and uses hexagonal structure for the location of the spots. For the evaluation, the detected centers for each of the spot in the image are compared to the centers of the annotation, obtaining up to 98% accuracy for the spot addressing procedure.

Knowledge Editor and execution engine development for optimal ventricular assist device weaning.

In this work, the weaning module of the SensorART specialist decision support system (SDSS) is presented. SensorART focuses on the treatment of patients suffering from end-stage heart failure (HF). The use of a ventricular assist device (VAD) is the main treatment for HF patients. However in certain cases, myocardial function recovers and VADs can be explanted after the patient is weaned. In that framework an efficient module is developed responsible for the selection of the most suitable candidates for VAD weaning. In this study we describe all technical specifications concerning its two main sub-modules of the weaning module, of the Clinical Knowledge Editor and the Knowledge Execution Engine.

Automated knowledge-based fuzzy models generation for weaning of patients receiving ventricular assist device (VAD) therapy.

The SensorART project focus on the management of heart failure (HF) patients which are treated with implantable ventricular assist devices (VADs). This work presents the way that crisp models are transformed into fuzzy in the weaning module, which is one of the core modules of the specialist's decision support system (DSS) in SensorART. The weaning module is a DSS that supports the medical expert on the weaning and remove VAD from the patient decision. Weaning module has been developed following a "mixture of experts" philosophy, with the experts being fuzzy knowledge-based models, automatically generated from initial crisp knowledge-based set of rules and criteria for weaning.