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.

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, β, 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.

The hackathon model to spur innovation around global mHealth

The challenge of providing quality healthcare to underserved populations in low- and middle-income countries (LMICs) has attracted increasing attention from information and communication technology (ICT) professionals interested in providing societal impact through their work. Sana is an organisation hosted at the Institute for Medical Engineering and Science at the Massachusetts Institute of Technology that was established out of this interest. Over the past several years, Sana has developed a model of organising mobile health bootcamp and hackathon events in LMICs with the goal of encouraging increased collaboration between ICT and medical professionals and leveraging the growing prevalence of cellphones to provide health solutions in resource limited settings. Most recently, these events have been based in Colombia, Uganda, Greece and Mexico. The lessons learned from these events can provide a framework for others working to create sustainable health solutions in the developing world.

eMed: the paradigm of utilization of digital economy techniques for the reimbursement of medical services across Europe

eMed provides for the first time a complete framework for organizations involved in the healthcare sector to utilize eCommerce and m-Commerce technologies and to enable information sharing and partnerships. It devises a sustainable supply-chain model that can best satisfy an ever-changing marketplace. It aids organizations in migrating to an improved system while focusing on driving costs out of the supply chain. eMed is an advanced experiment in the field of healthcare administration that aims at the connection of regional medical communities to the global digital economy. It aims at the creation of local medical digital communities in selected European regions as well as their interconnection. The main objective is to systematically assess the risks and opportunities involved in the implementation of a service for reimbursement of medical services in Europe, based on advanced telematics technologies and digital economy’s techniques.

CAROTID - a web-based platform for optimal personalized management of atherosclerotic patients

Carotid atherosclerosis is the main cause of fatal cerebral ischemic events, thereby posing a major burden for public health and state economies. We propose a web-based platform named CAROTID to address the need for optimal management of patients with carotid atherosclerosis in a twofold sense: (a) objective selection of patients who need carotid-revascularization (i.e., high-risk patients), using a multifaceted description of the disease consisting of ultrasound imaging, biochemical and clinical markers, and (b) effective storage and retrieval of patient data to facilitate frequent follow-ups and direct comparisons with related cases. These two services are achieved by two interconnected modules, namely the computer-aided diagnosis (CAD) tool and the intelligent archival system, in a unified, remotely accessible system. We present the design of the platform and we describe three main usage scenarios to demonstrate the CAROTID utilization in clinical practice. Additionally, the platform was evaluated in a real clinical environment in terms of CAD performance, end-user satisfaction and time spent on different functionalities. CAROTID classification of high- and low-risk cases was 87%; the corresponding stenosis-degree-based classification would have been 61%. Questionnaire-based user satisfaction showed encouraging results in terms of ease-of-use, clinical usefulness and patient data protection. Times for different CAROTID functionalities were generally short; as an example, the time spent for generating the diagnostic decision was 5min in case of 4-s ultrasound video. Large datasets and future evaluation sessions in multiple medical institutions are still necessary to reveal with confidence the full potential of the platform.

Monitoring stress in fish by applying image analysis to their skin mucous cells

Several authors have previously demonstrated that the number of the skin mucous cells of fish is affected by many stressors. In the present study, two experiments were conducted in order to examine the effects of two common environmental conditions on the morphology of skin of sea bass and particularly on the number and diameter of skin mucous cells. In the first experiment, two groups of sea bass (mean weight 155.6±10.3 g SD) were maintained in two different concentrations of nitrate, 100 and 700 ppm respectively, for 48 h, while a third group was used as control. In the second experiment, sea bass (initial mean weight 78.9±3.1 g SD) were divided into four groups and each group was maintained in a different level of oxygen for 9 weeks. The oxygen concentration in each group was: 3.6±0.2 ppm, 4.7±0.2 ppm, 6.2±0.2 ppm and 8.2±0.2 ppm. In both experiments the effects of the two environmental factors on the morphology of the fish skin were examined histologically and a software containing a visual basic script macro, allowing quantification of the skin mucous cells, was used to analyze the skin tissue sections. Concerning the overall morphology of the skin and the diameter of the skin mucous cells, no differences were noted in both experiments (P>0.05). It was demonstrated however, that fish maintained in the lowest oxygen level and fish maintained in the highest concentration of nitrate exhibited significantly increased number of mucous cells per skin area (mm²). There is evidence that the enumeration of the skin mucous cells of fish can be used to monitor stress in fish.

Immersion booster vaccination effect on sea bass (Dicentrarchus labrax L.) juveniles*

In each challenge 30 sea bass juveniles (mean weight 3.3 +/- 0.2 g SD) were used. During the whole experiment (water T: 18 +/- 1 degrees C) the fish were held in four 50l seawater independent recirculation systems (one fish group per 50l system). The protection to the pathogen Vibrio anguillarum was tested on booster vaccinated sea bass (Dicentrarchus labrax L.) juveniles. The vaccination was performed by immersion for 60 s in a commercial anti-V. anguillarum vaccine suspension. Booster vaccination took place 60 days after the initial immunization. Thirty days after the booster vaccination all the fish received intraperitoneally (IP) 3.0 x 10(6) cfu/fish (colony forming units) virulent V. anguillarum bacteria. The booster vaccination showed a strong protection effect on the challenged sea bass. In the next 20 days after the challenge the mortality was 0% among the booster vaccinated sea bass, 10% among the once vaccinated fish and 50% in the control group (unvaccinated fish). No mortality was observed among the unvaccinated sea bass injected IP with sterile normal saline by the challenge.

Cost-effective Ambulatory Monitoring

The Mobinet service concept emerged, as points of care move closer to the patient and the citizen/patient undertakes a more active role in healthcare monitoring and prevention. Today's advances in monitoring devices and telecommunication networks have made possible a viable solution regarding the provision of continuous health monitoring services, seamlessly from the patients' point of view. The Mobinet concept has been tested under various clinical, technical and business pilots throughout Europe and is currently set for commercial launch in Greece.

Ambulatory monitoring for chronic cardiac and pulmonary patients

In the Greek pilot of the e-Vital project, remote telemedicine services are provided to chronic cardiac and pulmonary patients who are not confined to a hospital (i.e. receiving home/ambulatory health care) with the aim of exploring the dynamics of interactive continuous chronic patient monitoring, particularly focusing on the impact on patient's quality of life, the patient's active involvement in their own care and according impact on the overall quality of healthcare provision, as well as the benefits for healthcare providers (time management, patient management, savings, etc). The current trial in progress validates the business potential of remote monitoring services and demonstrates the technical environment that enables patient-doctor interaction regardless of location and the according communication modes and protocols. The domain for applying the envisaged service is the private healthcare sector and the users groups include individual chronic patients with cardiac and pulmonary diseases. So far, from the patient's point of view, the service mainly appeals to patients with arrhythmias due to lightweight technology and easy processes involved in the transmission of 1-lead ECG. Asthma and COPD patients are also enthusiastic, as they can receive doctor advice in real time. From the health professional's point of view the service has real added value in the fields of diagnosis, prevention, monitoring and follow up. In the case of asthma and COPD the value of the service in diagnosis is even more apparent as these patients may be asymptomatic, when they visit their doctor and have exacerbations when they are at home. e-Vital in this case ensures that the healthcare professional will acquire the complete image of the patient condition. Finally, the experiences gained so far indicate that e-Vital could be particularly efficient in isolated areas, with shortage of experienced scientific personnel.

Cost-effective health services for interactive continuous monitoring of vital signs parameters--the e-Vital concept

The objective of the e-Vital project is the validation of the market concerning the provision of a novel remote telemedicine service aimed at large sensitive parts of the European population, the "at-risk" citizens, who are usually patients with a stable medical condition that allow a near normal life but may suddenly deteriorate and put life at risk. This service will increase their quality of life and their feeling of safety concerning their health. The e-Vital project focuses on the implementation and exploitation of a modular and ambulatory secure telemedicine platform, which is using easily wearable vital signs monitoring devices, causing minimal discomfort to patients, and which transfer in real time and on-line critical vital parameters to doctors and/or medical experts/consultants, regardless of their location, while getting feedback to increase their feeling of comfort or in case of alarm. The interactive continuous monitoring promises cost effective health services, more active involvement of patients in their own care, and a new sense of realism in making a diagnosis.

Single-channel demodulator and Hartley transform in MRI

A single-channel alternative detection system for magnetic resonance imaging and spectroscopy experiments is presented. After the phase error identification, which is realized through a simple method, one can correct the reconstructed image and discriminate between positive and negative frequencies without any loss of the S/N ratio. Since there is only one channel, that is a real signal, it is possible to use the Hartley instead of the Fourier transform. The former is faster and requires less storage memory.

Activation of peripheral blood lymphocytes in patients with primary Sjögren's syndrome

The peripheral blood from 15 patients with primary Sjögren's syndrome and from 15 matched controls was examined for the presence of activated T and B lymphocytes, by using monoclonal antibodies directed to interleukin-2 (IL-2) and transferrin receptors, and to HLA-DR determinants. The number of circulating positive-T cells was significantly greater in the patients than in the controls, irrespective of disease activity. There were more of the CD8 cells than of the CD4 cells that expressed IL-2 receptors. There was a small but significant increase in activated B cells in the patients, since this population is virtually absent from the normal blood.

CD5-expressing B lymphocytes in the blood and salivary glands of patients with primary Sjögren's syndrome

CD5, the human counterpart of Ly-1 molecules in the mouse, are detectable but weakly expressed on a minute fraction of circulating B cells. The number of CD5 + B cells in the blood of patients with Sjögren's syndrome was slightly higher than in control blood, but it became statistically significant after treatment of the cells with phorbol myristic acetate. These numbers were even higher in patients with homogeneous serum bands than in the others. A few scattered cells were stained with anti-human IgM antibody on salivary gland sections, and among them 5-10% were found to be positive for anti-CD5.