Showing papers in "Health technology in 2020"

Nanocomposites: a brief review

Abstract: Nanocomposite material consists out of several phases where at least one, two or three dimensions are in nanometer range. Taking material dimensions down to nanometer level creates phase interfaces which are very important for enhancement of materials properties. The ratio between surface area and volume of reinforced material used during nanocomposites preparation is directly involved in understanding of structure-property relationship. Nanocomposties offer opportunities on completely new scales for solving obstacles ranging from medical, pharmaceutical industry, food packaging, to electronics and energy industry. This paper presents main ideas behind nanocomposites and discusses matrix materials upon which nanocomposites can be divided in three classes; metal matrix, ceramic matrix and polymer matrix nanocomposites. The goal is to explain which raw material and technique is most suited for processing of a particular nanocomposites as well as application, advantages and drawbacks of nanocomposites. Nanotechnology is still in development and current limitations hinder global transition from macro-scale to nano-scale.

Electronic medical record systems: decision support examination framework for individual, security and privacy concerns using multi-perspective analysis

Abstract: Electronic medical record (EMR) is currently a popular topic in e-health. EMR includes the health-related information of patients and forms the main factor of e-health applications. Moreover, EMR contains the legal records that are created in the medical centre and ambulatory environments. These records serve as the data source for electronic health record. Although hospitals utilise the EMR system, healthcare professionals experience difficultly in trusting this system. Studies devoted to EMR acceptance in hospitals are lacking, particularly those on the EMR system in the contexts of privacy and security concerns based on multi-criteria perspective. Thus, the current study proposes a decision support examination framework on how individual, security and privacy determinants influence the acceptance and use of EMR. The proposed framework is based on a multi-criteria perspective derived from healthcare professionals in Malaysia as frame of reference. The framework comprises four phases. The sub-factors of individual, security and privacy determinants were investigated in the two initial phases. Thereafter, the sub-factors were identified with uniform multi-criteria perspective to establish a decision matrix. The decision matrix used individual uniform as basis to cluster the sub-factors and user perspectives. Subsequently, a new ‘multi-criteria decision-making (MCDM) approach’ was adopted. Integrated technique for order of preference by similarity (TOPSIS) and analytic hierarchy process (AHP) were used as bases in employing the MCDM approach to rank each group of factors. K-means clustering was also applied to identify the critical factors in each group. Healthcare professionals in Malaysia were selected as respondents and 100 questionnaires were distributed to those employed in 5 Malaysian public hospitals. A conceptual model adapted from Unified theory of acceptance and use of technology 2 (UTAUT2) was employed to clarify the connection between individual, privacy and security determinants and EMR system acceptance and use in the selected context. After collecting the data sets (363), structural equation modelling was used to analyse data related to EMR acceptance and use. Results are as follows. (1) Five determinants (i.e. data integrity, confidentiality, non-repudiation, facilitating conditions and effort expectancy) exerted an explicit and important positive effect on EMR acceptance and use. (2) Three determinants (i.e. unauthorised, error and secondary use) exerted a direct and significant negative effect on EMR acceptance and use. (3) Three other determinants (i.e. authentication, performance expectancy and habit) insignificantly affected the behavioural intention of healthcare experts in Malaysia to use EMR.

Digital transformation in the area of health: systematic review of 45 years of evolution

Abstract: This study aims to explore the potential of existing digital solutions to improve the quality and safety of healthcare and analyse the emerging trend of digital medicine. Systematic Literature Review (SLR) of the period 1973–2018. To select articles, a prioritization index is proposed, aggregating the characteristics of the score of journals (2017 basis), number of article citations and year of publication, through the Simple Multi-attribute Rating Technique Exploiting Ranks (SMARTER) method. Of the 749 articles listed, 53 were selected and analysed. The majority of research in digital medicine has been focused on integrated management, electronic medical records and medical images, but a research trend is observed in new areas such as virtual service, the use of portable devices as instruments for monitoring the patient and concern about the privacy of medical documents. Categorization in seven areas was carried out, focusing on integrated management of information technology in health, medical images, electronic medical records, development of portable, mobile devices in health, access to e-health, telemedicine and privacy of medical data. Longitudinal analysis of systematized studies, keeping the focus on digital technological developments in health is a trend to extend researchers’ vision, by providing important indications for further study. Suggestions for future investigations are formulated for each identified category. This study reveals great possibilities for SLR with the use of Simple Multi-attribute Rating Technique Exploiting Ranks (SMARTER).

Heart disease classification using data mining tools and machine learning techniques

Abstract: Nowadays, in healthcare industry, data analysis can save lives by improving the medical diagnosis. And with the huge development in software engineering, different data mining tools are available for researchers, and used to conduct studies and experiments. For this, we have decided to compare six common data mining tools: Orange, Weka, RapidMiner, Knime, Matlab, and Scikit-Learn, using six machine learning techniques: Logistic Regression, Support Vector Machine, K Nearest Neighbors, Artificial Neural Network, Naive Bayes, and Random Forest by classifying heart disease. The dataset used in this study has 13 features, one target variable, and 303 instances in which 139 suffers from cardiovascular disease and 164 are healthy subjects. Three performance measures were used to compare the performance of the techniques in each tool: the accuracy, the sensitivity, and the specificity. The results showed that Matlab was the best performing tool, and Matlab’s Artificial Neural Network model was the best performing technique. We concluded this research by plotting the Receiver operating characteristic curve of Matlab and by giving several recommendations on which tool to choose taking into account the users experience in the field of data mining.

Prediction of medical device performance using machine learning techniques: infant incubator case study

Abstract: With development in the area of electronics and artificial intelligence (AI), medical devices (MD) have been sophisticated as well. MD management strategies today are very different than decades ago, so it is reasonable to consider how we can prepare for where we are going in the future. This paper presents the result of application of machine learning (ML) techniques in management of infant incubators in healthcare institutions. A total of 140 samples was used for development of Expert system based on ML classifiers. These samples were collected during 2015–2017 period, as part of yearly inspections of incubators in healthcare institutions by ISO 17020 accredited laboratory. Dataset division 80–20 was used for classifiers development and validation. Performance of the following machine learning algorithms was investigated: Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), k-Nearest Neighbour (kNN), and Support Vector Machine (SVM). Resulting classifiers were compared by performance and classifier based on Decision Tree algorithm yielded highest accuracy (98.5%) among other tested systems. Obtained results suggest that by introducing ML algorithms in MD management strategies benefit healthcare institution firstly in terms of increase of safety and quality of patient diagnosis and treatments, but also in cost optimization and resource management.

New hybrid method for heart disease diagnosis utilizing optimization algorithm in feature selection

Abstract: The number and size of medical databases are rapidly increasing, and the advanced models of data mining techniques could help physicians to make efficient and applicable decisions. The challenges of heart disease data include the feature selection, the number of the samples; imbalance of the samples, lack of magnitude for some features, etc. This study mainly focuses on the feature selection improvement and decreasing the numbers of the features. In this study, imperialist competitive algorithm with meta-heuristic approach is suggested in order to select prominent features of the heart disease. This algorithm can provide a more optimal response for feature selection toward genetic in compare with other optimization algorithms. Also, the K-nearest neighbor algorithm is used for the classification. Evaluation result shows that by using the proposed algorithm, the accuracy of feature selection technique has been improved.

The Inadequacy of Regulatory Frameworks in Time of Crisis and in Low-Resource Settings: Personal Protective Equipment and COVID-19.

Abstract: COVID-19 pandemic is plaguing the world and representing the most significant stress test for many national healthcare systems and services, since their foundation. The supply-chain disruption and the unprecedented request for intensive care unit (ICU) beds have created in Europe conditions typical of low-resources settings. This generated a remarkable race to find solutions for the prevention, treatment and management of this disease which is involving a large amount of people. Every day, new Do-It-Yourself (DIY) solutions regarding personal protective equipment and medical devices populate social media feeds. Many companies (e.g., automotive or textile) are converting their traditional production to manufacture the most needed equipment (e.g., respirators, face shields, ventilators etc.). In this chaotic scenario, policy makers, international and national standards bodies, along with the World Health Organization (WHO) and scientific societies are making a joint effort to increase global awareness and knowledge about the importance of respecting the relevant requirements to guarantee appropriate quality and safety for patients and healthcare workers. Nonetheless, ordinary procedures for testing and certification are currently questioned and empowered with fast-track pathways in order to speed-up the deployment of new solutions for COVID-19. This paper shares critical reflections on the current regulatory framework for the certification of personal protective equipment. We hope that these reflections may help readers in navigating the framework of regulations, norms and international standards relevant for key personal protective equipment, sharing a subset of tests that should be deemed essential even in a period of crisis.

Application of nanoparticles in ocular drug delivery systems

Abstract: Application of a drug in the form of eye drops represents easiest, safest and, at the moment, the most common non-invasive method of ocular drug application. Other conventional ophthalmic formulations in the form of aqueous and oily solutions, ointments, suspensions and emulsions were established to increase bioavailability, solubility and pericorneal retention time of a drug, compared to eye drops. But in the last few decades, nanotechnology-based ophthalmic formulations have been intensively analysed in the area of drug delivery to anterior and posterior parts of the eye. Systems based on nanotechnology with adequate nanoparticle size can be formed to achieve lower irritation and inflammation and better bioavailability and interaction of a drug with ocular tissue. The nanocarrier-based approach led to the development of nanoparticles, nanosuspensions, nanoemulsions, liposomes, nanomicelles, niosomes, nanocrystals and dendrimers for ocular drug delivery. These systems have significant advancements compared to conventional systems, particularly if they are observed as systems for drug delivery to the posterior eye part. Besides advantages, the nanoparticle use in these circumstances could be a reason for concern, because of certain toxic effects noticed in some studies. In this article, we aim to provide an overview of the potential of incorporating an active pharmaceutical ingredient into nanoparticles investigated in the therapy of anterior and posterior eye segment conditions. We will discuss the most important improvements that have been accomplished in the development of nanoparticle-based formulations for the treatment of glaucoma, autoimmune uveitis, age-associated macular degeneration and corneal and choroidal neovascularization.

Hybrid fuzzy based spearman rank correlation for cranial nerve palsy detection in MIoT environment

Abstract: In the recent past, the micro vascular cranial nerve palsy has been detected from the EEG signal using the discrete wavelet transform and multi class support vector machine approach which examines each and every frequencies and features with effective manner. Though the epilepsy are identified using the various techniques, the accuracy and efficiency of the system with less error rate of the classifiers are still one of the major issues in Medical Internet of Things Environment (MIoT). Even though these methods retrieves the cranial nerve palsy which is termed as lack of function of nerves successfully, the efficiency of the system is must be improved. So effective epilepsy which causes cranial nerve palsy need to be analyzed and detect in an automatic manner for minimizing the number of deaths. These problems are reduced by using optimized signal decomposition, Exact feature extraction, selection and the recognition with less error rate has been computed with the help of the Fuzzy based twofold graphic discrete wavelet transform (FTF-TGTWT), hybrid Fuzzy based spearman rank correlation (HF-SRC) Then the performance of the system is analyzed using the experimental results and discussions.

Prostate cancer classification from prostate biomedical data using ant rough set algorithm with radial trained extreme learning neural network

Abstract: Prostate cancer is commonly occurs in prostate that affects small walnut and generates the seminal fluid for men. This disease is happening due to urinating trouble, blood semen, bone pain, stream of urine other harmful activities such as race, obesity and genetic changes. The improper symptoms of prostate cancer disease, it is challenge to identify it in the starting stage. So, different soft computing and machine learning techniques utilized to predict the Prostate cancer due to its severe side effects. Initially prostate cancer biomedical information has been collected from DBCR dataset that manage the patient age, cancer volume, prostate weight, Gleason score, vesicle invasion, prostate specific antigen details and so on. In the wake of gathering prostate biomedical data, undesirable information has been evacuated by applying the mean mode based standardization procedures and the advanced elements are chosen with the assistance of the subterranean insect harsh set hypothesis. The chose information has been arranged utilizing the outspread prepared extraordinary learning neural systems. The classifier successfully classifies the abnormal prostate features. At that point the effectiveness of prostate cancer prediction framework is inspected using assistance of mean square error rate, hit rate, selectivity and accuracy.

Knowledge and understanding among medical imaging professionals in India during the rapid rise of the covid-19 pandemic.

Abstract: During the first week of March,2020 the surge of coronavirus disease (COVID-19) cases reached all over the globe with more than 100,000 cases. Healthcare national and international authorities have already initiated awareness and lockdown activities. A poor understanding of the disease among medical imaging professionals (MIPs) may result in rapid spread of infection. This study aimed to investigate the knowledge and understanding of MIPs about COVID-19. A cross-sectional, web-based study was conducted among MIPs about COVID- 19 during the fourth week of March 2020. An online sample of MIPs was successfully recruited via the authors' networks in India using data collection tool - write google forms. A self-developed online KAP questionnaire was completed by the participants. The knowledge and understanding questionnaire consisted questions regarding the clinical characteristics and transmission routes of COVID-19. Assessment on practices towards COVID-19 included questions on techniques while imaging against COVID-19 suspected patients. Of 700 participants, a total of 550 MIPs completed the survey (response rate: 78.57%); 56.7% were males, 85.4.1% were aged 17-26 years, and most were undergraduates (77.6%) and postgraduates (17.1%). Regarding COVID-19, most of the participants answered correctly (95.5%) on symptoms, (84.4%) time interval for visible symptoms, (98.0%) transmission and (44%) airborne transmission respectively. A significant proportion of MIPs (36.4%) had poor knowledge about wearing multiple masks as an effective measure against coronavirus infection. Most of the respondents (48.5%) incorrectly considered X-ray as the reliable method of diagnosis for suspected COVID-19 patients. 44.6% of the respondents lacked knowledge about the steps involved in hand washing technique which is one of the most important safety practice methods in medical imaging to prevent spread of infection. Factors such as age and occupation were associated with inadequate knowledge and poor perception of COVID-19. As the current global threat of COVID-19 continues to emerge, it is crucial and critical to improve the knowledge and understanding of MIPs. Educational videos and live webinars are urgently needed to reach MIPs and further detailed studies are the need of the hour.

An intelligent and secure healthcare framework for the prediction and prevention of Dengue virus outbreak using fog computing

Abstract: Mosquitoes play a major role in spreading virus to human. One of the major virus is dengue, and it will cause an impact in the normal health condition. It will lead to some side effects in the human body. The prevention steps that are followed by some countries are not sufficient to control the disease. The remote monitoring as well as the detection and prevention with the help of fog and cloud environment will be an effective solution. The proposed framework will act as an effective method for detecting the people affected by dengue at earlier stage, that will help the medical team to provide treatment. The framework presented in this paper will classify the people depends upon the symptoms, alert is send to the people immediately through the mobile. The framework will help the doctors to find the impact of the disease by analysing the outcome and to act effectively within a limited period of time.

Internet of things for sleep tracking: wearables vs. nonwearables

Abstract: Sleep is a very significant biological function for the human being and is important to have a physical balance and a proper regime for a decent quality of life. It is very important to monitor sleep and quality of sleep, especially to older adults because they spend more time in bed compared to younger adults. Insufficient sleep for older adults might cause depression, attention and memory problems, excessive daytime sleepiness, and experience more nighttime falls. The current sleep assessments and evaluation methods are troublesome, expensive, and time-consuming. Thus, the healthcare community is seeking inexpensive and mobile devices that can support a long-term data collection and be accessible to most of the people. This is where a massive use of Internet of Things devices (wearables, low-energy sensors, beacons, apps) is playing a major shift in the quality of life of the population. This paper presents a summary of the current nonintrusive sleep tracking technologies (these include but not limited to consumer sleep trackers e.g., wearables such as bracelets; smart-watches, Mobile Apps and non-wearables such as sleep-tracking mats that can be placed under a bed mattress) and their suitability for the elderly.

A systematic review into the assessment of medical apps: motivations, challenges, recommendations and methodological aspect

Abstract: Recent years have shown significantly pervasive interest in mobile applications (hereinafter “apps”) The number and popularity of these apps are dramatically increasing Even though mobile apps are diverse, countless ones are available through many platforms Some of these apps are not useful nor do they possess rich content, which benefits end users as expected, especially in medical-related cases This research aims to review and analyze articles associated with medical app assessment across different platforms This research also aimed to provide the best practices and identify the academic challenges, motivations and recommendations related with quality assessments In addition, a methodological approach followed in previous research in this domain was also discussed to give some insights for future comers with what to expect We systematically searched articles on topics related to medical app assessment The search was conducted on five major databases, namely, Science Direct, Springer, Web of Science, IEEE Xplore and PubMed from 2009 to September 2019 These indices were considered sufficiently extensive and reliable to cover our scope of the literature Articles were selected on the basis of our inclusion and exclusion criteria (n = 72) Medical app assessment is considered a major topic which warrants attention This study emphasizes the current standpoint and opportunities for research in this area and boosts additional efforts towards the understanding of this research field

Dominant gray level based K-means algorithm for MRI images

Abstract: Image segmentation is the significant tasks in maximum medical diagnosis tools. In recent years, perfect segmentation of medical images is of the great challenging issue. Maximum investigation in most of the areas exhibit that numerous individuals having brain tumors expired because of authentic circumstance for inaccurate recognition. The traditional K-Means algorithm suffers from numerous issue which results in less accurate segmentation, therefore an efficient approach need to be introduced. In this regard, the proposed methodology focused on the MRI medical images for segmentation. Dissimilar to the existing approaches, in this proposed approach a novel K-Means algorithm is introduced by means of incorporating the utmost dominant gray level of the image. This paper addressed the issue of arbitrarily selecting k no of pixels using dominant gray level of the image. The experimental consequences of the proposed approach showed that it has better performance in terms of the images when compared to the traditional K-Means approach.

Fog computing in health: A systematic literature review

Abstract: Currently, technology greatly benefits the area of healthcare. Modern computers can quickly process a large volume of patient health records. Due to recent advances in the area of Internet of Things and healthcare, patient data can be dispersed in multiple locations. As a result, scientists have been proposing solutions based on Cloud Computing to manage healthcare data. However, suchs solutions present challenges regarding access latency, context-awareness, and large volumes of data. There is an increased probability of processing and transmission errors are more likely to occur as health data sets become larger and more complex. In this context, Fog Computing presents itself as an alternative to reduce health data management complexity, consequently increasing its reliability. To that end, it is important to comprehend the associated challenges before defining a Fog Computing-based architecture to manage healthcare data. This article presents a systematic literature review of fog computing being applied to healthcare area. We propose a taxonomy to explore the open issues and most important challenges on these fields of study. We selected 1070 scientific articles published in the last 10 years, filtering the 44 most significant works for an in-depth analysis. We found that there is several challenges to be addressed such as interoperability, privacy, security, data processing, management of resources and Big Data issues. Also, our contribution include developing a taxonomy for the Fog Computing and healthcare fields of study and finding out challenges and open questions of this area.

User-centred design and evaluation of a tele-operated echocardiography robot

Abstract: We present the collected findings of a user-centred approach for developing a tele-operated robot for remote echocardiography examinations. During the three-year development of the robot, we involved users in all development stages of the robot, to increase the usability of the system for the doctors. For requirement compilation, we conducted a literature review, observed two traditional examinations, arranged focus groups with doctors and patients, and conducted two online surveys. During the development of the robot, we regularly involved doctors in usability tests to receive feedback from them on the user interface for the robot and on the robot’s hardware. For evaluation of the robot, we conducted two eye tracking studies. In the first study, doctors executed a traditional echocardiography examination. In the second study, the doctors conducted a remote examination with our robot. The results of the studies show that all doctors were able to successfully complete a correct ultrasonography examination with the tele-operated robot. In comparison to a traditional examination, the doctors on average only need a short amount of additional time to successfully examine a patient when using our remote echocardiography robot. The results also show that the doctors fixate considerably more often, but with shorter fixation times, on the USG screen in the traditional examination compared to the remote examination. We found further that some of the user-centred design methods we applied had to be adjusted to the clinical context and the hectic schedule of the doctors. Overall, our experience and results suggest that the usage of user-centred design methodology is well suited for developing medical robots and leads to a usable product that meets the end users’ needs.

Assessing the impact of parameters tuning in ensemble based breast Cancer classification

Abstract: Breast cancer is one of the major causes of death among women. Different decision support systems were proposed to assist oncologists to accurately diagnose their patients. These decision support systems mainly used classification techniques to categorize the diagnosis into Malign or Benign tumors. Given that no consensus has been reached on the classifier that can perform best in all circumstances, ensemble-based classification, which classifies patients by combining more than one single classification technique, has recently been investigated. In this paper, heterogeneous ensembles based on three well-known machine learning techniques (support vector machines, multilayer perceptron, and decision trees) were developed and evaluated by investigating the impact of parameter values of the ensemble members on classification performance. In particular, we investigate three parameters tuning techniques: Grid Search (GS), Particle Swarm Optimization (PSO) and the default parameters of the Weka Tool to evaluate whether setting ensemble parameters permits more accurate classification in breast cancer over four datasets obtained from the Machine Learning repository. The heterogeneous ensembles of this study were built using the majority voting technique as a combination rule. The overall results obtained suggest that: (1) Using GS or PSO techniques for single techniques provide more accurate classification; (2) In general, ensembles generate more accurate classification than their single techniques regardless of the optimization techniques used. (3) Heterogeneous ensembles based on optimized single classifiers generate better results than the Uniform Configuration of Weka (UC-WEKA) ensembles, and (4) PSO and GS slightly have the same impact on the performances of ensembles.

HomeSense: Design of an ambient home health and wellness monitoring platform for older adults

Abstract: The unprecedented rise in the population of older adults and the number of seniors living with and managing chronic conditions are straining our institutional health care systems leading to reduced care quality and unmanageable cost increases. At the same time, an overwhelming majority of older adults express a strong desire to age in place in their communities. Ambient home sensing presents an opportunity to reduce healthcare costs by facilitating older adults’ ability to age-in-place in more familiar, less restrictive, and less expensive environments. Further, ambient home sensing tools have the potential to extend the health care work force and enhance health care quality/outcomes by facilitating remote patient monitoring as well as early intervention and prevention against adverse events – all while catering to older adults’ preference to live at home. Despite their potential, there is limited research at present about the benefits of ambient sensing systems installed in private homes, and older adults’ response to them. This paper describes a pilot ambient home sensing project, HomeSense, actively deployed in the homes of older adults residing in The Villages, Florida.

IDSS-based Two stage classification of brain tumor using SVM

Abstract: The computer and image processing has a significant role in detecting tumor area. The decision support systems for human brain MR images are essentially encouraged with the requirement of attaining maximal achievable efficiency and the motivation of the approach which is to enhance the performance of Computer-Aided Diagnosis (CAD) system to detect a tumor in the human brain. Even though numerous support systems have been introduced in the past, this is still an open problem seeking for an accurate and robust decision support system. The Interactive Diagnosis Support System (IDSS) approach has addressed the limitations of nonillumination and low contrast of a brain tumor MR image that influences the procedure of accurate image classification. Thus, the IDSS is implemented in three phases namely image preprocessing for enhancing non-illuminated features, feature extraction and image classification which is accomplished using two-stage interactive SVM Classification. The local binary patterns are detected in the feature extraction for accurate classification of usual and unusual brain MR Images. The experimental outcomes for this approach are carried out using MATLAB R2016a and evaluated using the brain images downloaded from the Internet. The performance metrics such as structured similarity index, sensitivity, specificity and accuracy were used to assess the IDSS-based tumor classification system. When compared with the traditional classifiers such as ANFIS, Backpropagation and K-NN, the IDSS approach has significant brain tumor classification accuracy.

Leveraging FHIR to Integrate Activity Data with Electronic Health Record

Abstract: Health technology wearables can quantify and visualize an individual’s physical activity and any other associated data (e.g., vitals, calories, steps, distance, etc.) across time. Currently, this data is communicated to the wearable’s organization data repositories and is accessible to the individual via a mobile application. However, the data cannot be integrated with the individual’s EHR due to structural and semantic interoperability issues and experts relying on EHRs don’t have a complete view of the individual’s health, activity data along with other health records, to provide better healthcare outcomes. This issue is due to the inability of the existing healthcare standards to capture and share the activity and its associated data with any healthcare information systems, such as an EHR. The goal of this research is to addresses this issue by leveraging the HL7 FHIR standard to design an interoperable entity that will allow us to integrate activity and its associated data with an EHR. The research design is implemented using the HL7 FHIR Java-based implementation, REST web service, OpenEMR, and tested using widely used wearables.

Audio-visual stimulation based emotion classification by correlated EEG channels

Abstract: In this paper, a new channel selection technique is presented for emotion classification by electroencephalography (EEG) signals. Audio-visual stimulation is used to generate emotions at the time of experiment. After recording of EEG signals, feature extraction and classification has been applied to classify the emotions (happy, angry, sad and relaxing). The main highlights of the study include: 1) identification/characterization of audio-visual stimulation which generate harmful emotions and 2) proposed approach to reduce the number of EEG channels for emotion classification. Intention behind identification of audio-visual stimulation (video) responsible for harmful emotions like sad and anger is to control their access over social media and another public platform. EEG channels are selected on the basis of their activation probability, calculated from the correlation matrix of EEG channels. Three types of features are extracted from EEG signals, time domain, frequency domain and entropy based. After feature extraction three different algorithms, support vector machine (SVM), artificial neural network (ANN) and naive bayes (NB) are used to classify the emotions. This study is conducted over the DEAP (Database for emotion analysis using Physiological signals) database of EEG signals recorded at different emotional states of several subjects. To compare performance after channel selection, parameters like accuracy, average precision and average recall are calculated. After result analysis, ANN is found as best classifier with 97.74% average accuracy. Among listed features, entropy-based features are found as best features with 90.53% average accuracy.

Machine learning models for the prediction of acuity and variability of eye-positioning using features extracted from oculography

Abstract: During the first months of life, babies can be affected by congenital nystagmus, an ocular-motor disease making visual acuity decrease. Electrooculography (EOG) and Infrared-oculography are utilized in order to perform eye-tracking of patients, giving the possibility to extract from the signals several useful features. In the past years, different algorithms were used to perform the detection of events on these features and many researchers studied the relationships between the features and physiological values such as visual acuity and variability of eye-positioning. In this paper, machine learning techniques were used to predict visual acuity and the variability of eye positioning using features extracted from EOG. The EOG of 20 patients was acquired, signals underwent a pre-processing, and some parameters were extracted through a custom-made software. Frequency, amplitude, intensity, nystagmus foveation periods and both amplitude and frequency of baseline oscillation were the features used as input for the algorithms. Knime analytics platform was employed to perform a predictive analysis using Random Forests, Logistic Regression Tree, Gradient boosted tree, K nearest neighbour, Multilayer Perceptron and Support Vector Machine. Finally, some evaluation metrics were computed employing a leave one out cross validation. Considering the coefficient of determination, visual acuity achieved values between 0.67 and 0.85 while variability of eye positioning ranged from 0.62 to 0.79. These results were compared with past analysis with the exact same aims and dataset, obtaining a greater value as regards the variability of eye positioning and comparable results exploiting all the features related to nystagmus as regards the visual acuity. This paper showed the feasibility of a regression analysis performed through machine learning algorithms in detecting relationships among variables related to congenital nystagmus.

An empirical investigation of the adoption of mobile health applications: integrating big data and social media services

Abstract: With the advancement of digital technologies, the mobile healthcare industry aims to enhance health intelligence through delivering transformational digital services. This study integrates knowledge derived from three models of innovation diffusion, privacy calculus, and information systems success with the current studies on technology acceptance literature in the context of mHealth apps. It focuses on the contribution of big data and social media in enhancing mobile health apps and their impact on patients’ behavior and adoption. Through structural equation modeling of 582 questionnaires, this study develops a framework analyzing the impact of data quality, social interactivity, personalization, data risk, and performance risk. The study confirms the association between personalization, data quality, and data risk on the adoption decisions, while it did not find a link between social connectivity and the adoption decision. Theoretically, this paper builds new knowledge on the technology adoption literature by emphasizing digital services in the context of mobile health apps. Practically, this paper can assist the healthcare care industry to re-engineer its traditional business models by delivering enhanced digital services during the design of mobile health apps.

Gut microbiota and artificial intelligence approaches: A scoping review

Abstract: This article aims to provide a thorough overview of the use of Artificial Intelligence (AI) techniques in studying the gut microbiota and its role in the diagnosis and treatment of some important diseases. The association between microbiota and diseases, together with its clinical relevance, is still difficult to interpret. The advances in AI techniques, such as Machine Learning (ML) and Deep Learning (DL), can help clinicians in processing and interpreting these massive data sets. Two research groups have been involved in this Scoping Review, working in two different areas of Europe: Florence and Sarajevo. The papers included in the review describe the use of ML or DL methods applied to the study of human gut microbiota. In total, 1109 papers were considered in this study. After elimination, a final set of 16 articles was considered in the scoping review. Different AI techniques were applied in the reviewed papers. Some papers applied ML, while others applied DL techniques. 11 papers evaluated just different ML algorithms (ranging from one to eight algorithms applied to one dataset). The remaining five papers examined both ML and DL algorithms. The most applied ML algorithm was Random Forest and it also exhibited the best performances.

Heart disease classification using hybridized Ruzzo-Tompa memetic based deep trained Neocognitron neural network

Abstract: According to the survey 17.5 million deaths are happened due to the cardiovascular disease that leads to create heart attack, chest pain and stroke. Based on the survey it clearly concludes that most of the people affected by heart problem that need to be identified in the earlier stage for eliminating the future risk in patient health. The importance of the heart disease detection process helps to create the earlier detection system for identifying heart problem by using machine learning and optimized techniques but the developed forecasting systems are difficult to predict the heart problems in an accurate manner with minimum time. So, hybridized Ruzzo–Tompa memetic based deep trained Neocognitron neural network is introduced to analyze the heart disease related features and predict the heart disease in earlier stage. First, heart disease data has been collected from UCI repository, dimensionality of the data is minimized by hybridized Ruzzo–Tompa memetic approach. After reducing the number of features, that are trained by deep learning approach which analyze the features using maximum number of hidden layers that used to predict heart disease features successfully while making the Neocognitron neural network classification. Further efficiency of the system is evaluated using MATLAB based simulation results.

An integrated custom decision-support computer aided facility management informative system for healthcare facilities and analysis

Abstract: This article presents a Computer Aided Facility Management informative system which can output Key Performance Indicators and quantitative parameters about the analysed healthcare facility. The designed system is a self-sufficient application able to manage and analyse digital plans of hospital buildings with no need of third-party plugins or licenses. The system maps hospital’s inner organisation, destinations of use and environmental comforts giving quantitative, qualitative and graphical reports. The core database is linked to other existing hospital databases, so that the system can act as a central control cockpit. Outputs can be used by top-management and decisional staff as a decision-support tool in order to improve hospital’s structure and organisation and to reduce the major workflow risks. Furthermore, many plug-ins and modules have been developed through the years which can be easily linked to the main application thanks to its REST architecture, and which contribute to a complete analysis and management of the healthcare facilities.

Brain and pancreatic tumor segmentation using SRM and BPNN classification

Abstract: As of late, to enhance the features of serviceability in medical clinic management, medical image processing plays progressive development in conditions of modus operandi and applications. Various techniques are used to diagnosis tumor parts in modern medical image processing with the rising demand in the respective field. In this paper, the detection of the brain tumor and pancreatic tumor using DBCWMF (Decision Based Couple Window Median Filter)algorithm, Statistical region merging (SRM), Cat Swarm Optimization and Scale-invariant feature transform (CSO-SIFT) extraction and classification through Back Propagation Neural Network (BPNN) is presented. DBCWMF works effectively in the preprocessing compared to Median and PGPD filter, segmentation done with SRM algorithm. After that, the feature selection techniques CSO and SIFT are used for detecting the part in tumor images which is affected and final classification through BPNN classification works effectively compared to ANN and AdaBoost classifier. The experimental tested on images from Medical Harvard School database and The Cancer Imaging Archive (TCIA) repository’s database.

Screening of antioxidant and cytotoxic activities of several microalgal extracts with pharmaceutical potential

Abstract: The bioactive molecules from microalgae have important properties such as antioxidant, anticancer, antiviral, antibacterial, antihypertensive, skin regenerative, neuroprotective, sunscreen, and, immunostimulatory effects. Bioactive molecules derived from microalgae is getting intense attention from pharmaceuticals, cosmetics and nutraceuticals industries because of these properties and numerous researches have been done to investigate the role of these bioactive molecules that can enlighten microalgal biotechnology to result in new nature derived pharmaceutical formulations. In this study we investigate antioxidant activities of crude extracts of G. Galdieria sulphuraria, Ettlia carotinosa, Neochloris texensis, Chlorella minutissima, Stichococcus bacillaris, Schizochytrium limacinum, Crypthecodinium cohnii, and Chlorella vulgaris with determining radical scavenging activity (RSA) by DPPH (2,2-diphenyl-1-picrylhydrazyl hydrate radical) method and total phenolic content by Folin-Ciocalteu method. Selected extracts according to their antioxidant activities cytotoxicity was evaluated after exposure to human hepatocellular liver carcinoma cells (HepG2) for 48 h. Antioxidant activities of these species ranged from 89 to 95% RSA (radical scavenging activity) while their phenolic contents were also very high, varied from 41 to 312 mg GAE (gallic acid equivalents)/mg extract. MTT (3-[4,5-dimethylthiazol-2-yl]-2,5 diphenyl tetrazolium bromide) assay also showed microalgae has a potential to be used as a novel therapeutic compound.

Bench to bedside: The technology adoption pathway in healthcare

Abstract: New technologies have the potential to revolutionize the way we manage health and wellbeing now and in the future. But often seen as expensive and difficult to implement, the challenge is to identify the best technology to deliver real patient benefit and support its rapid adoption to help address the funding difficulties faced by all modern healthcare systems. In this paper we consider the traditional linear model of the technology adoption pathway as it pertains to healthcare, look at common challenges faced traversing this path and suggest solutions. In so doing, we recognise the limitations of the linear model and describe our version of a more realistic, non-linear model. Throughout, we will be looking at the key role of the Clinical Engineer to successful healthcare technology adoption based on our experience of supporting medical device products through to adoption and present the key lessons we learnt along the way.