A hybrid cancer prediction based on multi-omics data and reinforcement learning state action reward state action (SARSA).

These days, the ratio of cancer diseases among patients has been growing day by day. Recently, many cancer cases have been reported in different clinical hospitals. Many machine learning algorithms have been suggested in the literature to predict cancer diseases with the same class types based on trained and test data. However, there are many research rooms available for further research. In this paper, the studies look into the different types of cancer by analyzing, classifying, and processing the multi-omics dataset in a fog cloud network. Based on SARSA on-policy and multi-omics workload learning, made possible by reinforcement learning, the study made new hybrid cancer detection schemes. It consists of different layers, such as clinical data collection via laboratories and tool processes (biopsy, colonoscopy, and mammography) at the distributed omics-based clinics in the network. The study considers the different cancer classes such as carcinomas, sarcomas, leukemias, and lymphomas with their types in work and processes them using the multi-omics distributed clinics in work. In order to solve the problem, the study presents omics cancer workload reinforcement learning state action reward state action "SARSA" (OCWLS) schemes, which are made up of an on-policy learning scheme on different parameters like states, actions, timestamps, reward, accuracy, and processing time constraints. The goal is to process multiple cancer classes and workload feature matching while reducing the time it takes to process in clinical hospitals that are spread out. Simulation results show that OCWLS is better than other machine learning methods regarding+ processing time, extracting features from multiple classes of cancer, and matching in the system.

Serious Games for Executive Functions Training for Adults with Intellectual Disability: Overview.

(1) Background: Throughout the history of medical and psychology practice, specialists have worked to improve the quality of treatment and rehabilitation, which has led to the emergence of concepts such as serious games. These tools focus on different areas of intervention procedures, one of which is to help people with intellectual disability (ID). Individuals with ID have problems with executive functions (EFs), which are related to adaptive functioning. Recent studies showed that serious games positively impact cognitive, social, and communication skills in people with ID. The purpose of this study is to analyze the solutions that have been found in EF training for adults with ID in recent years, evaluating them with a number of key parameters and identifying the features and possible problems in the further development of our system. (2) Methods: A review was conducted starting with 573 articles in English related to serious games and selected from studies that had been published since 2015. Finally, 10 were examined in detail as they focused on EFs in adults with ID. They were searched in seven major databases ("Association for Computing Machinery" (ACM), IEEE Xplore database, DBLP computer science bibliography, Google Scholar, PubMed, SCOPUS, and PsycInfo). (3) Results: It was determined that the most frequent EFs referred to in the studies analyzed were planning and decision-making, followed by working memory and social cognition, behavioral regulation, flexibility, and inhibition capacity. The basic approach to the creation of support systems was also analyzed in terms of technical and program execution. The trend results' analysis evidenced improvements in EFs, even though they were not significant. This comprehensive technique enabled the identification of the main features and aspects to be taken into account for further development of our system.

Are AI systems biased against the poor? A machine learning analysis using Word2Vec and GloVe embeddings.

Among the myriad of technical approaches and abstract guidelines proposed to the topic of AI bias, there has been an urgent call to translate the principle of fairness into the operational AI reality with the involvement of social sciences specialists to analyse the context of specific types of bias, since there is not a generalizable solution. This article offers an interdisciplinary contribution to the topic of AI and societal bias, in particular against the poor, providing a conceptual framework of the issue and a tailor-made model from which meaningful data are obtained using Natural Language Processing word vectors in pretrained Google Word2Vec, Twitter and Wikipedia GloVe word embeddings. The results of the study offer the first set of data that evidences the existence of bias against the poor and suggest that Google Word2vec shows a higher degree of bias when the terms are related to beliefs, whereas bias is higher in Twitter GloVe when the terms express behaviour. This article contributes to the body of work on bias, both from and AI and a social sciences perspective, by providing evidence of a transversal aggravating factor for historical types of discrimination. The evidence of bias against the poor also has important consequences in terms of human development, since it often leads to discrimination, which constitutes an obstacle for the effectiveness of poverty reduction policies.

Predicting Genetic Disorder and Types of Disorder Using Chain Classifier Approach.

Genetic disorders are the result of mutation in the deoxyribonucleic acid (DNA) sequence which can be developed or inherited from parents. Such mutations may lead to fatal diseases such as Alzheimer's, cancer, Hemochromatosis, etc. Recently, the use of artificial intelligence-based methods has shown superb success in the prediction and prognosis of different diseases. The potential of such methods can be utilized to predict genetic disorders at an early stage using the genome data for timely treatment. This study focuses on the multi-label multi-class problem and makes two major contributions to genetic disorder prediction. A novel feature engineering approach is proposed where the class probabilities from an extra tree (ET) and random forest (RF) are joined to make a feature set for model training. Secondly, the study utilizes the classifier chain approach where multiple classifiers are joined in a chain and the predictions from all the preceding classifiers are used by the conceding classifiers to make the final prediction. Because of the multi-label multi-class data, macro accuracy, Hamming loss, and α-evaluation score are used to evaluate the performance. Results suggest that extreme gradient boosting (XGB) produces the best scores with a 92% α-evaluation score and a 84% macro accuracy score. The performance of XGB is much better than state-of-the-art approaches, in terms of both performance and computational complexity.

Transfer Learning for Alzheimer's Disease through Neuroimaging Biomarkers: A Systematic Review.

Alzheimer's disease (AD) is a remarkable challenge for healthcare in the 21st century. Since 2017, deep learning models with transfer learning approaches have been gaining recognition in AD detection, and progression prediction by using neuroimaging biomarkers. This paper presents a systematic review of the current state of early AD detection by using deep learning models with transfer learning and neuroimaging biomarkers. Five databases were used and the results before screening report 215 studies published between 2010 and 2020. After screening, 13 studies met the inclusion criteria. We noted that the maximum accuracy achieved to date for AD classification is 98.20% by using the combination of 3D convolutional networks and local transfer learning, and that for the prognostic prediction of AD is 87.78% by using pre-trained 3D convolutional network-based architectures. The results show that transfer learning helps researchers in developing a more accurate system for the early diagnosis of AD. However, there is a need to consider some points in future research, such as improving the accuracy of the prognostic prediction of AD, exploring additional biomarkers such as tau-PET and amyloid-PET to understand highly discriminative feature representation to separate similar brain patterns, managing the size of the datasets due to the limited availability.

Reviewing Mobile Apps to Control Heart Rate in Literature and Virtual Stores.

BACKGROUND: Information and communications technologies are transforming our social interactions and life-styles. One of the most promising applications of information technology is healthcare and wellness management that characterized by early detection of conditions, prevention, and long-term healthcare management. OBJECTIVE: The main purpose of this document is to do a study, first about the actual literature about mobile phone applications to measure and control heart-rate and second a study about these applications themselves, analyzing the different app stores more popular nowadays, Google Play Store and iTunes (for Android and iOS devices respectively). METHODS: The Web portals and databases that were used to perform the searches are IEEE Xplore, National Center for Biotechnology Information, Springer, ResearchGate, Science Direct and Scopus, taking into account the date of publication from 2010 to 2018, publications in English and Spanish. RESULTS: 40 relevant papers have been found related to mobile phone apps to measure and control heart rate. The results show that of a total of 400 applications found 61.25% of them are in the Play Store (Android systems) and the remaining 38.75% were found in the iTunes Store (iOS systems). CONCLUSIONS: From the review of the research articles analyzed, it can be said that the most applications found are for Android devices. They occupy 76.53% of the world mobile phone market, while iOS only owns 18.97%.

Classification of pressure ulcer tissues with 3D convolutional neural network.

A 3D convolution neural network (CNN) of deep learning architecture is supplied with essential visual features to accurately classify and segment granulation, necrotic eschar, and slough tissues in pressure ulcer color images. After finding a region of interest (ROI), the features are extracted from both the original and convolved with a pre-selected Gaussian kernel 3D HSI images, combined with first-order models of current and prior visual appearance. The models approximate empirical marginal probability distributions of voxel-wise signals with linear combinations of discrete Gaussians (LCDG). The framework was trained and tested on 193 color pressure ulcer images. The classification accuracy and robustness were evaluated using the Dice similarity coefficient (DSC), the percentage area distance (PAD), and the area under the ROC curve (AUC). The obtained preliminary DSC of 92%, PAD of 13%, and AUC of 95% are promising. Graphical Abstract The Classification of Pressure Ulcer Tissues Based on 3D Convolutional Neural Network.

Comparison of background EEG activity of different groups of patients with idiopathic epilepsy using Shannon spectral entropy and cluster-based permutation statistical testing.

Idiopathic epilepsy is characterized by generalized seizures with no apparent cause. One of its main problems is the lack of biomarkers to monitor the evolution of patients. The only tools they can use are limited to inspecting the amount of seizures during previous periods of time and assessing the existence of interictal discharges. As a result, there is a need for improving the tools to assist the diagnosis and follow up of these patients. The goal of the present study is to compare and find a way to differentiate between two groups of patients suffering from idiopathic epilepsy, one group that could be followed-up by means of specific electroencephalographic (EEG) signatures (intercritical activity present), and another one that could not due to the absence of these markers. To do that, we analyzed the background EEG activity of each in the absence of seizures and epileptic intercritical activity. We used the Shannon spectral entropy (SSE) as a metric to discriminate between the two groups and performed permutation-based statistical tests to detect the set of frequencies that show significant differences. By constraining the spectral entropy estimation to the [6.25-12.89) Hz range, we detect statistical differences (at below 0.05 alpha-level) between both types of epileptic patients at all available recording channels. Interestingly, entropy values follow a trend that is inversely related to the elapsed time from the last seizure. Indeed, this trend shows asymptotical convergence to the SSE values measured in a group of healthy subjects, which present SSE values lower than any of the two groups of patients. All these results suggest that the SSE, measured in a specific range of frequencies, could serve to follow up the evolution of patients suffering from idiopathic epilepsy. Future studies remain to be conducted in order to assess the predictive value of this approach for the anticipation of seizures.

Dual System for Enhancing Cognitive Abilities of Children with ADHD Using Leap Motion and eye-Tracking Technologies.

Attention Deficit Hyperactivity Disorder (ADHD) is a brain disorder marked by an ongoing pattern of inattention and/or hyperactivity-impulsivity that affects with development or functioning. It affects 3-5% of all American and European children. The objective of this paper is to develop and test a dual system for the rehabilitation of cognitive functions in children with ADHD. A technological platform has been developed using the ". NET framework", which makes use of two physiological sensors, -an eye-tracker and a hand gesture recognition sensor- in order to provide children with the opportunity to develop their learning and attention skills. The two physiological sensors we utilized for the development are the Tobii X1 Light Eye Tracker and the Leap Motion. SUS and QUIS questionnaires have been carried out. 19 users tested the system and the average age was 10.88 years (SD = 3.14). The results obtained after tests were performed were quite positive and hopeful. The learning of the users caused by the system and the interfaces item got a high punctuation with a mean of 7.34 (SD = 1.06) for SUS questionnaire and 7.73 (SD = 0.6) for QUIS questionnaire. We didn't find differences between boys and girls. The developed multimodal rehabilitation system can help to children with attention deficit and learning issues. Moreover, the teachers may utilize this system to track the progression of their students and see their behavior.

A New mHealth App for Monitoring and Awareness of Healthy Eating: Development and User Evaluation by Spanish Users.

Modern-day society has moved towards a more sedentary lifestyle. Advances in technology and changes in habits in our daily lives have led a large part of the population towards a spiralling sedentary lifestyle and obesity. The main objective of this work is to develop and subsequently assess a mobile app, named DietApp, that provides advice about obtaining a healthy diet according to age, clinical history and physical condition. DietApp has been developed for iOS and Android systems, and a survey comprising 7 simple questions enabled the app to be evaluated on a user level by taking into account aspects such as its usefulness and ease of use. DietApp was assessed by 150 Spanish individuals between 18 and 69 years of age, and 84% of them thought it was easy to use. 80% of users also considered the dietary suggestions provided by the app to be very useful while 62% were of the opinion that it is very useful in general. All of them would recommend the app to other users. During the six months when the app was used, any dietary excess or shortcomings were corrected in 72% of those interviewed. A mobile app has been created that is easy to use and attractive, providing personalised suggestions according to illness that are useful for the individual.

Proposing Telecardiology Services on Cloud for Different Medical Institutions: A Model of Reference.

INTRODUCTION: For a cloud-based telecardiology solution to be established in any scenario, it is necessary to ensure optimum levels of security, as patient's data will not be in the same place from where access is gained. The main objective of this article is to present a secure, cloud-based solution for a telecardiology service in different scenarios: a hospital, a health center in a city, and a group of health centers in a rural area. METHODS: iCanCloud software is used to simulate the scenarios. The first scenario will be a city hospital with over 220,000 patients at its emergency services, and ∼1 million outpatient consultations. For the health center in a city, it serves ∼107,000 medical consultations and 16,700 pediatric consultations/year. In the last scenario, a group of health centers in a rural area serve an average 437.08 consultations/month and around 15.6 a day. RESULTS: Each one of the solutions proposed shares common features including the following: secure authentication through smart cards, the use of StorageGRID technology, and load balancers. For all cases, the cloud is private and the estimated price of the solution would cost around 450 €/month. CONCLUSIONS: Thanks to the research conducted in this work, it has been possible to provide an adapted solution in the form of a telecardiology service for a hospital, city health center, and rural health centers that offer security, privacy, and robustness, and is also optimum for a large number of cloud requests.

Big Data in Health: a Literature Review from the Year 2005.

The information stored in healthcare systems has increased over the last ten years, leading it to be considered Big Data. There is a wealth of health information ready to be analysed. However, the sheer volume raises a challenge for traditional methods. The aim of this article is to conduct a cutting-edge study on Big Data in healthcare from 2005 to the present. This literature review will help researchers to know how Big Data has developed in the health industry and open up new avenues for research. Information searches have been made on various scientific databases such as Pubmed, Science Direct, Scopus and Web of Science for Big Data in healthcare. The search criteria were "Big Data" and "health" with a date range from 2005 to the present. A total of 9724 articles were found on the databases. 9515 articles were discarded as duplicates or for not having a title of interest to the study. 209 articles were read, with the resulting decision that 46 were useful for this study. 52.6 % of the articles used were found in Science Direct, 23.7 % in Pubmed, 22.1 % through Scopus and the remaining 2.6 % through the Web of Science. Big Data has undergone extremely high growth since 2011 and its use is becoming compulsory in developed nations and in an increasing number of developing nations. Big Data is a step forward and a cost reducer for public and private healthcare.

Monitoring and Follow-up of Chronic Heart Failure: a Literature Review of eHealth Applications and Systems.

In developed countries heart failure is one of the most important causes of death, followed closely by strokes and other cerebrovascular diseases. It is one of the major healthcare issues in terms of increasing number of patients, rate of hospitalizations and costs. The main aim of this paper is to present telemedicine applications for monitoring and follow-up of heart failure and to show how these systems can help reduce costs of administering heart failure. The search for e-health applications and systems in the field of telemonitoring of heart failure was pursued in IEEE Xplore, Science Direct, PubMed and Scopus systems between 2005 and the present time. This search was conducted between May and June 2015, and the articles deemed to be of most interest about treatment, prevention, self-empowerment and stabilization of patients were selected. Over 100 articles about telemonitoring of heart failure have been found in the literature reviewed since 2005, although the most interesting ones have been selected from the scientific standpoint. Many of them show that telemonitoring of patients with a high risk of heart failure is a measure that might help to reduce the risk of suffering from the disease. Following the review conducted, in can be stated that via the research articles analysed that telemonitoring systems can help to reduce the costs of administering heart failure and result in less re-hospitalization of patients.

Security Recommendations for mHealth Apps: Elaboration of a Developer's Guide.

Being the third fastest-growing app category behind games and utilities, mHealth apps are changing the healthcare model, as medicine today involves the data they compile and analyse, information known as Big Data. However, the majority of apps are lacking in security when gathering and dealing with the information, which becomes a serious problem. This article presents a guide regarding security solution, intended to be of great use for developers of mHealth apps. In August 2015 current mobile health apps were sought out in virtual stores such as Android Google Play, Apple iTunes App Store etc., in order to classify them in terms of usefulness. After this search, the most widespread weaknesses in the field of security in the development of these mobile apps were examined, based on sources such as the "OWASP Mobile Security Project, the initiative recently launched by the Office of Civil Rights (OCR), and other articles of scientific interest. An informative, elemental guide has been created for the development of mHealth apps. It includes information about elements of security and its implementation on different levels for all types of mobile health apps based on the data that each app manipulates, the associated calculated risk as a result of the likelihood of occurrence and the threat level resulting from its vulnerabilities - high level (apps for monitoring, diagnosis, treatment and care) from 6 ≤ 9, medium level (calculator, localizer and alarm) from 3 ≤ 6 and low level (informative and educational apps) from 0 ≤ 3. The guide aims to guarantee and facilitate security measures in the development of mobile health applications by programmers unconnected to the ITC and professional health areas.

Development, Technical, and User Evaluation of a Web Mobile Application for Self-Control of Diabetes.

OBJECTIVE: The main objective of this research was to develop and evaluate a Web-based mobile application (app) known as "Diario Diabetes" on both a technical and user level, by means of which individuals with diabetes may monitor their illness easily at any time and in any place using any device that has Internet access. METHODS: The technologies used to develop the app were HTML, CSS, JavaScript, PHP, and MySQL, all of which are an open source. Once the app was developed, it was evaluated on a technical level (by measuring loading times) and on a user level, through a survey. RESULTS: Different loading times for the application were measured, with it being noted that under no circumstances does this exceed 2 s. Usability was evaluated by 150 users who initially used the application. A majority (71%) of users used a PC to access the app, 83% considered the app's design to be attractive, 67% considered the tasks to be very useful, and 67% found it very easy to use. CONCLUSIONS: Although applications exist for controlling diabetes both at mobile virtual shops or on a research level, our app may help to improve the administration of these types of patients and they are the ones who will ultimately opt for one or the other. According to the results obtained, we can state that all users would recommend the app's use to other users.

Patient prognosis based on feature extraction, selection and classification of EEG periodic activity.

Periodic activity in electroencephalography (PA-EEG) is shown as comprising a series of repetitive wave patterns that may appear in different cerebral regions and are due to many different pathologies. The diagnosis based on PA-EEG is an arduous task for experts in Clinical Neurophysiology, being mainly based on other clinical features of patients. Considering this difficulty in the diagnosis it is also very complicated to establish the prognosis of patients who present PA-EEG. The goal of this paper is to propose a method capable of determining patient prognosis based on characteristics of the PA-EEG activity. The approach, based on a parallel classification architecture and a majority vote system has proven successful by obtaining a success rate of 81.94% in the classification of patient prognosis of our database.

EEG artifact removal-state-of-the-art and guidelines.

This paper presents an extensive review on the artifact removal algorithms used to remove the main sources of interference encountered in the electroencephalogram (EEG), specifically ocular, muscular and cardiac artifacts. We first introduce background knowledge on the characteristics of EEG activity, of the artifacts and of the EEG measurement model. Then, we present algorithms commonly employed in the literature and describe their key features. Lastly, principally on the basis of the results provided by various researchers, but also supported by our own experience, we compare the state-of-the-art methods in terms of reported performance, and provide guidelines on how to choose a suitable artifact removal algorithm for a given scenario. With this review we have concluded that, without prior knowledge of the recorded EEG signal or the contaminants, the safest approach is to correct the measured EEG using independent component analysis-to be precise, an algorithm based on second-order statistics such as second-order blind identification (SOBI). Other effective alternatives include extended information maximization (InfoMax) and an adaptive mixture of independent component analyzers (AMICA), based on higher order statistics. All of these algorithms have proved particularly effective with simulations and, more importantly, with data collected in controlled recording conditions. Moreover, whenever prior knowledge is available, then a constrained form of the chosen method should be used in order to incorporate such additional information. Finally, since which algorithm is the best performing is highly dependent on the type of the EEG signal, the artifacts and the signal to contaminant ratio, we believe that the optimal method for removing artifacts from the EEG consists in combining more than one algorithm to correct the signal using multiple processing stages, even though this is an option largely unexplored by researchers in the area.

Eye/head tracking technology to improve HCI with iPad applications.

In order to improve human computer interaction (HCI) for people with special needs, this paper presents an alternative form of interaction, which uses the iPad's front camera and eye/head tracking technology. With this functional nature/capability operating in the background, the user can control already developed or new applications for the iPad by moving their eyes and/or head. There are many techniques, which are currently used to detect facial features, such as eyes or even the face itself. Open source bookstores exist for such purpose, such as OpenCV, which enable very reliable and accurate detection algorithms to be applied, such as Haar Cascade using very high-level programming. All processing is undertaken in real time, and it is therefore important to pay close attention to the use of limited resources (processing capacity) of devices, such as the iPad. The system was validated in tests involving 22 users of different ages and characteristics (people with dark and light-colored eyes and with/without glasses). These tests are performed to assess user/device interaction and to ascertain whether it works properly. The system obtained an accuracy of between 60% and 100% in the three test exercises taken into consideration. The results showed that the Haar Cascade had a significant effect by detecting faces in 100% of cases, unlike eyes and the pupil where interference (light and shade) evidenced less effectiveness. In addition to ascertaining the effectiveness of the system via these exercises, the demo application has also helped to show that user constraints need not affect the enjoyment and use of a particular type of technology. In short, the results obtained are encouraging and these systems may continue to be developed if extended and updated in the future.

Technological solution for determining gait parameters using pressure sensors: a case study of multiple sclerosis patients.

This paper describes a study dealing with a technological solution to measure gait quality in people suffering from multiple sclerosis (MS) by selecting objective parameters that focus on their step. Android mobile technology, online services and four wireless pressure sensors are used in concert for this purpose. The objective of this work is the early detection of deterioration of the patient so that a physician can quickly intervene. Tests were carried out on a group of 8 persons with MS, and these results were compared with a control a group of 6 healthy participants. The results indicated a statistical difference in 7 of 40 general step features, with a minimum σ=0.013 and a maximum σ=0.029. These characteristics showed differences between first and fifth metatarsals for each group. It was concluded that these parameters can be used to evaluate gait degeneration in people with MS and that further information could be obtained from measurements with sensors to monitor activities such as bending and inertial sensors.

Shoe-integrated sensors in physical rehabilitation.

This paper presents a shoe-integrated sensor device which collects objective information concerning the gait quality in patients' physical rehabilitation. It involves four pressure sensors, two bending sensors, an ultrasonic sensor and a 9dof IMU, an Inertial Measurement Unit with three accelerometers, three gyroscopes and three magnetometers. The device includes a SDRAMPS with the aim of storing the information for long periods of time. The collected data can be sent to the server for later visualization by the specialist and the patient on a web platform. An interface shows the data in real time, allowing it to verify the connections and to check different movements.