Hybrid Classical-Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays

Cardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication. Based on pre-trained DenseNet-121, we designed hybrid classical-quantum (CQ) transfer learning models to detect cardiomegaly in CXRs. Using Qiskit and PennyLane, we integrated a parameterized quantum circuit into a classic network implemented in PyTorch. We mined the CheXpert public repository to create a balanced dataset with 2436 posteroanterior CXRs from different patients distributed between cardiomegaly and the control. Using k-fold cross-validation, the CQ models were trained using a state vector simulator. The normalized global effective dimension allowed us to compare the trainability in the CQ models run on Qiskit. For prediction, ROC AUC scores up to 0.93 and accuracies up to 0.87 were achieved for several CQ models, rivaling the classical-classical (CC) model used as a reference. A trustworthy Grad-CAM++ heatmap with a hot zone covering the heart was visualized more often with the QC option than that with the CC option (94% vs. 61%, p < 0.001), which may boost the rate of acceptance by health professionals.

COVID-CheXNet: hybrid deep learning framework for identifying COVID-19 virus in chest X-rays images

The outbreaks of Coronavirus (COVID-19) epidemic have increased the pressure on healthcare and medical systems worldwide. The timely diagnosis of infected patients is a critical step to limit the spread of the COVID-19 epidemic. The chest radiography imaging has shown to be an effective screening technique in diagnosing the COVID-19 epidemic. To reduce the pressure on radiologists and control of the epidemic, fast and accurate a hybrid deep learning framework for diagnosing COVID-19 virus in chest X-ray images is developed and termed as the COVID-CheXNet system. First, the contrast of the X-ray image was enhanced and the noise level was reduced using the contrast-limited adaptive histogram equalization and Butterworth bandpass filter, respectively. This was followed by fusing the results obtained from two different pre-trained deep learning models based on the incorporation of a ResNet34 and high-resolution network model trained using a large-scale dataset. Herein, the parallel architecture was considered, which provides radiologists with a high degree of confidence to discriminate between the healthy and COVID-19 infected people. The proposed COVID-CheXNet system has managed to correctly and accurately diagnose the COVID-19 patients with a detection accuracy rate of 99.99%, sensitivity of 99.98%, specificity of 100%, precision of 100%, F1-score of 99.99%, MSE of 0.011%, and RMSE of 0.012% using the weighted sum rule at the score-level. The efficiency and usefulness of the proposed COVID-CheXNet system are established along with the possibility of using it in real clinical centers for fast diagnosis and treatment supplement, with less than 2 s per image to get the prediction result.

Design of intelligent monitoring of loneliness in the elderly using a serverless architecture with real-time communication API

BACKGROUND

Loneliness and social isolation are recognized as critical public health issues. Older people are at greater risk of loneliness and social isolation as they deal with things like living alone, loss of family or friends, chronic illness, and hearing loss. Loneliness increases a person's risk of premature death from all causes, including dementia, heart disease, and stroke. To address these issues, the inclusion of technological platforms and the use of commercial monitoring devices are vastly increasing in healthcare and elderly care.

OBJECTIVE

The objective of this study is to design and develop a loneliness monitor serverless architecture to obtain real-time data from commercial activity wristbands through an Application Programming Interface.

METHODS

For the design and development of the architecture, the Amazon Web Services platform has been used. To monitor loneliness, the Fitbit Charge 5 bracelet was selected. Through the web Application Programming Interface offered by the AWS Lambda service, the data is obtained and stored in AWS services with an automated frequency thanks to the event bridge.

RESULTS

In the pilot stage in which the system is, it is showing great possibilities in the ease of collecting data and programming the sampling frequency. Once the request is made, the data is automatically analyzed to monitor loneliness.

CONCLUSION

The proposed architecture shows great potential for easy data collection, analysis, security, personalization, real-time inference, and scalability of sensors and actuators in the future. It has powerful benefits to apply in the health sector and reduces cases of depression and loneliness.

Natural language processing analysis applied to COVID-19 open-text opinions using a distilBERT model for sentiment categorization

COVID-19 is a disease that affects the quality of life in all aspects. However, the government policy applied in 2020 impacted the lifestyle of the whole world. In this sense, the study of sentiments of people in different countries is a very important task to face future challenges related to lockdown caused by a virus. To contribute to this objective, we have proposed a natural language processing model with the aim to detect positive and negative feelings in open-text answers obtained from a survey in pandemic times. We have proposed a distilBERT transformer model to carry out this task. We have used three approaches to perform a comparison, obtaining for our best model the following average metrics: Accuracy: 0.823, Precision: 0.826, Recall: 0.793 and F1 Score: 0.803.

Novel complex-valued deep learning applied to automatic classification of heart sounds

Introduction

Cardiovascular disease (CVD) is a problem facing governments around the world. Early detection saves the healthcare system thousands of dollars by allowing prevention and avoiding costly treatments when the disease has progressed to advanced stages. According to the World Health Organization (WHO), cardiovascular diseases represent the leading cause of mortality worldwide (WHO, 2019). That is why, we have decided to develop novel artificial intelligence models for the detection of heart disease, with accuracies that allow us to put the obtained algorithms into production. The revolution of artificial intelligence allows the application Deep Learning techniques of two-dimensional images in the domain of both real numbers and complex value numbers, as classifiers of heart sounds, for the detection of normality or abnormality in the functioning of the heart.

Purpose

In the present work, we propose the comparison of a novel 2D convolutional neural network (CNN) algorithm in the domain of complex value numbers with its counterpart in the domain of real numbers for the automatic classification of heart sounds into normal or abnormal.

Material

The database we decided to use for our research is Pascal, which has audio files of cardiac activity, distributed in 351 normal sounds and 129 pathological sounds.

Methods

The following steps were applied to get the objectives of our work: 1) automatic segmentation of a single heartbeat, 2) conversion of the segmented sound into its associated image scalogram using the Hilbert transform, 3) classification of the sounds into normal and abnormal using the proposed algorithms, and 4) measurement and comparison of the results obtained by performing a two-tailed t-student hypothesis test and cross-validation.

Results

We present a comparative table between the two proposed models, finding that Accuracy, F1 Score, Precision and Recall metrics obtained using complex-valued convolution networks present significant improvements compared with the real valued one. The following table show us the obtained numbers.

For all cases, the t-student test shows us p-values less than 0.05%, giving statistical evidence that the means are significantly different between the two proposed models. Besides, in all cases, the performance of the Complex-valued model is better compared with the Real-valued one.

Conclusion

Complex-valued neural networks propose a significant advance around Deep learning, since they present a better performance than the traditional counterparts based on real numbers. This proposes an experimental basis for the construction of a new Deep learning paradigm, where information in another numerical domain, is better exploited with the help of mathematical transforms. The latter is a significant advance in health sciences, where the demand is higher, in terms of performance of the proposed models.

Funding Acknowledgement

Type of funding sources: Other. Main funding source(s): eVIDA research Group

Multiclass classification of breast cancer histopathology images using multilevel features of deep convolutional neural network

Breast cancer is a common malignancy and a leading cause of cancer-related deaths in women worldwide. Its early diagnosis can significantly reduce the morbidity and mortality rates in women. To this end, histopathological diagnosis is usually followed as the gold standard approach. However, this process is tedious, labor-intensive, and may be subject to inter-reader variability. Accordingly, an automatic diagnostic system can assist to improve the quality of diagnosis. This paper presents a deep learning approach to automatically classify hematoxylin-eosin-stained breast cancer microscopy images into normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma using our collected dataset. Our proposed model exploited six intermediate layers of the Xception (Extreme Inception) network to retrieve robust and abstract features from input images. First, we optimized the proposed model on the original (unnormalized) dataset using 5-fold cross-validation. Then, we investigated its performance on four normalized datasets resulting from Reinhard, Ruifrok, Macenko, and Vahadane stain normalization. For original images, our proposed framework yielded an accuracy of 98% along with a kappa score of 0.969. Also, it achieved an average AUC-ROC score of 0.998 as well as a mean AUC-PR value of 0.995. Specifically, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. For normalized images, the proposed architecture performed better for Makenko normalization compared to the other three techniques. In this case, the proposed model achieved an accuracy of 97.79% together with a kappa score of 0.965. Also, it attained an average AUC-ROC score of 0.997 and a mean AUC-PR value of 0.991. Especially, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. These results demonstrate that our proposed model outperformed the baseline AlexNet as well as state-of-the-art VGG16, VGG19, Inception-v3, and Xception models with their default settings. Furthermore, it can be inferred that although stain normalization techniques offered competitive performance, they could not surpass the results of the original dataset.

A Fair Performance Comparison between Complex-Valued and Real-Valued Neural Networks for Disease Detection

Our aim is to contribute to the classification of anomalous patterns in biosignals using this novel approach. We specifically focus on melanoma and heart murmurs. We use a comparative study of two convolution networks in the Complex and Real numerical domains. The idea is to obtain a powerful approach for building portable systems for early disease detection. Two similar algorithmic structures were chosen so that there is no bias determined by the number of parameters to train. Three clinical data sets, ISIC2017, PH2, and Pascal, were used to carry out the experiments. Mean comparison hypothesis tests were performed to ensure statistical objectivity in the conclusions. In all cases, complex-valued networks presented a superior performance for the Precision, Recall, F1 Score, Accuracy, and Specificity metrics in the detection of associated anomalies. The best complex number-based classifier obtained in the Receiving Operating Characteristic (ROC) space presents a Euclidean distance of 0.26127 with respect to the ideal classifier, as opposed to the best real number-based classifier, whose Euclidean distance to the ideal is 0.36022 for the same task of melanoma detection. The 27.46% superiority in this metric, as in the others reported in this work, suggests that complex-valued networks have a greater ability to extract features for more efficient discrimination in the dataset.

Application of Machine Learning Techniques to Help in the Feature Selection Related to Hospital Readmissions of Suicidal Behavior

Suicide was the main source of death from external causes in Spain in 2020, with 3,941 cases. The importance of identifying those mental disorders that influenced hospital readmissions will allow us to manage the health care of suicidal behavior. The feature selection of each hospital in this region was carried out by applying Machine learning (ML) and traditional statistical methods. The results of the characteristics that best explain the readmissions of each hospital after assessment by the psychiatry specialist are presented. Adjustment disorder, alcohol abuse, depressive syndrome, personality disorder, and dysthymic disorder were selected for this region. The most influential methods or characteristics associated with suicide were benzodiazepine poisoning, suicidal ideation, medication poisoning, antipsychotic poisoning, and suicide and/or self-harm by jumping. Suicidal behavior is a concern in our society, so the results are relevant for hospital management and decision-making for its prevention.

Early detection and classification of abnormality in prior mammograms using image-to-image translation and YOLO techniques

BACKGROUND AND OBJECTIVE

Computer-aided-detection (CAD) systems have been developed to assist radiologists on finding suspicious lesions in mammogram. Deep Learning technology have recently succeeded to increase the chance of recognizing abnormality at an early stage in order to avoid unnecessary biopsies and decrease the mortality rate. In this study, we investigated the effectiveness of an end-to-end fusion model based on You-Only-Look-Once (YOLO) architecture, to simultaneously detect and classify suspicious breast lesions on digital mammograms. Four categories of cases were included: Mass, Calcification, Architectural Distortions, and Normal from a private digital mammographic database including 413 cases. For all cases, Prior mammograms (typically scanned 1 year before) were all reported as Normal, while Current mammograms were diagnosed as cancerous (confirmed by biopsies) or healthy.

METHODS

We propose to apply the YOLO-based fusion model to the Current mammograms for breast lesions detection and classification. Then apply the same model retrospectively to synthetic mammograms for an early cancer prediction, where the synthetic mammograms were generated from the Prior mammograms by using the image-to-image translation models, CycleGAN and Pix2Pix.

RESULTS

Evaluation results showed that our methodology could significantly detect and classify breast lesions on Current mammograms with a highest rate of 93% ± 0.118 for Mass lesions, 88% ± 0.09 for Calcification lesions, and 95% ± 0.06 for Architectural Distortion lesions. In addition, we reported evaluation results on Prior mammograms with a highest rate of 36% ± 0.01 for Mass lesions, 14% ± 0.01 for Calcification lesions, and 50% ± 0.02 for Architectural Distortion lesions. Normal mammograms were accordingly classified with an accuracy rate of 92% ± 0.09 and 90% ± 0.06 respectively on Current and Prior exams.

CONCLUSIONS

Our proposed framework was first developed to help detecting and identifying suspicious breast lesions in X-ray mammograms on their Current screening. The work was also suggested to reduce the temporal changes between pairs of Prior and follow-up screenings for early predicting the location and type of abnormalities in Prior mammogram screening. The paper presented a CAD method to assist doctors and experts to identify the risk of breast cancer presence. Overall, the proposed CAD method incorporates the advances of image processing, deep learning and image-to-image translation for a biomedical application.

Analysis of the Effects of Lockdown on Staff and Students at Universities in Spain and Colombia Using Natural Language Processing Techniques

The aim of this study is to analyze the effects of lockdown using natural language processing techniques, particularly sentiment analysis methods applied at large scale. Further, our work searches to analyze the impact of COVID-19 on the university community, jointly on staff and students, and with a multi-country perspective. The main findings of this work show that the most often related words were "family", "anxiety", "house", and "life". Besides this finding, we also have shown that staff have a slightly less negative perception of the consequences of COVID-19 in their daily life. We have used artificial intelligence models such as swivel embedding and a multilayer perceptron as classification algorithms. The performance that was reached in terms of accuracy metrics was 88.8% and 88.5% for students and staff, respectively. The main conclusion of our study is that higher education institutions and policymakers around the world may benefit from these findings while formulating policy recommendations and strategies to support students during this and any future pandemics.

Automated Knee MR Images Segmentation of Anterior Cruciate Ligament Tears

The anterior cruciate ligament (ACL) is one of the main stabilizer parts of the knee. ACL injury leads to causes of osteoarthritis risk. ACL rupture is common in the young athletic population. Accurate segmentation at an early stage can improve the analysis and classification of anterior cruciate ligaments tears. This study automatically segmented the anterior cruciate ligament (ACL) tears from magnetic resonance imaging through deep learning. The knee mask was generated on the original Magnetic Resonance (MR) images to apply a semantic segmentation technique with convolutional neural network architecture U-Net. The proposed segmentation method was measured by accuracy, intersection over union (IoU), dice similarity coefficient (DSC), precision, recall and F1-score of 98.4%, 99.0%, 99.4%, 99.6%, 99.6% and 99.6% on 11451 training images, whereas on the validation images of 3817 was, respectively, 97.7%, 93.8%,96.8%, 96.5%, 97.3% and 96.9%. We also provide dice loss of training and test datasets that have remained 0.005 and 0.031, respectively. The experimental results show that the ACL segmentation on JPEG MRI images with U-Nets achieves accuracy that outperforms the human segmentation. The strategy has promising potential applications in medical image analytics for the segmentation of knee ACL tears for MR images.

A Comparative Study between Scanning Devices for 3D Printing of Personalized Ostomy Patches

This papers presents a comparative study of three different 3D scanning modalities to acquire 3D meshes of stoma barrier rings from ostomized patients. Computerized Tomography and Structured light scanning methods were the digitization technologies studied in this research. Among the Structured Light systems, the Go!Scan 20 and the Structure Sensor were chosen as the handheld 3D scanners. Nineteen ostomized patients took part in this study, starting from the 3D scans acquisition until the printed ostomy patches validation. 3D mesh processing, mesh generation and 3D mesh comparison was carried out using commercial softwares. The results of the presented study show that the Structure Sensor, which is the low cost structured light 3D sensor, has a great potential for such applications. This study also discusses the benefits and reliability of low-cost structured light systems.

hGLUTEN Tool: Measuring Its Social Impact Indicators

hGLUTEN is a technological solution capable of detecting gluten and spoiled food. We measured the social impact of the hGLUTEN tool using two Likert scale surveys with two groups: professionals (engineers/chefs) and end-users. These data have been assessed in accordance with the social impact indicators defined for the Key Impact Pathways introduced by the European Commission for Horizon Europe and the criteria of the Social Impact Open Repository (SIOR). A total of 85% of users, 100% of engineers and 68% of professional chefs consider it very relevant to participate and give their opinion in research projects, which shows the increasingly high level of involvement of the general population. A total of 88% of users were unaware of other applications that detect gluten and were more dependent on guidelines provided by allergy associations and expiry dates of foodstuffs. In addition, only 5% of professional chefs said they were aware of other technology capable of detecting gluten in food, which may indicate a large economic market and good commercialisation possibilities for the tool in the future. Finally, the inclusion of tools to motivate users to promote it has been identified as an area for improvement, which could mean that it should be made more visible in the media to increase its impact and influence.

Multi-Agent Systems in Fog-Cloud Computing for Critical Healthcare Task Management Model (CHTM) Used for ECG Monitoring

In the last decade, the developments in healthcare technologies have been increasing progressively in practice. Healthcare applications such as ECG monitoring, heartbeat analysis, and blood pressure control connect with external servers in a manner called cloud computing. The emerging cloud paradigm offers different models, such as fog computing and edge computing, to enhance the performances of healthcare applications with minimum end-to-end delay in the network. However, many research challenges exist in the fog-cloud enabled network for healthcare applications. Therefore, in this paper, a Critical Healthcare Task Management (CHTM) model is proposed and implemented using an ECG dataset. We design a resource scheduling model among fog nodes at the fog level. A multi-agent system is proposed to provide the complete management of the network from the edge to the cloud. The proposed model overcomes the limitations of providing interoperability, resource sharing, scheduling, and dynamic task allocation to manage critical tasks significantly. The simulation results show that our model, in comparison with the cloud, significantly reduces the network usage by 79%, the response time by 90%, the network delay by 65%, the energy consumption by 81%, and the instance cost by 80%.

Predicting Physical Exercise Adherence in Fitness Apps Using a Deep Learning Approach

The use of mobile fitness apps has been on the rise for the last decade and especially during the worldwide SARS-CoV-2 pandemic, which led to the closure of gyms and to reduced outdoor mobility. Fitness apps constitute a promising means for promoting more active lifestyles, although their attrition rates are remarkable and adherence to their training plans remains a challenge for developers. The aim of this project was to design an automatic classification of users into adherent and non-adherent, based on their training behavior in the first three months of app usage, for which purpose we proposed an ensemble of regression models to predict their behaviour (adherence) in the fourth month. The study was conducted using data from a total of 246 Mammoth Hunters Fitness app users. Firstly, pre-processing and clustering steps were taken in order to prepare the data and to categorize users into similar groups, taking into account the first 90 days of workout sessions. Then, an ensemble approach for regression models was used to predict user training behaviour during the fourth month, which were trained with users belonging to the same cluster. This was used to reach a conclusion regarding their adherence status, via an approach that combined affinity propagation (AP) clustering algorithm, followed by the long short-term memory (LSTM), rendering the best results (87% accuracy and 85% F1_score). This study illustrates the suggested the capacity of the system to anticipate future adherence or non-adherence, potentially opening the door to fitness app creators to pursue advanced measures aimed at reducing app attrition.

Sentiment Analysis Techniques Applied to Raw-Text Data from a Csq-8 Questionnaire about Mindfulness in Times of COVID-19 to Improve Strategy Generation

The use of artificial intelligence in health care has grown quickly. In this sense, we present our work related to the application of Natural Language Processing techniques, as a tool to analyze the sentiment perception of users who answered two questions from the CSQ-8 questionnaires with raw Spanish free-text. Their responses are related to mindfulness, which is a novel technique used to control stress and anxiety caused by different factors in daily life. As such, we proposed an online course where this method was applied in order to improve the quality of life of health care professionals in COVID 19 pandemic times. We also carried out an evaluation of the satisfaction level of the participants involved, with a view to establishing strategies to improve future experiences. To automatically perform this task, we used Natural Language Processing (NLP) models such as swivel embedding, neural networks, and transfer learning, so as to classify the inputs into the following three categories: negative, neutral, and positive. Due to the limited amount of data available-86 registers for the first and 68 for the second-transfer learning techniques were required. The length of the text had no limit from the user's standpoint, and our approach attained a maximum accuracy of 93.02% and 90.53%, respectively, based on ground truth labeled by three experts. Finally, we proposed a complementary analysis, using computer graphic text representation based on word frequency, to help researchers identify relevant information about the opinions with an objective approach to sentiment. The main conclusion drawn from this work is that the application of NLP techniques in small amounts of data using transfer learning is able to obtain enough accuracy in sentiment analysis and text classification stages.

Deep Learning Models for Colorectal Polyps

Colorectal cancer is one of the main causes of cancer incident cases and cancer deaths worldwide. Undetected colon polyps, be them benign or malignant, lead to late diagnosis of colorectal cancer. Computer aided devices have helped to decrease the polyp miss rate. The application of deep learning algorithms and techniques has escalated during this last decade. Many scientific studies are published to detect, localize, and classify colon polyps. We present here a brief review of the latest published studies. We compare the accuracy of these studies with our results obtained from training and testing three independent datasets using a convolutional neural network and autoencoder model. A train, validate and test split was performed for each dataset, 75%, 15%, and 15%, respectively. An accuracy of 0.937 was achieved for CVC-ColonDB, 0.951 for CVC-ClinicDB, and 0.967 for ETIS-LaribPolypDB. Our results suggest slight improvements compared to the algorithms used to date.

Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach

The most commonly injured ligament in the human body is an anterior cruciate ligament (ACL). ACL injury is standard among the football, basketball and soccer players. The study aims to detect anterior cruciate ligament injury in an early stage via efficient and thorough automatic magnetic resonance imaging without involving radiologists, through a deep learning method. The proposed approach in this paper used a customized 14 layers ResNet-14 architecture of convolutional neural network (CNN) with six different directions by using class balancing and data augmentation. The performance was evaluated using accuracy, sensitivity, specificity, precision and F1 score of our customized ResNet-14 deep learning architecture with hybrid class balancing and real-time data augmentation after 5-fold cross-validation, with results of 0.920%, 0.916%, 0.946%, 0.916% and 0.923%, respectively. For our proposed ResNet-14 CNN the average area under curves (AUCs) for healthy tear, partial tear and fully ruptured tear had results of 0.980%, 0.970%, and 0.999%, respectively. The proposing diagnostic results indicated that our model could be used to detect automatically and evaluate ACL injuries in athletes using the proposed deep-learning approach.

Mobile Health Apps for Medical Emergencies: Systematic Review

Background

Mobile health apps are used to improve the quality of health care. These apps are changing the current scenario in health care, and their numbers are increasing.

Objective

We wanted to perform an analysis of the current status of mobile health technologies and apps for medical emergencies. We aimed to synthesize the existing body of knowledge to provide relevant insights for this topic. Moreover, we wanted to identify common threads and gaps to support new challenging, interesting, and relevant research directions.

Methods

We reviewed the main relevant papers and apps available in the literature. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was used in this review. The search criteria were adopted using systematic methods to select papers and apps. On one hand, a bibliographic review was carried out in different search databases to collect papers related to each application in the health emergency field using defined criteria. On the other hand, a review of mobile apps in two virtual storage platforms (Google Play Store and Apple App Store) was carried out. The Google Play Store and Apple App Store are related to the Android and iOS operating systems, respectively.

Results

In the literature review, 28 papers in the field of medical emergency were included. These studies were collected and selected according to established criteria. Moreover, we proposed a taxonomy using six groups of applications. In total, 324 mobile apps were found, with 192 identified in the Google Play Store and 132 identified in the Apple App Store.

Conclusions

We found that all apps in the Google Play Store were free, and 73 apps in the Apple App Store were paid, with the price ranging from US $0.89 to US $5.99. Moreover, 39% (11/28) of the included studies were related to warning systems for emergency services and 21% (6/28) were associated with disaster management apps.

Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging

BACKGROUND AND OBJECTIVES

Dyslexia is a disorder of neurological origin which affects the learning of those who suffer from it, mainly children, and causes difficulty in reading and writing. When undiagnosed, dyslexia leads to intimidation and frustration of the affected children and also of their family circles. In case no early intervention is given, children may reach high school with serious achievement gaps. Hence, early detection and intervention services for dyslexic students are highly important and recommended in order to support children in developing a positive self-esteem and reaching their maximum academic capacities. This paper presents a new approach for automatic recognition of children with dyslexia using functional magnetic resonance Imaging.

METHODS

Our proposed system is composed of a sequence of preprocessing steps to retrieve the brain activation areas during three different reading tasks. Conversion to Nifti volumes, adjustment of head motion, normalization and smoothing transformations were performed on the fMRI scans in order to bring all the subject brains into one single model which will enable voxels comparison between each subject. Subsequently, using Statistical Parametric Maps (SPMs), a total of 165 3D volumes containing brain activation of 55 children were created. The classification of these volumes was handled using three parallel 3D Convolutional Neural Network (3D CNN), each corresponding to a brain activation during one reading task, and concatenated in the last two dense layers, forming a single architecture devoted to performing optimized detection of dyslexic brain activation. Additionally, we used 4-fold cross validation method in order to assess the generalizability of our model and control overfitting.

RESULTS

Our approach has achieved an overall average classification accuracy of 72.73%, sensitivity of 75%, specificity of 71.43%, precision of 60% and an F1-score of 67% in dyslexia detection.

CONCLUSIONS

The proposed system has demonstrated that the recognition of dyslexic children is feasible using deep learning and functional magnetic resonance Imaging when performing phonological and orthographic reading tasks.

Detection of Focal and Non-Focal Electroencephalogram Signals Using Fast Walsh-Hadamard Transform and Artificial Neural Network

The discrimination of non-focal class (NFC) and focal class (FC), is vital in localizing the epileptogenic zone (EZ) during neurosurgery. In the conventional diagnosis method, the neurologist has to visually examine the long hour electroencephalogram (EEG) signals, which consumes time and is prone to error. Hence, in this present work, automated diagnosis of FC EEG signals from NFC EEG signals is developed using the Fast Walsh-Hadamard Transform (FWHT) method, entropies, and artificial neural network (ANN). The FWHT analyzes the EEG signals in the frequency domain and decomposes it into the Hadamard coefficients. Five different nonlinear features, namely approximate entropy (ApEn), log-energy entropy (LogEn), fuzzy entropy (FuzzyEn), sample entropy (SampEn), and permutation entropy (PermEn) are extracted from the decomposed Hadamard coefficients. The extracted features detail the nonlinearity in the NFC and the FC EEG signals. The judicious entropy features are supplied to the ANN classifier, with a 10-fold cross-validation method to classify the NFC and FC classes. Two publicly available datasets such as the University of Bonn and Bern-Barcelona dataset are used to evaluate the proposed approach. A maximum sensitivity of 99.70%, the accuracy of 99.50%, and specificity of 99.30% with the 3750 pairs of NFC and FC signal are achieved using the Bern-Barcelona dataset, while the accuracy of 92.80%, the sensitivity of 91%, and specificity of 94.60% is achieved using University of Bonn dataset. Compared to the existing technique, the proposed approach attained a maximum classification performance in both the dataset.

Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models

Breast cancer is one of the major public health issues and is considered a leading cause of cancer-related deaths among women worldwide. Its early diagnosis can effectively help in increasing the chances of survival rate. To this end, biopsy is usually followed as a gold standard approach in which tissues are collected for microscopic analysis. However, the histopathological analysis of breast cancer is non-trivial, labor-intensive, and may lead to a high degree of disagreement among pathologists. Therefore, an automatic diagnostic system could assist pathologists to improve the effectiveness of diagnostic processes. This paper presents an ensemble deep learning approach for the definite classification of non-carcinoma and carcinoma breast cancer histopathology images using our collected dataset. We trained four different models based on pre-trained VGG16 and VGG19 architectures. Initially, we followed 5-fold cross-validation operations on all the individual models, namely, fully-trained VGG16, fine-tuned VGG16, fully-trained VGG19, and fine-tuned VGG19 models. Then, we followed an ensemble strategy by taking the average of predicted probabilities and found that the ensemble of fine-tuned VGG16 and fine-tuned VGG19 performed competitive classification performance, especially on the carcinoma class. The ensemble of fine-tuned VGG16 and VGG19 models offered sensitivity of 97.73% for carcinoma class and overall accuracy of 95.29%. Also, it offered an F1 score of 95.29%. These experimental results demonstrated that our proposed deep learning approach is effective for the automatic classification of complex-natured histopathology images of breast cancer, more specifically for carcinoma images.

Wireless Body Area Networks: UWB Wearable Textile Antenna for Telemedicine and Mobile Health Systems

A compact textile ultra-wideband (UWB) antenna with an electrical dimension of 0.24λ_o × 0.24λ_o × 0.009λ_o with microstrip line feed at lower edge and a frequency of operation of 2.96 GHz is proposed for UWB application. The analytical investigation using circuit theory concepts and the cavity model of the antenna is presented to validate the design. The main contribution of this paper is to propose a wearable antenna with wide impedance bandwidth of 118.68 % (2.96–11.6 GHz) applicable for UWB range of 3.1 to 10.6 GHz. The results present a maximum gain of 5.47 dBi at 7.3 GHz frequency. Moreover, this antenna exhibits Omni and quasi-Omni radiation patterns at various frequencies (4 GHz, 7 GHz and 10 GHz) for short-distance communication. The cutting notch and slot on the patch, and its effect on the antenna impedance to increase performance through current distribution is also presented. The time-domain characteristic of the proposed antenna is also discussed for the analysis of the pulse distortion phenomena. A constant group delay less than 1 ns is obtained over the entire operating impedance bandwidth (2.96–11.6 GHz) of the textile antenna in both situations, i.e., side by side and front to front. Linear phase consideration is also presented for both situations, as well as configurations of reception and transmission. An assessment of the effects of bending and humidity has been demonstrated by placing the antenna on the human body. The specific absorption rate (SAR) value was tested to show the radiation effect on the human body, and it was found that its impact on the human body SAR value is 1.68 W/kg, which indicates the safer limit to avoid radiation effects. Therefore, the proposed method is promising for telemedicine and mobile health systems.

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Pressure injuries represent a major concern in many nations. These wounds result from prolonged pressure on the skin, which mainly occur among elderly and disabled patients. If retrieving quantitative information using invasive methods is the most used method, it causes significant pain and discomfort to the patients and may also increase the risk of infections. Hence, developing non-intrusive methods for the assessment of pressure injuries would represent a highly useful tool for caregivers and a relief for patients. Traditional methods rely on findings retrieved solely from 2D images. Thus, bypassing the 3D information deriving from the deep and irregular shape of this type of wounds leads to biased measurements. In this paper, we propose an end-to-end system which uses a single 2D image and a 3D mesh of the pressure injury, acquired using the Structure Sensor, and outputs all the necessary findings such as: external segmentation of the wound as well as its real-world measurements (depth, area, volume, major axis and minor axis). More specifically, a first block composed of a Mask RCNN model uses the 2D image to output the segmentation of the external boundaries of the wound. Then, a second block matches the 2D and 3D views to segment the wound in the 3D mesh using the segmentation output and generates the aforementioned real-world measurements. Experimental results showed that the proposed framework can not only output refined segmentation with 87% precision, but also retrieves reliable measurements, which can be used for medical assessment and healing evaluation of pressure injuries.

Internet of Things and Enhanced Living Environments: Measuring and Mapping Air Quality Using Cyber-physical Systems and Mobile Computing Technologies

This paper presents a real-time air quality monitoring system based on Internet of Things. Air quality is particularly relevant for enhanced living environments and well-being. The Environmental Protection Agency and the World Health Organization have acknowledged the material impact of air quality on public health and defined standards and policies to regulate and improve air quality. However, there is a significant need for cost-effective methods to monitor and control air quality which provide modularity, scalability, portability, easy installation and configuration features, and mobile computing technologies integration. The proposed method allows the measuring and mapping of air quality levels considering the spatial-temporal information. This system incorporates a cyber-physical system for data collection and mobile computing software for data consulting. Moreover, this method provides a cost-effective and efficient solution for air quality supervision and can be installed in vehicles to monitor air quality while travelling. The results obtained confirm the implementation of the system and present a relevant contribution to enhanced living environments in smart cities. This supervision solution provides real-time identification of unhealthy behaviours and supports the planning of possible interventions to increase air quality.

Detection of Volatile Compounds Emitted by Bacteria in Wounds Using Gas Sensors

In this paper we analyze an experiment for the use of low-cost gas sensors intended to detect bacteria in wounds using a non-intrusive technique. Seven different genera/species of microbes tend to be present in most wound infections. Detection of these bacteria usually requires sample and laboratory testing which is costly, inconvenient and time-consuming. The validation processes for these sensors with nineteen types of microbes (1 Candida, 2 Enterococcus, 6 Staphylococcus, 1 Aeromonas, 1 Micrococcus, 2 E. coli and 6 Pseudomonas) are presented here, in which four sensors were evaluated: TGS-826 used for ammonia and amines, MQ-3 used for alcohol detection, MQ-135 for CO₂ and MQ-138 for acetone detection. Validation was undertaken by studying the behavior of the sensors at different distances and gas concentrations. Preliminary results with liquid cultures of 10⁸ CFU/mL and solid cultures of 10⁸ CFU/cm² of the 6 Pseudomonas aeruginosa strains revealed that the four gas sensors showed a response at a height of 5 mm. The ammonia detection response of the TGS-826 to Pseudomonas showed the highest responses for the experimental samples over the background signals, with a difference between the values of up to 60 units in the solid samples and the most consistent and constant values. This could suggest that this sensor is a good detector of Pseudomonas aeruginosa, and the recording made of its values could be indicative of the detection of this species. All the species revealed similar CO₂ emission and a high response rate with acetone for Micrococcus, Aeromonas and Staphylococcus.

Segmentation of skin lesions in dermoscopy images using fuzzy classification of pixels and histogram thresholding

BACKGROUND AND OBJECTIVE

To ensure proper functioning of a Computer Aided Diagnosis (CAD) system for melanoma detection in dermoscopy images, it is important to accurately detect the border of the lesion. This paper proposes a method developed by the authors to address this problem.

METHODS

The algorithm for segmentation of skin lesions in dermoscopy images is based on fuzzy classification of pixels and subsequent histogram thresholding.

RESULTS

This method participated in the 2016 and 2017 ISBI (International Symposium on Biomedical Imaging) Challenges, hosted by the ISIC (International Skin Imaging Collaboration). It was tested against two public databases containing 379 and 600 images respectively, and compared using the same defined metrics (Accuracy, Dice Coefficient, Jaccard Index, Sensitivity and Specificity) with the rest of participating state-of-the-art work, obtaining good results: (0.934, 0.869, 0.791, 0.870 and 0.978) and (0.884, 0.760, 0.665, 0.869 and 0.923) respectively, ranking 9th and 15th out of a total of 21 and 28 participants respectively using the Jaccard Index (which was the indicator used as a basis for ranking) and the 1st in the 2017 Challenge using the Sensitivity.

CONCLUSION

The method has been proven to be robust and reliable. It's main contribution is the very design of the algorithm, highly innovative, which could also be used to deal with other segmentation problems of a similar nature.

Tissue classification and segmentation of pressure injuries using convolutional neural networks

BACKGROUND AND OBJECTIVES

This paper presents a new approach for automatic tissue classification in pressure injuries. These wounds are localized skin damages which need frequent diagnosis and treatment. Therefore, a reliable and accurate systems for segmentation and tissue type identification are needed in order to achieve better treatment results.

METHODS

Our proposed system is based on a Convolutional Neural Network (CNN) devoted to performing optimized segmentation of the different tissue types present in pressure injuries (granulation, slough, and necrotic tissues). A preprocessing step removes the flash light and creates a set of 5x5 sub-images which are used as input for the CNN network. The network output will classify every sub-image of the validation set into one of the three classes studied.

RESULTS

The metrics used to evaluate our approach show an overall average classification accuracy of 92.01%, an average total weighted Dice Similarity Coefficient of 91.38%, and an average precision per class of 97.31% for granulation tissue, 96.59% for necrotic tissue, and 77.90% for slough tissue.

CONCLUSIONS

Our system has been proven to make recognition of complicated structures in biomedical images feasible.

Managing and Controlling Stress Using mHealth: Systematic Search in App Stores

Background

Traditional stress management techniques have been proven insufficient to tackle the needs of today’s population. Computational-based techniques and now mobile health (mHealth) apps are showing promise to enable ease of use and access while educating end users on self-management.

Objective

The main aim of this paper was to put forward a systematic review of mHealth apps for stress management.

Methods

The scenario chosen for this study consists of a sample of the most relevant mHealth apps found on the British and Spanish online stores of the two main mobile operating systems: iOS and Android. The apps have been categorized and scored base on their impact, presence, number of results, language, and operating system.

Results

A total of 433 different mobile apps for stress management was analyzed. Of these apps, 21.7% (94/433) belonged to the “relaxing music” category, 10.9% (47/433) were in the “draw and paint” category, 1.2% (5/433) belonged to the “heart rate control” category, and 1.2% (5/433) fell under “integral methodology.” Only 2.0% (8/433) of the apps qualified as high or medium interest while 98.0% were low interest. Furthermore, 2.0% (8/433) of the apps were available on both iOS and Android, and 98% of apps ran on only one platform (iOS or Android).

Conclusions

There are many low-value apps available at the moment, but the analysis shows that they are adding new functionalities and becoming fully integrated self-management systems with extra capabilities such as professional assistance services and online support communities.

Efficient use of mobile devices for quantification of pressure injury images

Pressure Injuries are chronic wounds that are formed due to the constriction of the soft tissues against bone prominences. In order to assess these injuries, the medical personnel carry out the evaluation and diagnosis using visual methods and manual measurements, which can be inaccurate and may generate discomfort in the patients. By using segmentation techniques, the Pressure Injuries can be extracted from an image and accurately parameterized, leading to a correct diagnosis. In general, these techniques are based on the solution of differential equations and the involved numerical methods are demanding in terms of computational resources. In previous work, we proposed a technique developed using toroidal parametric equations for image decomposition and segmentation without solving differential equations. In this paper, we present the development of a mobile application useful for the non-contact assessment of Pressure Injuries based on the toroidal decomposition from images. The usage of this technique allows us to achieve an accurate segmentation almost 8 times faster than Active Contours without Edges (ACWE) and Dynamic Contours methods. We describe the techniques and the implementation for Android devices using Python and Kivy. This application allows for the segmentation and parameterization of injuries, obtain relevant information for the diagnosis and tracking the evolution of patient’s injuries.

Activating Technology for Connected Health in Cancer: Protocol for a Research and Training Program

BACKGROUND

As cancer survival rates increase, the challenge of ensuring that cancer survivors reclaim their quality of life (QoL) becomes more important. This paper outlines the research element of a research and training program that is designed to do just that.

OBJECTIVE

Bridging sectors, disciplines, and geographies, it brings together eight PhD projects and students from across Europe to identify the underlying barriers, test different technology-enabled rehabilitative approaches, propose a model to optimize the patient pathways, and examine the business models that might underpin a sustainable approach to cancer survivor reintegration using technology.

METHODS

The program, funded under the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 722012, includes deep disciplinary PhD projects, intersectoral and international secondments, interdisciplinary plenary training schools, and virtual subject-specific education modules.

RESULTS

The 8 students have now been recruited and are at the early stages of their projects.

CONCLUSIONS

CATCH will provide a comprehensive training and research program by embracing all key elements-technical, social, and economic sciences-required to produce researchers and project outcomes that are capable of meeting existing and future needs in cancer rehabilitation.

Recognition of pigment network pattern in dermoscopy images based on fuzzy classification of pixels

BACKGROUND AND OBJECTIVE

One of the most relevant dermoscopic patterns is the pigment network. An innovative method of pattern recognition is presented for its detection in dermoscopy images.

METHODS

It consists of two steps. In the first one, by means of a supervised machine learning process and after performing the extraction of different colour and texture features, a fuzzy classification of pixels into the three categories present in the pattern's definition ("net", "hole" and "other") is carried out. This enables the three corresponding fuzzy sets to be created and, as a result, the three probability images that map them out are generated. In the second step, the pigment network pattern is characterised from a parameterisation process -derived from the system specification- and the subsequent extraction of different features calculated from the combinations of image masks extracted from the probability images, corresponding to the alpha-cuts obtained from the fuzzy sets.

RESULTS

The method was tested on a database of 875 images -by far the largest used in the state of the art to detect pigment network- extracted from a public Atlas of Dermoscopy, obtaining AUC results of 0.912 and 88%% accuracy, with 90.71%% sensitivity and 83.44%% specificity.

CONCLUSION

The main contribution of this method is the very design of the algorithm, highly innovative, which could also be used to deal with other pattern recognition problems of a similar nature. Other contributions are: 1. The good performance in discriminating between the pattern and the disturbing artefacts -which means that no prior preprocessing is required in this method- and between the pattern and other dermoscopic patterns; 2. It puts forward a new methodological approach for work of this kind, introducing the system specification as a required step prior to algorithm design and development, being this specification the basis for a required parameterisation -in the form of configurable parameters (with their value ranges) and set threshold values- of the algorithm and the subsequent conducting of the experiments.

FRED: Exergame to Prevent Dependence and Functional Deterioration Associated with Ageing. A Pilot Three-Week Randomized Controlled Clinical Trial

Introduction: Frailty syndrome and advanced age may decrease the acceptance of illness and quality of life, and worsen patients' existing health conditions, as well as leading to an increase in health care expenses. Purpose: The purpose of this study is to reduce frailty risk via the use of a FRED game which has been expressly designed and put together for the study. Materials and methods: A total of 40 frail volunteers with a score of <10 points in the short physical performance battery (SPPB) took part in a feasibility study in order to validate the FRED game. Following randomisation, the study group (20 subjects) took part in nine sessions of 20 min each over a three-week period. The control group (19 subjects) continued to lead their daily lives in the course of which they had no physical activity scheduled; Results: After three weeks and having taken part in nine physical activity sessions with the FRED game, 60% of subjects from the study group (12/20) obtained a score of ≥10 points at the end of the study, i.e., less risk of evidencing frailty. This result proved to be statistically significant (p < 0.001). The degree of compliance with and adherence to the game was confirmed by 100% attendance of the sessions. Discussion: Our findings support the hypothesis that FRED, an ad hoc designed exergame, significantly reduced the presence and severity of frailty in a sample of sedentary elders, thus potentially modifying their risk profile. Conclusions: The FRED game is a tool that shows a 99% certain improvement in the degree of frailty in frail elderly subjects. The effectiveness of the design of ad hoc games in a certain pathology or population group is therefore evidenced.

Primary Prevention of Asymptomatic Cardiovascular Disease Using Physiological Sensors Connected to an iOS App

Cardiovascular disease is the first cause of death and disease and one of the leading causes of disability in developed countries. The prevalence of this disease is expected to increase in coming years although the death rate may be lower due to better treatment. To present the design and development of a technology solution for primary prevention of cardiovascular disease in asymptomatic patients. The system aims to raise the population's awareness of the importance of adopting healthy heart habits by using self-feedback techniques. A series of sensors which makes it possible to detect cardiovascular risk factors in asymptomatic patients were used. These sensors enable evaluation of heart rate, blood pressure, SpO₂ -oxygen saturation in blood- and body temperature. This work has developed a modular solution centred on four parts: iOS app, sensors, server and web. The CoreBluetooth library, which carries out Bluetooth 4.0 communication, was used for the connection between the app and the sensors. The data files are stored on the iPad and the server by using CoreData and SQL mechanisms. The system was validated with 20 healthy volunteers and 10 patients with established structural heart disease. Once the samples had been obtained, a comparison of all the significant data was run, in addition to a statistical analysis. The result of this calculation was a total of 32 cases of first level significance correlations (p < 0.01), for example, the inverse relationship between the daily step count and high blood pressure (p = 0.008) and 24 s level cases (p < 0.05) such as the significant correlation between risk and age (p = 0.013). The system designed in this paper has made it possible to create an application capable of collecting data on cardiovascular risk factors through a sensor system that measures physiological variables and records physical activity and diet.

Automatic migraine classification via feature selection committee and machine learning techniques over imaging and questionnaire data

BACKGROUND

Feature selection methods are commonly used to identify subsets of relevant features to facilitate the construction of models for classification, yet little is known about how feature selection methods perform in diffusion tensor images (DTIs). In this study, feature selection and machine learning classification methods were tested for the purpose of automating diagnosis of migraines using both DTIs and questionnaire answers related to emotion and cognition - factors that influence of pain perceptions.

METHODS

We select 52 adult subjects for the study divided into three groups: control group (15), subjects with sporadic migraine (19) and subjects with chronic migraine and medication overuse (18). These subjects underwent magnetic resonance with diffusion tensor to see white matter pathway integrity of the regions of interest involved in pain and emotion. The tests also gather data about pathology. The DTI images and test results were then introduced into feature selection algorithms (Gradient Tree Boosting, L1-based, Random Forest and Univariate) to reduce features of the first dataset and classification algorithms (SVM (Support Vector Machine), Boosting (Adaboost) and Naive Bayes) to perform a classification of migraine group. Moreover we implement a committee method to improve the classification accuracy based on feature selection algorithms.

RESULTS

When classifying the migraine group, the greatest improvements in accuracy were made using the proposed committee-based feature selection method. Using this approach, the accuracy of classification into three types improved from 67 to 93% when using the Naive Bayes classifier, from 90 to 95% with the support vector machine classifier, 93 to 94% in boosting. The features that were determined to be most useful for classification included are related with the pain, analgesics and left uncinate brain (connected with the pain and emotions).

CONCLUSIONS

The proposed feature selection committee method improved the performance of migraine diagnosis classifiers compared to individual feature selection methods, producing a robust system that achieved over 90% accuracy in all classifiers. The results suggest that the proposed methods can be used to support specialists in the classification of migraines in patients undergoing magnetic resonance imaging.

Is Technology Present in Frailty? Technology a Back-up Tool for Dealing with Frailty in the Elderly: A Systematic Review

This study analyzes the technologies used in dealing with frailty within the following areas: prevention, care, diagnosis and treatment. The aim of this paper is, on the one hand, to analyze the extent to which technology is present in terms of its relationship with frailty and what technological resources are used to treat it. Its other purpose is to define new challenges and contributions made by physiotherapy using technology. Eighty documents related to research, validation and/or the ascertaining of different types of hardware, software or both were reviewed in prominent areas. The authors used the following scales: in the area of diagnosis, Fried's phenotype model of frailty and a model based on trials for the design of devices. The technologies developed that are based on these models accounted for 55% and 45% of cases respectively. In the area of prevention, the results proved similar regarding the use of wireless sensors with cameras (35.71%), and Kinect™ sensors (28.57%) to analyze movements and postures that indicate a risk of falling. In the area of care, results were found referring to the use of different motion, physiological and environmental wireless sensors (46,15%), i.e. so-called smart homes. In the area of treatment, the results show with a percentage of 37.5% that the Nintendo® Wii™ console is the most used tool for treating frailty in elderly persons. Further work needs to be carried out to reduce the gap existing between technology, frail elderly persons, healthcare professionals and carers to bring together the different views about technology. This need raises the challenge of developing and implementing technology in physiotherapy via serious games that may via play and connectivity help to improve the functional capacity, general health and quality of life of frail individuals.

Building Bridges for Innovation in Ageing: Synergies between Action Groups of the EIP on AHA

The Strategic Implementation Plan of the European Innovation Partnership on Active and Healthy Ageing (EIP on AHA) proposed six Action Groups. After almost three years of activity, many achievements have been obtained through commitments or collaborative work of the Action Groups. However, they have often worked in silos and, consequently, synergies between Action Groups have been proposed to strengthen the triple win of the EIP on AHA. The paper presents the methodology and current status of the Task Force on EIP on AHA synergies. Synergies are in line with the Action Groups' new Renovated Action Plan (2016-2018) to ensure that their future objectives are coherent and fully connected. The outcomes and impact of synergies are using the Monitoring and Assessment Framework for the EIP on AHA (MAFEIP). Eight proposals for synergies have been approved by the Task Force: Five cross-cutting synergies which can be used for all current and future synergies as they consider overarching domains (appropriate polypharmacy, citizen empowerment, teaching and coaching on AHA, deployment of synergies to EU regions, Responsible Research and Innovation), and three cross-cutting synergies focussing on current Action Group activities (falls, frailty, integrated care and chronic respiratory diseases).

A Robot-Based Tool for Physical and Cognitive Rehabilitation of Elderly People Using Biofeedback

This publication presents a complete description of a technological solution system for the physical and cognitive rehabilitation of elderly people through a biofeedback system, which is combined with a Lego robot. The technology used was the iOS's (iPhone Operating System) Objective-C programming language and its XCode programming environment; and SQLite in order to create the database. The biofeedback system is implemented by the use of two biosensors which are, in fact, a Microsoft band 2 in order to register the user's heart rate and a MYO sensor to detect the user's arm movement. Finally, the system was tested with seven elderly people from La Santa y Real Casa de la Misericordia nursing home in Bilbao. The statistical assessment has shown that the users are satisfied with the usability of the system, with a mean score of 79.29 on the System Usability Scale (SUS) questionnaire.

HClass: Automatic classification tool for health pathologies using artificial intelligence techniques

The classification of subjects' pathologies enables a rigorousness to be applied to the treatment of certain pathologies, as doctors on occasions play with so many variables that they can end up confusing some illnesses with others. Thanks to Machine Learning techniques applied to a health-record database, it is possible to make using our algorithm. hClass contains a non-linear classification of either a supervised, non-supervised or semi-supervised type. The machine is configured using other techniques such as validation of the set to be classified (cross-validation), reduction in features (PCA) and committees for assessing the various classifiers. The tool is easy to use, and the sample matrix and features that one wishes to classify, the number of iterations and the subjects who are going to be used to train the machine all need to be introduced as inputs. As a result, the success rate is shown either via a classifier or via a committee if one has been formed. A 90% success rate is obtained in the ADABoost classifier and 89.7% in the case of a committee (comprising three classifiers) when PCA is applied. This tool can be expanded to allow the user to totally characterise the classifiers by adjusting them to each classification use.

Analysis of the sleep quality of elderly people using biomedical signals

This paper presents a technical solution that analyses sleep signals captured by biomedical sensors to find possible disorders during rest. Specifically, the method evaluates electrooculogram (EOG) signals, skin conductance (GSR), air flow (AS), and body temperature. Next, a quantitative sleep quality analysis determines significant changes in the biological signals, and any similarities between them in a given time period. Filtering techniques such as the Fourier transform method and IIR filters process the signal and identify significant variations. Once these changes have been identified, all significant data is compared and a quantitative and statistical analysis is carried out to determine the level of a person's rest. To evaluate the correlation and significant differences, a statistical analysis has been calculated showing correlation between EOG and AS signals (p=0,005), EOG, and GSR signals (p=0,037) and, finally, the EOG and Body temperature (p=0,04). Doctors could use this information to monitor changes within a patient.

Comprehensive verticality analysis and web-based rehabilitation system for people with multiple sclerosis with supervised medical monitoring

People with Multiple Sclerosis (MS) need regular physical activities along with medical treatment despite their ability or disability level. However, poorly performed exercises could aggravate muscle imbalances and worsen their health. The goal of our work is to create a comprehensive system, encompassing a face-to-face sessions performed by MS patients one day a week at the medical center with exercises at home the rest of the week through a web platform in combination with a tracking tool to analyze the position of patients during exercise and correct them in real-time. The whole system is currently testing during six months with ten participants, five persons with MS and 5 professionals related with MS. Two tests, the Functional Independence Measure and the Berg Balance Scale will be act as a barometer for measuring the degree of independence obtained by the people with MS and also the validity of the whole system as a rehabilitation tool. Preliminary results about the usability of the system using SUS scale, 72 and 76 points over 100 (patients and professionals respectively), demonstrate that our system is usable for both patients and professionals.