Search

The use of wearable devices has increased substantially in recent years. This, together with the rise of telemedicine, has led to the use of these types of devices in the healthcare field. In this work, we carried out a detailed study on the use of these devices (regarding the general trends); we analyzed the research works and devices marketed in the last 10 years. This analysis extracted relevant information on the general trend of use, as well as more specific aspects, such as the use of sensors, communication technologies, and diseases. A comparison was made between the commercial and research aspects linked to wearables in the healthcare field, and upcoming trends were analyzed.

Nowadays, the study of the gait by analyzing the distribution of plantar pressure is a well-established technique. The use of intelligent insoles allows real-time monitoring of the user. Thus, collecting and analyzing information is a more accurate process than consultations in so-called gait laboratories. Most of the previous published studies consider the composition and operation of these insoles based on resistive sensors. However, the use of capacitive sensors could provide better results, in terms of linear behavior under the pressure exerted. This behavior depends on the properties of the dielectric used. In this work, the design and implementation of an intelligent plantar insole composed of capacitive sensors is proposed. The dielectric used is a polydimethylsiloxane (PDMS)-based composition. The sensorized plantar insole developed achieves its purpose as a tool for collecting pressure in different areas of the sole of the foot. The fundamentals and details of the composition, manufacture, and implementation of the insole and the system used to collect data, as well as the data samples, are shown. Finally, a comparison of the behavior of both insoles, resistive and capacitive sensor-equipped, is made. The prototype presented lays the foundation for the development of a tool to support the diagnosis of gait abnormalities. Junta de Andalucía US-1263715

Medical image segmentation can be implemented using Deep Learning methods with fast and efficient segmentation networks. Single-board computers (SBCs) are difficult to use to train deep networks due to their memory and processing limitations. Specific hardware such as Google's Edge TPU makes them suitable for real time predictions using complex pre-trained networks. In this work, we study the performance of two SBCs, with and without hardware acceleration for fundus image segmentation, though the conclusions of this study can be applied to the segmentation by deep neural networks of other types of medical images. To test the benefits of hardware acceleration, we use networks and datasets from a previous published work and generalize them by testing with a dataset with ultrasound thyroid images. We measure prediction times in both SBCs and compare them with a cloud based TPU system. The results show the feasibility of Machine Learning accelerated SBCs for optic disc and cup segmentation obtaining times below 25 milliseconds per image using Edge TPUs., Preprint of paper published in Engineering Applications of Artificial Intelligence

Nowadays, the percentage of time that the population spends sitting has increased substantially due to the use of computers as the main tool for work or leisure and the increase in jobs with a high office workload. As a consequence, it is common to suffer musculoskeletal pain, mainly in the back, which can lead to both temporary and chronic damage. This pain is related to holding a posture during a prolonged period of sitting, usually in front of a computer. This work presents a IoT posture monitoring system while sitting. The system consists of a device equipped with Force Sensitive Resistors (FSR) that, placed on a chair seat, detects the points where the user exerts pressure when sitting. The system is complemented with a Machine Learning model based on Artificial Neural Networks, which was trained to recognize the neutral correct posture as well as the six most frequent postures that involve risk of damage to the locomotor system. In this study, data was collected from 12 participants for each of the seven positions considered, using the developed sensing device. Several neural network models were trained and evaluated in order to improve the classification effectiveness. Hold-Out technique was used to guide the training and evaluation process. The results achieved a mean accuracy of 81% by means of a model consisting of two hidden layers of 128 neurons each. These results demonstrate that is feasible to distinguish different sitting postures using few sensors allocated in the surface of a seat, which implies lower costs and less complexity of the system.

The elderly is a continuous growth sector thanks to the life expectancy increase in Western society. This sector is especially at risk from the appearance of respiratory diseases and, therefore, is the most affected sector in the COVID-19 epidemic. Many of these elderly require continuous care in residences or by specialized caregivers, but these personal contacts put this sector at risk. In this work, an IoT system for elderly remote monitoring is studied, designed, developed and tested. This system is composed by a smart garment that records information from various physiological sensors in order to detect falls, sudden changes in body temperature, heart problems and heat stroke; This information is sent to a cloud server through a gateway located in the patient’s residence, allowing to real-time monitor remotely patient’s activity using a customized App, as well as receiving alerts in dangerous situations. This system has been tested with professional caregivers, obtaining usability and functionality surveys; and, in addition, a detailed power-consumption study has been carried out. The results, compared with other similar systems, demonstrate that the proposed one is useful, usable, works in real time and has a decent power consumption that allows the patient to carry it during all day without charging the battery.

Diagnosis aid systems that use image analysis are currently very useful due to the large workload of health professionals involved in making diagnoses. In recent years, Convolutional Neural Networks (CNNs) have been used to help in these tasks. For this reason, multiple studies that analyze the detection precision for several diseases have been developed. However, many of these works distinguish between only two classes: healthy and with a specific disease. Based on this premise, in this work, we try to answer the questions: When training an image classification system with only two classes (healthy and sick), does this system extract the specific features of this disease, or does it only obtain the features that differentiate it from a healthy patient? Trying to answer these questions, we analyze the particular case of COVID-19 detection. Many works that classify this disease using X-ray images have been published, some of them use two classes (with and without COVID-19), while others include more classes (pneumonia, SARS, influenza, etc.). In this work, we carry out several classification studies with two classes, using test images that do not belong to those classes, in order to try to answer the previous questions. The first studies indicate problems in these two-class systems when using a third class as a test, being classified inconsistently. Deeper studies show that deep learning systems trained with two classes do not correctly extract the characteristics of pathologies, but rather differentiate the classes based on the physical characteristics of the images. After the discussion, we conclude that these two-class trained deep learning systems are not valid if there are other diseases that cause similar symptoms.

Non-verbal communication is essential in the communication process. This means that its lack can cause misinterpretations of the message that the sender tries to transmit to the receiver. With the rise of video calls, it seems that this problem has been partially solved. However, people with cognitive disorders such as those with some kind of Autism Spectrum Disorder (ASD) are unable to interpret non-verbal communication neither live nor by video call. This work analyzes the relationship between some physiological measures (EEG, ECG, and GSR) and the affective state of the user. To do that, some public datasets are evaluated and used for a multiple Deep Learning (DL) system. Each physiological signal is pre-processed using a feature extraction process after a frequency study with the Discrete Wavelet Transform (DWT), and those coefficients are used as inputs for a single DL classifier focused on that signal. These multiple classifiers (one for each signal) are evaluated independently and their outputs are combined in order to optimize the results and obtain additional information about the most reliable signals for classifying the affective states into three levels: low, middle, and high. The full system is carefully detailed and tested, obtaining promising results (more than 95% accuracy) that demonstrate its viability.

Recommender systems are gaining traction in healthcare because they can tailor recommendations based on users' feedback concerning their appreciation of previous health-related messages. However, recommender systems are often not grounded in behavioral change theories, which may further increase the effectiveness of their recommendations. This paper's objective is to describe principles for designing and developing a health recommender system grounded in the I-Change behavioral change model that shall be implemented through a mobile app for a smoking cessation support clinical trial. We built upon an existing smoking cessation health recommender system that delivered motivational messages through a mobile app. A group of experts assessed how the system may be improved to address the behavioral change determinants of the I-Change behavioral change model. The resulting system features a hybrid recommender algorithm for computer tailoring smoking cessation messages. A total of 331 different motivational messages were designed using 10 health communication methods. The algorithm was designed to match 58 message characteristics to each user pro le by following the principles of the I-Change model and maintaining the bene ts of the recommender system algorithms. The mobile app resulted in a streamlined version that aimed to improve the user experience, and this system's design bridges the gap between health recommender systems and the use of behavioral change theories. This article presents a novel approach integrating recommender system technology, health behavior technology, and computer-tailored technology. Future researchers will be able to build upon the principles applied in this case study. European Union's Horizon 2020 Research and Innovation Programme under Grant 681120

The spread of the SARS-CoV-2 virus has made the COVID-19 disease a worldwide epidemic. The most common tests to identify COVID-19 are invasive, time consuming and limited in resources. Imaging is a non-invasive technique to identify if individuals have symptoms of disease in their lungs. However, the diagnosis by this method needs to be made by a specialist doctor, which limits the mass diagnosis of the population. Image processing tools to support diagnosis reduce the load by ruling out negative cases. Advanced artificial intelligence techniques such as Deep Learning have shown high effectiveness in identifying patterns such as those that can be found in diseased tissue. This study analyzes the effectiveness of a VGG16-based Deep Learning model for the identification of pneumonia and COVID-19 using torso radiographs. Results show a high sensitivity in the identification of COVID-19, around 100%, and with a high degree of specificity, which indicates that it can be used as a screening test. AUCs on ROC curves are greater than 0.9 for all classes considered.

Abnormal foot postures can be measured during the march by plantar pressures in both dynamic and static conditions. These detections may prevent possible injuries to the lower limbs like fractures, ankle sprain or plantar fasciitis. This information can be obtained by an embedded instrumented insole with pressure sensors and a low-power microcontroller. However, these sensors are placed in sparse locations inside the insole, so it is not easy to correlate manually its values with the gait type, that is why a machine learning system is needed. In this work, we analyse the feasibility of integrating a machine learning classifier inside a low-power embedded system in order to obtain information from the user&rsquo, s gait in real-time and prevent future injuries. Moreover, we analyse the execution times, the power consumption and the model effectiveness. The machine learning classifier is trained using an acquired dataset of 3000+ steps from 6 different users. Results prove that this system provides an accuracy over 99% and the power consumption tests obtains a battery autonomy over 25 days.

Falls have become a relevant public health issue due to their high prevalence and negative effects in elderly people. Wearable fall detector devices allow the implementation of continuous and ubiquitous monitoring systems. The effectiveness for analyzing temporal signals with low energy consumption is one of the most relevant characteristics of these devices. Recurrent neural networks (RNNs) have demonstrated a great accuracy in some problems that require analyzing sequential inputs. However, getting appropriate response times in low power microcontrollers remains a difficult task due to their limited hardware resources. This work shows a feasibility study about using RNN-based deep learning models to detect both falls and falls&rsquo, risks in real time using accelerometer signals. The effectiveness of four different architectures was analyzed using the SisFall dataset at different frequencies. The resulting models were integrated into two different embedded systems to analyze the execution times and changes in the model effectiveness. Finally, a study of power consumption was carried out. A sensitivity of 88.2% and a specificity of 96.4% was obtained. The simplest models reached inference times lower than 34 ms, which implies the capability to detect fall events in real-time with high energy efficiency. This suggests that RNN models provide an effective method that can be implemented in low power microcontrollers for the creation of autonomous wearable fall detection systems in real-time.

Abnormal foot postures during gait are common sources of pain and pathologies of the lower limbs. Measurements of foot plantar pressures in both dynamic and static conditions can detect these abnormal foot postures and prevent possible pathologies. In this work, a plantar pressure measurement system is developed to identify areas with higher or lower pressure load. This system is composed of an embedded system placed in the insole and a user application. The instrumented insole consists of a low-power microcontroller, seven pressure sensors and a low-energy bluetooth module. The user application receives and shows the insole pressure information in real-time and, finally, provides information about the foot posture. In order to identify the different pressure states and obtain the final information of the study with greater accuracy, a Deep Learning neural network system has been integrated into the user application. The neural network can be trained using a stored dataset in order to obtain the classification results in real-time. Results prove that this system provides an accuracy over 90% using a training dataset of 3000+ steps from 6 different users.

Colorectal cancer is the third most frequently diagnosed malignancy in the world. To prevent this disease, polyps, the principal precursor, are removed during a colonoscopy. Automatic detection of polyps in this technique could play an important role to assist doctors for achieving an accurate diagnosis. In this work, we apply a state-of-the-art Deep Learning algorithm called Faster Regional Convolutional Neural Network to each colonoscopy frame in order to detect the presence of polyps. The proposed detection system contains two main stages: (1) processing of the colonoscopy frames for training and testing datasets generation, where artifacts are extracted and the number of images in the dataset is augmented; and (2) the Neural Network model, which performs feature extraction over the frames in order to detect polyps within the frames. After training the algorithm under different conditions, our result shows that the proposed system detection has a precision of 80.31%, a recall of 75.37%, an accuracy of 71.99% and a specificity of 65.70%. Ministerio de Economía y Competitividad TEC2016-77785-P

Breast cancer is one of the most frequent causes of mortality in women. For the early detection of breast cancer, the mammography is used as the most efficient technique to identify abnormalities such as tumors. Automatic detection of tumors in mammograms has become a big challenge and can play a crucial role to assist doctors in order to achieve an accurate diagnosis. State-of-the-art Deep Learning algorithms such as Faster Regional Convolutional Neural Networks are able to determine the presence of an object and also its position inside the image in a reduced computation time. In this work, we evaluate these algorithms to detect tumors in mammogram images and propose a detection system that contains: (1) a preprocessing step performed on mammograms taken from the Digital Database for Screening Mammography (DDSM) and (2) the Neural Network model, which performs feature extraction over the mammograms in order to locate tumors within each image and classify them as malignant or benign. The results obtained show that the proposed algorithm has an accuracy of 97.375%. These results show that the system could be very useful for aiding physicians when detecting tumors from mammogram images. Ministerio de Economía y Competitividad TEC2016-77785-P

Falls are the most common cause of fatal injuries in elderly people, causing even death if there is no immediate assistance. Fall detection systems can be used to alert and request help when this type of accident happens. Certain types of these systems include wearable devices that analyze bio-medical signals from the person carrying it in real time. In this way, Deep Learning algorithms could automate and improve the detection of unintentional falls by analyzing these signals. These algorithms have proven to achieve high effectiveness with competitive performances in many classification problems. This work aims to study 16 Recurrent Neural Networks architectures (using Long Short-Term Memory and Gated Recurrent Units) for falls detection based on accelerometer data, reducing computational requirements of previous research. The architectures have been tested on a labeled version of the publicly available SisFall dataset, achieving a mean F1-score above 0.73 and improving state-of-the-art solutions in terms of network complexity. Ministerio de Economía y Competitivida TEC2016-77785-P

Medical images from different clinics are acquired with different instruments and settings. To perform segmentation on these images as a cloud-based service we need to train with multiple datasets to increase the segmentation independency from the source. We also require an ef cient and fast segmentation network. In this work these two problems, which are essential for many practical medical imaging applications, are studied. As a segmentation network, U-Net has been selected. U-Net is a class of deep neural networks which have been shown to be effective for medical image segmentation. Many different U-Net implementations have been proposed.With the recent development of tensor processing units (TPU), the execution times of these algorithms can be drastically reduced. This makes them attractive for cloud services. In this paper, we study, using Google's publicly available colab environment, a generalized fully con gurable Keras U-Net implementation which uses Google TPU processors for training and prediction. As our application problem, we use the segmentation of Optic Disc and Cup, which can be applied to glaucoma detection. To obtain networks with a good performance, independently of the image acquisition source, we combine multiple publicly available datasets (RIM-One V3, DRISHTI and DRIONS). As a result of this study, we have developed a set of functions that allow the implementation of generalized U-Nets adapted to TPU execution and are suitable for cloud-based service implementation. Ministerio de Economía y Competitividad TEC2016-77785-P

Glioma is a type of brain tumor that causes mortality in many cases. Early diagnosis is an important factor. Typically, it is detected through MRI and then either a treatment is applied, or it is removed through surgery. Deep-learning techniques are becoming popular in medical applications and image-based diagnosis. Convolutional Neural Networks are the preferred architecture for object detection and classification in images. In this paper, we present a study to evaluate the efficiency of using CNNs for diagnosis aids in glioma detection and the improvement of the method when using a clustering method (Fuzzy C-means) for preprocessing the input MRI dataset. Results offered an accuracy improvement from 0.77 to 0.81 when using Fuzzy C-Means. Ministerio de Economía y Competitividad TEC2016-77785-P

Smoking is one of the most avoidable health risk factors, and yet the quitting success rates are low. The usage of tailored health messages to support quitting has been proved to increase quitting success rates. Technology can provide convenient means to deliver tailored health messages. Health recommender systems are information-filtering algorithms that can choose the most relevant health-related items—for instance, motivational messages aimed at smoking cessation—for each user based on his or her profile. The goals of this study are to analyze the perceived quality of an mHealth recommender system aimed at smoking cessation, and to assess the level of engagement with the messages delivered to users via this medium. Patients participating in a smoking cessation program will be provided with a mobile app to receive tailored motivational health messages selected by a health recommender system, based on their profile retrieved from an electronic health record as the initial knowledge source. Patients’ feedback on the messages and their interactions with the app will be analyzed and evaluated following an observational prospective methodology to a) assess the perceived quality of the mobile-based health recommender system and the messages, using the precision and time-to-read metrics and an 18-item questionnaire delivered to all patients who complete the program, and b) measure patient engagement with the mobile-based health recommender system using aggregated data analytic metrics like session frequency and, to determine the individual-level engagement, the rate of read messages for each user. This paper details the implementation and evaluation protocol that will be followed. This study will explore whether a health recommender system algorithm integrated with an electronic health record can predict which tailored motivational health messages patients would prefer and consider to be of a good quality, encouraging them to engage with the system. The outcomes of this study will help future researchers design better tailored motivational message-sending recommender systems for smoking cessation to increase patient engagement, reduce attrition, and, as a result, increase the rates of smoking cessation. The trial was registered at clinicaltrials.org under the ClinicalTrials.gov identifier NCT03206619 on July 2nd 2017. Retrospectively registered.

Background Recommender systems are information retrieval systems that provide users with relevant items (e.g., through messages). Despite their extensive use in the e-commerce and leisure domains, their application in healthcare is still in its infancy. These systems may be used to create tailored health interventions, thus reducing the cost of healthcare and fostering a healthier lifestyle in the population. Objective This paper identifies, categorizes, and analyzes the existing knowledge in terms of the literature published over the past 10 years on the use of health recommender systems for patient interventions. The aim of this study is to understand the scientific evidence generated about health recommender systems, to identify any gaps in this field to achieve the United Nations Sustainable Development Goal 3 (SDG3) (namely, “Ensure healthy lives and promote well-being for all at all ages”), and to suggest possible reasons for these gaps as well as to propose some solutions. Methods We conducted a scoping review, which consisted of a keyword search of the literature related to health recommender systems for patients in the following databases: ScienceDirect, PsycInfo, Association for Computing Machinery, IEEExplore, and Pubmed. Further, we limited our search to consider only English-language journal articles published in the last 10 years. The reviewing process comprised three researchers who filtered the results simultaneously. The quantitative synthesis was conducted in parallel by two researchers, who classified each paper in terms of four aspects—the domain, the methodological and procedural aspects, the health promotion theoretical factors and behavior change theories, and the technical aspects—using a new multidisciplinary taxonomy. Results Nineteen papers met the inclusion criteria and were included in the data analysis, for which thirty-three features were assessed. The nine features associated with the health promotion theoretical factors and behavior change theories were not observed in any of the selected studies, did not use principles of tailoring, and did not assess (cost)-effectiveness. Discussion Health recommender systems may be further improved by using relevant behavior change strategies and by implementing essential characteristics of tailored interventions. In addition, many of the features required to assess each of the domain aspects, the methodological and procedural aspects, and technical aspects were not reported in the studies. Conclusions The studies analyzed presented few evidence in support of the positive effects of using health recommender systems in terms of cost-effectiveness and patient health outcomes. This is why future studies should ensure that all the proposed features are covered in our multidisciplinary taxonomy, including integration with electronic health records and the incorporation of health promotion theoretical factors and behavior change theories. This will render those studies more useful for policymakers since they will cover all aspects needed to determine their impact toward meeting SDG3.

Deep Learning tools are widely used for medical image segmentation. The results produced by these techniques depend to a great extent on the data sets used to train the used network. Nowadays many cloud service providers offer the required resources to train networks and deploy deep learning networks. This makes the idea of segmentation as a cloud-based service attractive. In this paper we study the possibility of training, a generalized configurable, Keras U-Net to test the feasibility of training with images acquired, with specific instruments, to perform predictions on data from other instruments. We use, as our application example, the segmentation of Optic Disc and Cup which can be applied to glaucoma detection. We use two publicly available data sets (RIM-One V3 and DRISHTI) to train either independently or combining their data. Ministerio de Economía y Competitividad TEC2016-77785-P

Falls are one of the most frequent causes of injuries in elderly people. Wearable Fall Detection Systems provided a ubiquitous tool for monitoring and alert when these events happen. Recurrent Neural Networks (RNN) are algorithms that demonstrates a great accuracy in some problems analyzing sequential inputs, such as temporal signal values. However, their computational complexity are an obstacle for the implementation in IoT devices. This work shows a performance analysis of a set of RNN architectures when trained with data obtained using different sampling frequencies. These architectures were trained to detect both fall and fall hazards by using accelerometers and were tested with 10-fold cross validation, using the F1-score metric. The results obtained show that sampling with a frequency of 25Hz does not affect the effectiveness, based on the F1-score, which implies a substantial increase in the performance in terms of computational cost. The architectures with two RNN layers and without a first dense layer had slightly better results than the smallest architectures. In future works, the best architectures obtained will be integrated in an IoT solution to determine the effectiveness empirically. Ministerio de Economía y Competitividad TEC2016-77785-P