Search

Federated learning is a very convenient approach for scenarios where (i) the exchange of data implies privacy concerns and/or (ii) a quick reaction is needed. In smart healthcare systems, both aspects are usually required. In this paper, we work on the first scenario, where preserving privacy is key and, consequently, building a unique and massive medical image data set by fusing different data sets from different medical institutions or research centers (computation nodes) is not an option. We propose an ensemble federated learning (EFL) approach that is based on the following characteristics: First, each computation node works with a different data set (but of the same type). They work locally and apply an ensemble approach combining eight well-known CNN models (densenet169, mobilenetv2, xception, inceptionv3, vgg16, resnet50, densenet121, and resnet152v2) on Chest X-ray images. Second, the best two local models are used to create a local ensemble model that is shared with a central node. Third, the ensemble models are aggregated to obtain a global model, which is shared with the computation nodes to continue with a new iteration. This procedure continues until there are no changes in the best local models. We have performed different experiments to compare our approach with centralized ones (with or without an ensemble approach). The results conclude that our proposal outperforms these ones in Chest X-ray images (achieving an accuracy of 96.63%) and offers very competitive results compared to other proposals in the literature. A source code is provided at the Code Ocean repository: https://codeocean.com/capsule/0530602/tree Xunta de Galicia | Ref. (Centro de investigación de Galicia accreditation 2019– 2022) Universidade de Vigo/CISUG Ministerio de Ciencia e Innovación | Ref. PID2020-113795RB-C33

Intelligent systems are increasingly present in various areas of society, gaining special relevance in healthcare environments. In this work, grounded on previous developments proposed by the authors, the evolution and improvement of a novel intelligent system focused on the diagnosis of obstructive sleep apnea (OSA) is addressed. To do this, starting from two packages of information of a heterogeneous nature, and deploying a set of Machine Learning classification algorithms, focused each of them on different levels of the apnea-hypopnea index (AHI), as well as a set of cascaded expert systems, it is possible to obtain a series of risk metric pairs (Statistical Risk, Symbolic Risk) for each AHI level, understood as a warning forecast associated with the early detection of the pathology. The risk indicators of each pair are subsequently aggregated by means of a symbolic inference system, whose knowledge base was determined using the automatic rule generation approach proposed by Wang and Mendel. At the output of each inference system, a risk indicator is obtained for each AHI level, the Apnea Risk, whose interpretation makes it possible to discriminate between patients who could suffer OSA and those who do not, as well as to generate the appropriate recommendations. For the initial tests of the system, the design and development of a specific software artifact was carried out using data from 4,400 patients from the Álvaro Cunqueiro Hospital in Vigo, obtaining when applied to the test set AUC values within the range 0.74–0.88, which invites optimism and points to the benefits expected from the architecture of the proposed intelligent system.

Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort. European Union | Ref. 875406 Fondo Europeo de Desarrollo Regional (FEDER) Xunta de Galicia

The occurrence of atheroma plaques in the arteries can eventually obstruct them, leading to diseases such as atherosclerosis, which can cause, among others, a myocardial infarction or a stroke. As a consequence, it is necessary to shorten the time spent in locating and reconstructing the atheroma plaque that can be developed in an artery. This localization is usually conducted manually from the contours located on the cross-sectional radiographs of the artery and then reconstructed by creating the volumes using different techniques. This paper presents a 3-D reconstruction of the atheroma plaque by applying an image processing algorithm ad-hoc developed in order to obtain the boundaries of the atheroma, from a set of intravascular ultrasound images. The advantage of the approach developed in this paper is that it can be implemented in common medical procedures, as an important complementary decision-support tool. By reconstructing the atheroma instead of the artery, this work provides a different approach to improve its location and treatment. Results presented herein can be implemented in machine-learning-based algorithms, able to predict the growth and extent of incipient atheroma plaques, which ultimately contribute to an early detection of this pathology.

The high prevalence of Alzheimer-type dementia and the limitations of traditional neuropsychological tests motivate the introduction of new cognitive assessment methods. We discuss the validation of an all-digital, ecological and non-intrusive e-health application for the early detection of cognitive impairment, based on artificial intelligence for patient classification, and more specifically on machine learning algorithms. To evaluate the discrimination power of this application, a cross-sectional pilot study was carried out involving 30 subjects: 10 health control subjects (mean age: 75.62 years); 14 individuals with mild cognitive impairment (mean age: 81.24 years) and 6 early-stage Alzheimer’s patients (mean age: 80.44 years). The study was carried out in two separate sessions in November 2021 and January 2022. All participants completed the study, and no concerns were raised about the acceptability of the test. Analysis including socio-demographics and game data supports the prediction of participants’ cognitive status using machine learning algorithms. According to the performance metrics computed, best classification results are obtained a Multilayer Perceptron classifier, Support Vector Machines and Random Forest, respectively, with weighted recall values >= 0.9784 ± 0.0265 and F1-score = 0.9764 ± 0.0291. Furthermore, thanks to hyper-parameter optimization, false negative rates were dramatically reduced. Shapley’s additive planning (SHAP) applied according to the eXplicable AI (XAI) method, made it possible to visually and quantitatively evaluate the importance of the different features in the final classification. This is a relevant step ahead towards the use of machine learning and gamification to early detect cognitive impairment. In addition, this tool was designed to support self-administration, which could be a relevant aspect in confinement situations with limited access to health professionals. However, further research is required to identify patterns that may help to predict or estimate future cognitive damage and normative data. Ministerio de Ciencia e Innovación | Ref. PID2020-115137RB-I00

Trabajo de Fin de Grado. Grado en Ingeniería Informática. Curso académico 2021-2022., [ES]Vivimos en un mundo cada vez más globalizado, dónde viajar cada vez es más fácil y la tecnología nos permite estar siempre informados. Esto provoca que muchos ciudadanos estén periodos de tiempo fuera de su residencia habitual, por eso muchos donantes de sangre reciben las alertas del Servicio Nacional de Salud tarde o en hospitales muy lejanos a su ubicación actual. En la actualidad, existen aplicaciones orientadas al usuario, dónde se puede registrar cómo donante de sangre y ver los puntos de donación cercanos, sin embargo, la mayoría de estas aplicaciones son gestionadas por Comunidades Autónomas, esto causa un uso ineficiente del sistema de donaciones debido a que, en caso de urgencia, los mensajes de necesidad de sangre no llegan a todas los donantes disponibles en la zona. Este fue el punto de partida de este proyecto, ofrecer una plataforma que pone en contacto al Servicio Nacional de Salud y los donantes de sangre, para que, en caso de urgencia, se puedan emitir alertas para solicitar la donación en los hospitales en los que sea necesario, permitiendo al usuario de forma simple, cambiar su ubicación cuando viaje. A su vez, permite al Servicio Nacional de Salud tener constancia del número de donantes de sangre en cada provincia en tiempo real, así como su tipo de sangre, permitiendo incluso comunicarse con el usuario a través de un chat interno. De esta forma se incrementa la eficiencia en la emisión de alertas, maximizando el número de donantes posible que puedan acudir a donar cuando sea necesario., [EN]We live in an increasingly globalized world, where travel is becoming easier and easier and technology allows us to be always informed. This causes many citizens to spend periods of time away from their usual residence, so many blood donors receive alerts from the National Health Service late or in hospitals far away from their current location. Currently, there are user-oriented applications, where you can register as a blood donor and see nearby donation points, however, most of these applications are managed by Autonomous Communities, this causes an inefficient use of the donation system because, in case of emergency, the messages of blood need do not reach all available donors in the area. This was the starting point of this project, to offer a platform that puts the National Health Service and blood donors in contact, so that, in case of emergency, alerts can be issued to request donation in the hospitals where it is necessary, allowing the user to simply change their location when traveling. In turn, it allows the National Health Service to keep track of the number of blood donors in each province in real time, as well as their blood type, even allowing communication with the user through an internal chat. This increases the efficiency in the issuing of alerts, maximizing the number of donors who can come to donate when needed.

Obstructive sleep apnea (OSA), characterized by recurrent episodes of partial or total obstruction of the upper airway during sleep, is currently one of the respiratory pathologies with the highest incidence worldwide. This situation has led to an increase in the demand for medical appointments and specific diagnostic studies, resulting in long waiting lists, with all the health consequences that this entails for the affected patients. In this context, this paper proposes the design and development of a novel intelligent decision support system applied to the diagnosis of OSA, aiming to identify patients suspected of suffering from the pathology. For this purpose, two sets of heterogeneous information are considered. The first one includes objective data related to the patient’s health profile, with information usually available in electronic health records (anthropometric information, habits, diagnosed conditions and prescribed treatments). The second type includes subjective data related to the specific OSA symptomatology reported by the patient in a specific interview. For the processing of this information, a machine-learning classification algorithm and a set of fuzzy expert systems arranged in cascade are used, obtaining, as a result, two indicators related to the risk of suffering from the disease. Subsequently, by interpreting both risk indicators, it will be possible to determine the severity of the patients’ condition and to generate alerts. For the initial tests, a software artifact was built using a dataset with 4400 patients from the Álvaro Cunqueiro Hospital (Vigo, Galicia, Spain). The preliminary results obtained are promising and demonstrate the potential usefulness of this type of tool in the diagnosis of OSA. Xunta de Galicia | Ref. ED481A-2020/038

Deep Learning (DL) has attracted a lot of attention in the field of medical image analysis because of its higher performance in image classification when compared to previous state-of-the-art techniques. In addition, a recent meta-analysis found that the diagnostic performance of DL models is equivalent to that of health-care professionals. In this scenario, a lot of research using DL for polyp detection and classification have been published showing promising results in the last five years. Our work aims to review the most relevant studies from a technical point of view, focusing on the low-level details for the implementation of the DL models. To do so, this review analyzes the published research covering aspects like DL architectures, training strategies, data augmentation, transfer learning, or the features of the datasets used and their impact on the performance of the models. Additionally, comparative tables summarizing the main aspects analyzed in this review are publicly available at https://github.com/sing-group/deep-learning-colonoscopy. Xunta de Galicia | Ref. ED431C2018 / 55-GRC Ministerio de Economía, Industria y Competitividad | Ref. DPI2017-87494-R Xunta de Galicia | Ref. ED481A-2019/299 Xunta de Galicia | Ref. ED481B 2016 / 068-0 Instituto de Salud Carlos III | Ref. PI11 / 00094 Instituto de Salud Carlos III | Ref. PI17 / 00837

Colorectal cancer is one of the most frequent malignancies. Colonoscopy is the de facto standard for precancerous lesion detection in the colon, i.e., polyps, during screening studies or after facultative recommendation. In recent years, artificial intelligence, and especially deep learning techniques such as convolutional neural networks, have been applied to polyp detection and localization in order to develop real-time CADe systems. However, the performance of machine learning models is very sensitive to changes in the nature of the testing instances, especially when trying to reproduce results for totally different datasets to those used for model development, i.e., inter-dataset testing. Here, we report the results of testing of our previously published polyp detection model using ten public colonoscopy image datasets and analyze them in the context of the results of other 20 state-of-the-art publications using the same datasets. The F1-score of our recently published model was 0.88 when evaluated on a private test partition, i.e., intra-dataset testing, but it decayed, on average, by 13.65% when tested on ten public datasets. In the published research, the average intra-dataset F1-score is 0.91, and we observed that it also decays in the inter-dataset setting to an average F1-score of 0.83. Ministerio de Ciencia y Competitividad, Gobierno de España | Ref. DPI2017-87494-R Ministerio de Ciencia y Competitividad, Gobierno de España | Ref. PDC2021-121644-I00 Xunta de Galicia | Ref. ED481A-2019/299 Xunta de Galicia | Ref. ED431C2018/55-GRC Fundação para a Ciência e a Tecnologia | Ref. 2020.00515.CEECIND

Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722). Ministerio de Ciencia y Competitividad y Ministerio de Ciencia e Innovación | Ref. DPI2017-87494-R Ministerio de Ciencia y Competitividad y Ministerio de Ciencia e Innovación | Ref. PDC2021-121644-I00 Xunta de Galicia | Ref. ED431C2018/55-GRC Xunta de Galicia | Ref. ED431C 2022/03-GRC

Obstructive Sleep Apnea (OSA) is a chronic sleep-related pathology characterized by recurrent episodes of total or partial obstruction of the upper airways during sleep. It entails a high impact on the health and quality of life of patients, affecting more than one thousand million people worldwide, which has resulted in an important public health concern in recent years. The usual diagnosis involves performing a sleep test, cardiorespiratory polygraphy, or polysomnography, which allows characterizing the pathology and assessing its severity. However, this procedure cannot be used on a massive scale in general screening studies of the population because of its execution and implementation costs; therefore, causing an increase in waiting lists which would negatively affect the health of the affected patients. Additionally, the symptoms shown by these patients are often unspecific, as well as appealing to the general population (excessive somnolence, snoring, etc.), causing many potential cases to be referred for a sleep study when in reality are not suffering from OSA. This paper proposes a novel intelligent clinical decision support system to be applied to the diagnosis of OSA that can be used in early outpatient stages, quickly, easily, and safely, when a suspicious OSA patient attends the consultation. Starting from information related to the patient’s health profile (anthropometric data, habits, comorbidities, or medications taken), the system is capable of determining different alert levels of suffering from sleep apnea associated with different apnea-hypopnea index (AHI) levels to be studied. To that end, a series of automatic learning algorithms are deployed that, working concurrently, together with a corrective approach based on the use of an Adaptive Neuro-Based Fuzzy Inference System (ANFIS) and a specific heuristic algorithm, allow the calculation of a series of labels associated with the different levels of AHI previously indicated. For the initial software implementation, a data set with 4600 patients from the Álvaro Cunqueiro Hospital in Vigo was used. The results obtained after performing the proof tests determined ROC curves with AUC values in the range 0.8–0.9, and Matthews correlation coefficient values close to 0.6, with high success rates. This points to its potential use as a support tool for the diagnostic process, not only from the point of view of improving the quality of the services provided, but also from the best use of hospital resources and the consequent savings in terms of costs and time. Xunta de Galicia | Ref. ED481A-2020/038

It is of great interest to develop and introduce new techniques to automatically and efficiently analyze the enormous amount of data generated in today’s hospitals, using state-of-the-art artificial intelligence methods. Patients readmitted to the ICU in the same hospital stay have a higher risk of mortality, morbidity, longer length of stay, and increased cost. The methodology proposed to predict ICU readmission could improve the patients’ care. The objective of this work is to explore and evaluate the potential improvement of existing models for predicting early ICU patient readmission by using optimized artificial intelligence algorithms and explainability techniques. In this work, XGBoost is used as a predictor model, combined with Bayesian techniques to optimize it. The results obtained predicted early ICU readmission (AUROC of 0.92 ± 0.03) improves state-of-the-art consulted works (whose AUROC oscillate between 0.66 and 0.78). Moreover, we explain the internal functioning of the model by using Shapley Additive Explanation-based techniques, allowing us to understand the model internal performance and to obtain useful information, as patient-specific information, the thresholds from which a feature begins to be critical for a certain group of patients, and the feature importance ranking. Agencia Gallega de Innovación | Ref. IN845D-2020/29 Agencia Gallega de Innovación | Ref. IN607B-2021/18

Background: Telemedicine has been incorporated into daily clinical practice. The purpose of this paper is to evaluate the economic impact of electronic consultation as a means of referring patients between Primary Care (PC) services and the referral Cardiology Service (CS) of a tertiary hospital, in particular, the cost of reduced air pollution. Methods: The direct and indirect costs associated with all the interconsultations between PC and a CS of a tertiary hospital were analyzed under a universal single act model versus a prior e-consultation model that selected patients who would later attend the single-act consultation. The cost of pollution from private motor vehicle travel by road has been analyzed with a Cobb–Douglas cost function. Results: The total cost per patient, including the costs associated with death, represented a saving in the model with e-consultation of 25.6%. The economic value for the reduction of contamination would be EUR 12.86 per patient. Conclusions: The introduction of e-consultation in the outpatient management of patients referred from PC to a CS, helps to reduce direct and indirect costs for the patient and the Health Care System. The cost of pollution associated with the trips explains the total cost to a greater extent, except for the first face-to-face consultation.

Psoriasis is a chronic skin disease that affects 125 million people worldwide and, particularly, 2% of the Spanish population, characterized by the appearance of skin lesions due to a growth of the epidermis that is seven times larger than usual. Its diagnosis and monitoring are based on the use of methodologies for measuring the severity and extent of these spots, and this includes a large subjective component. For this reason, this paper presents an automatic method for characterizing psoriasis images that is divided into four parts: image preparation or pre-processing, feature extraction, classification of the lesions, and the obtaining of parameters. The methodology proposed in this work covers different digital-image processing techniques, namely, marker-based image delimitation, hair removal, nipple detection, lesion contour detection, areal-measurement-based lesion classification, as well as lesion characterization by means of red and white intensity. The results obtained were also endorsed by a professional dermatologist. This methodology provides professionals with a common software tool for monitoring the different existing typologies, which proved satisfactory in the cases analyzed for a set of 20 images corresponding to different types of lesions. Ministerio de Economía, Industria y Competitividad | Ref. TIN2016-76770-R

Trabajo de Fin de Grado. Grado en Ingeniería Informática. Curso académico 2020-2021., [ES]El proyecto consiste en crear una app móvil que ayude a una persona con diabetes. La aplicación móvil permite llevar un diario de la actividad física, niveles de azúcar en sangre, ingesta de hidratos de carbono, unidades de insulina, estado emocional y el ciclo menstrual. El proyecto ha sido desarrolla do dentro del convenio de colaboración de la facultad de ciencias con el observatorio hp, [EN]The project consists of creating a mobile app that helps a person with diabe tes. The mobile app allows to keep a diary of physical activity, blood sugar levels, carbohydrate intake, insulin units, emotional state and menstrual cycle. The project has been developed within the collaboration agreement between the faculty of science and the hp observatory

Trabajo de Fin de Grado. Grado en Ingeniería Informática. Curso académico 2020-2021., [ES]Este trabajo de fin de grado, como su nombre indica, consta de la investigación y realización de un sistema para la detección de patologías médicas mediante el análisis de imágenes. Esta aplicación web ayuda a los especialistas médicos detectar el cáncer de mama y registrarlo en una base de datos. La detección de esta enfermedad se centra en el análisis de imágenes previamente introducidas por un médico, estas se guardarán en un directorio con el nombre del DNI y un subdirectorio con la fecha de la realización del análisis. La inteligencia artificial que se ha creado con el propósito de la detección de esta enfermedad analizará las distintas imágenes introducidas y dará un resultado de la paciente. Además de esto, se podrá acceder a los distintos análisis que se han realizado a las pacientes, ver los resultados y las imágenes analizadas., [EN]This end-of-degree project, as its name suggests, consists of the research and development of a system for the detection of medical pathologies through image analysis. This web application helps medical specialists to detect breast cancer and register it in a database. The detection of this disease focuses on the analysis of images previously entered by a doctor, these will be stored in a directory with the name of the DNI and a subdirectory with the date of the analysis. The artificial intelligence that has been created for the purpose of detecting this disease will analyze the different images entered and give a result of the patient. In addition to this, it will be possible to access the different analyses that have been performed on the patients, view the results and the analyzed images.

Hospital-acquired Infections (HAIs) surveillance, defined as the systematic collection of data related to a certain health event, is considered an essential dimension for a prevention HAI program to be effective. In recent years, new automated HAI surveillance methods have emerged with the wide adoption of electronic health records (EHR). Here we present the validation results against the gold standard of HAIs diagnosis of the InNoCBR system deployed in the Ourense University Hospital Complex (Spain). Acting as a totally autonomous system, InNoCBR achieves a HAI sensitivity of 70.83% and a specificity of 97.76%, with a positive predictive value of 77.24%. The kappa index for infection type classification is 0.67. Sensitivity varies depending on infection type, where bloodstream infection attains the best value (93.33%), whereas the respiratory infection could be improved the most (53.33%). Working as a semi-automatic system, InNoCBR reaches a high level of sensitivity (81.73%), specificity (99.47%), and a meritorious positive predictive value (94.33%). Xunta de Galicia | Ref. ED431C2018/55-GRC

Trabajo de Fin de Grado. Grado en Ingeniería Informática. Curso académico 2020-2021., [ES]El objetivo principal de este proyecto es la creación de un programa para una plataforma universal, en este caso PC, accesible para usuarios de cualquier tipo de perfil, desde la que poder jugar y consultar su evolución de forma sencilla y cómoda. La aplicación permitirá la gestión de diferentes usuarios desde el mismo ordenador, manteniendo separadas sus puntuaciones y ajustes personales. Además, el programa contará con un modo Tour, que guíe al jugador de forma secuencial por los diferentes juegos recogidos en la aplicación para facilitarle una rutina diaria de forma sencilla., [EN] The main goal of this project is the creation of a program launchable in a universal platform, PC in this case, that can be reached by users of different profiles, allowing users to play and check their evolution easily. The program will be able to manage different users from the same computer, keeping their scores and personal preferences separated. Also, the program will have a Tour mode, that drives the player through the different games sequentially to make him easier the creation of a daily training routine.

Trabajo de fin de Grado. Grado en Física. Curso académico 2019-2020, [ES}El estudio de las redes complejas supone una parte fundamental de la modelización matemática. Una red está formada por nodos y aristas, además de una serie de conceptos sobre la teoría de grafos que se presentarán en la primera parte del trabajo, aportando a la idea de grado y distribución de grado mayor importancia. Se introducen en la segunda parte diferentes tipos de redes complejas, así como sus principales propiedades. Las redes que se estudiarán son: homogéneas, aleatorias, de mundo pequeño y de escala libre. La siguiente parte del trabajo muestra un análisis de distintos modos de propagación de una epidemia, introduciendo los modelos SI, SIS y SIR. Para terminar, se vinculan ambas áreas, mostrando la unión entre la distribución de grado (característica de cada tipo de red) con la evolución de epidemias según el modelo a estudiar., [EN}The study of complex networks is a fundamental part of mathematics modelization. The networks are constructed by nodes and edges, and other concepts of graph theory that it is going to be studied at the first part of this work, giving more importance the idea of degree and degree distribution. In the second part, it is introducing some differents kinds of complex networks and their principal properties. The studies networks are: homogeneous, random networks, small-world and scale-free. The work continues with an analysis of differents spread models of an epidemic, appearing the SI, SIS and SIR models. At the last part, both áreas will be linked, appearing the conection between the degree distribution (something caracteristic of each network) and the epidemic evolution depending of the analysed model.

© 2020 by the authors., Bifidobacteria are among the most abundant microorganisms inhabiting the intestine of humans and many animals. Within the genus Bifidobacterium, several beneficial effects have been attributed to strains belonging to the subspecies Bifidobacterium longum subsp. longum and Bifidobacterium longum subsp. infantis, which are often found in infants and adults. The increasing numbers of sequenced genomes belonging to these two subspecies, and the availability of novel computational tools focused on predicting glycolytic abilities, with the aim of understanding the capabilities of degrading specific carbohydrates, allowed us to depict the potential glycoside hydrolases (GH) of these bacteria, with a focus on those GH profiles that differ in the two subspecies. We performed an in silico examination of 188 sequenced B. longum genomes and depicted the commonly present and strain-specific GHs and GH families among representatives of this species. Additionally, GH profiling, genome-based and 16S rRNA-based clustering analyses showed that the subspecies assignment of some strains does not properly match with their genetic background. Furthermore, the analysis of the potential GH component allowed the distinction of clear GH patterns. Some of the GH activities, and their link with the two subspecies under study, are further discussed. Overall, our in silico analysis poses some questions about the suitability of considering the GH activities of B. longum subsp. longum and B. longum subsp. infantis to gain insight into the characterization and classification of these two subspecies with probiotic interest., The research included in the present work was funded by the grants AGL2016-78311-R (funded by AEI/FEDER, UE), RTI2018-095021-J-I00 (funded by MCIU/AEI/FEDER, UE), and IDI/2018/000236 (funded by PCTI Gobierno del Principado de Asturias/FEDER, UE). This study was supported by the Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia) under the scope of the strategic funding of ED431C2018/55-GRC Competitive Reference Group, the “Centro singular de investigación de Galicia” (accreditation 2019-2022) and the European Union (European Regional Development Fund—ERDF)-Ref. ED431G2019/06, and the Portuguese Foundation for Science and Technology (FCT) under the scope of the strategic funding of UIDB/04469/2020 unit and BioTecNorte operation (NORTE-01-0145-FEDER-000004) funded by the European Regional Development Fund under the scope of Norte2020—Programa Operacional Regional do Norte.

This paper presents the usability assessment of the design of an Internet of Medical Things (IoMT) system for older adults, the evaluation, using heuristics, was held early on the design process to assess potential problems with the system and was found to be an efficient method to find issues with the application design and led to significant usability improvements on the IoMT platform.

Lactobacillus genus includes both probiotic and representative strains of the human gut microbiota. Independent studies have reported on the anti-inflammatory properties of different Lactobacillus strains, although we are far from understanding the underlying molecular interplay. In this work we show that a daily administration of Lactobacillus acidophilus DSM20079T (DSM20079) to healthy piglets resulted in plasmatic increases of the anti-inflammatory IL10, whilst IL12 and the pro-inflammatory ratio IL12+TNF/IL10 decreased. The extracellular protein fraction of DSM20079 was identified as the responsible for the crosstalk interaction that elicited these tolerogenic effects. This strain was able to activate innate immune pathways in dendritic cells and to decrease the production of pro-inflammatory cytokines in both CD4+/CD8+ T cell subsets in healthy donors and in Crohns Disease patients. The tolerogenic effect exerted by the extracellular proteins of this strain suggests their potential use as coadjutant for therapeutic applications targeting chronic inflammatory illnesses., Our work is supported by the Spanish “Programa Estatal de Investigación, Desarrollo e Inovación Orientada a los Retos de la Sociedad” (grant AGL2016-78311-R); the Asociación Española Contra el Cancer (“Obtención de péptidos bioactivos contra el Cáncer ColoRectal a partir de secuencias genéticas de microbiomas intestinales”, Grant PS-2016) and by the Asturias Regional Plan I+D+i for research groups (FYCYT-IDI/2018/000236). This study was also supported by the Portuguese Foundation for Science and Technology (FCT) under the scope of the strategic funding of UID/BIO/04469/2013 unit and COMPETE 2020 (POCI-01-0145-FEDER006684). SING group thanks CITI (Centro de Investigación, Transferencia e Innovación) from University of Vigo for hosting its IT infrastructure. LJR was supported by the Principado de Asturias, PCTI 2018–2020 (GRUPIN: IDI2018-000237) and FEDER. This work was partially supported by the Consellería de Educación, Universidades e Formación Profesional (Xunta de Galicia) under the scope of the strategic funding of ED431C2018/55-GRC Competitive Reference Group., info:eu-repo/semantics/publishedVersion

Breast cancer is currently one of the main causes of death and tumoral diseases in women. Even if early diagnosis processes have evolved in the last years thanks to the popularization of mammogram tests, nowadays, it is still a challenge to have available reliable diagnosis systems that are exempt of variability in their interpretation. To this end, in this work, the design and development of an intelligent clinical decision support system to be used in the preventive diagnosis of breast cancer is presented, aiming both to improve the accuracy in the evaluation and to reduce its uncertainty. Through the integration of expert systems (based on Mamdani-type fuzzy-logic inference engines) deployed in cascade, exploratory factorial analysis, data augmentation approaches, and classification algorithms such as k-neighbors and bagged trees, the system is able to learn and to interpret the patient’s medical-healthcare data, generating an alert level associated to the danger she has of suffering from cancer. For the system’s initial performance tests, a software implementation of it has been built that was used in the diagnosis of a series of patients contained into a 130-cases database provided by the School of Medicine and Public Health of the University of Wisconsin-Madison, which has been also used to create the knowledge base. The obtained results, characterized as areas under the ROC curves of 0.95–0.97 and high success rates, highlight the huge diagnosis and preventive potential of the developed system, and they allow forecasting, even when a detailed and contrasted validation is still pending, its relevance and applicability within the clinical field. Xunta de Galicia | Ref. ED481A-2020/038

Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic analysis of these data has many practical applications in patient monitoring, including the optimization of alarm systems for alerting healthcare personnel. In this paper, explainable machine learning techniques are used for this purpose, with a methodology based on age-stratification, boosting classifiers, and Shapley Additive Explanations (SHAP) proposed. The methodology is evaluated using MIMIC-III, an ICU patient research database. The results show that the proposed model can predict mortality within the ICU with AUROC values of 0.961, 0.936, 0.898, and 0.883 for age groups 18–45, 45–65, 65–85 and 85+, respectively. By using SHAP, the features with the highest impact in predicting mortality for different age groups and the threshold from which the value of a clinical feature has a negative impact on the patient’s health can be identified. This allows ICU alarms to be improved by identifying the most important variables to be sensed and the threshold values at which the health personnel must be warned. Axencia Galega de Innovacion | Ref. IN845D-2020/29

With the increase in global life expectancy and the advance of technology, the creation of age-friendly environments is a priority in the design of new products for elderly people healthcare. This paper presents a proposal for a real-time health monitoring system of older adults living in geriatric residences. This system was developed to help caregivers to have a better control in monitoring the health of their patients and have closer communication with their patients&rsquo, family members. To validate the feasibility and effectiveness of this proposal, a prototype was built, using a biometric bracelet connected to a mobile application, which allows real-time visualization of all the information generated by the sensors (heart rate, body temperature, and blood oxygenation) in the bracelet. Using these data, caregivers can make decisions about the health status of their patients. The evaluation found that the users perceived the system to be easy to learn and use, providing initial evidence that our proposal could improve the quality of the adult&rsquo, s healthcare.

Este proyecto describe el diseño de una arquitectura software que permite el control, con fines terapéuticos, de un exoesqueleto de miembros inferiores. El sistema está especialmente dirigido a personas de avanzada edad, con problemas de movilidad, de manera que un rehabilitador transmite los movimientos a través de una interfaz natural y éstos son traducidos en consignas de posición para las extremidades del robot. La solución planteada permite la ejecución simultanea e independiente de diferentes componentes, todos ellos interconectados bajo un middleware donde la información es intercambiada con transparencia. Concretamente, un sistema operativo robótico, ROS, resuelve los problemas asociados al hardware y facilita la tarea de control, ejecutándose por medio de nodos. El prototipo ha sido conveniente probado y los resultados obtenidos analizados, permitiendo así concluir una serie de ventajas e inconvenientes, así como un conjunto de futuras revisiones. Escuela Técnica Superior de Ingeniería Industrial Universidad Politécnica de Cartagena

Este trabajo tiene como objetivo principal analizar la relación entre los índices de variabilidad de frecuencia cardíaca y la respuesta emocional. Para ello, se pretende diseñar y construir una base de datos especializada, estudiar las aplicaciones prácticas en diferentes campos, como la publicidad o la psiquiatría, y mejorar la herramienta VARVI (heart rate Variability Analysis in Response to Visual stImuli), para el análisis de la variabilidad de la frecuencia cardíaca en respuesta a diferentes estímulos visuales. Este traballo ten como obxectivo principal analizar a relación entre os índices de variabilidade de frecuencia cardíaca e a resposta emocional. Para iso, preténdese deseñar e construír unha base de datos especializada, estudar as aplicacións prácticas en diferentes campos, como a publicidade ou a psiquiatría, e mellorar a ferramenta VARVI (heart rate Variability Analysis in Response to Visual stImuli), para a análise da variabilidade da frecuencia cardíaca en resposta a diferentes estímulos visuais. The main goal of this work is to analyze the relationship among the different heart rate variability indices and the emotional response. To do this task, a specialized database will be designed and constructed. Results achieved will be studied in several practical applications in different fields, such as Psychiatry or Marketing. Improvement of the VARVI (heart rate Variability Analysis in Response to Visual stImuli) tool, aimed at analyzing the response of the heart rate variability to different visual stimuli, will also be performed.

In the world, many older adults are living alone for most of the day. This work propose the use of the television set, a medium well known by seniors, to improve the way that seniors and their caregivers can track daily activities such as medication intakes reminders. Two evaluations were held, a heuristic usability assessment early on the design process and an evaluation of the technology adoption. Both evaluations generated initial evidence that the system supported elders in achieving a better quality of life.

Modern bioinformatics and computational biology are fields of study driven by the availability of effective software required for conducting appropriate research tasks. Apart from providing reliable and fast implementations of different data analysis algorithms, these software applications should also be clear and easy to use through proper user interfaces, providing appropriate data management and visualization capabilities. In this regard, the user experience obtained by interacting with these applications via their Graphical User Interfaces (GUI) is a key factor for their final success and real utility for researchers. Despite the existence of different packages and applications focused on advanced data visualization, there is a lack of specific libraries providing pertinent GUI components able to help scientific bioinformatics software developers. To that end, this paper introduces GC4S, a bioinformatics-oriented collection of high-level, extensible, and reusable Java GUI elements specifically designed to speed up bioinformatics software development. Within GC4S, developers of new applications can focus on the specific GUI requirements of their projects, relying on GC4S for generalities and abstractions. GC4S is free software distributed under the terms of GNU Lesser General Public License and both source code and documentation are publicly available at http://www.sing-group.org/gc4s H. López-Fernández is supported by a post-doctoral fellowship from Xunta de Galicia (ED481B 2016/068-0). SING group thanks CITI (Centro de Investigación, Transferencia e Innovación) from University of Vigo for hosting its IT infrastructure.

The elderly population is the fastest growing age group in our society; it also presents the most problems related to abandonment, social isolation and poverty. One of the main health problem faced by this population age group is falls, as they are the leading cause of death related accidents. In this research work it is proposed a solution not only to detect falls, but to also detect health problems and incorrect activities that propitiate these falls, increasing the safety and quality of life of its users. This is achieved through the application of various advanced algorithms, which allow the definition of intelligent human motion profiles based on inertial and physiological sensors. In addition, the proposed solution has a very low impact on the user's day-to-day life, a large autonomy and reduced deployment costs. The major contributions of thesis were conducted in the following areas: Ambient Assisted Living (AAL), Body Area Networks (BAN) and Intelligent Systems (IS). La tendencia de envejecimiento de la población, más significativa en países desarrollados, constituye una alerta ante la necesidad de adaptación de las tecnologías existentes para los desafíos que este fenómeno acarrea. En este sentido, un estudio realizado en 2008 por Eurostat prevé que el porcentaje de personas con más de 65 años aumentará de un 17.1% a un 30% en el 2060, pasando de existir 84,6 millones de personas mayores de 65 años en 2008, a 151,1 millones en 2060. Paralelamente, un informe realizado en el año 2004 por la HealthEvidence Network para la Organización Mundial de la Salud establece que el 30% de la población con edad superior a 65 años sufre una caída por lo menos una vez al año. Este porcentaje aumenta significativamente según avanza en rango estudiado, alcanzando un 50% en personas mayores de 80 años. Estas caídas se traducen en la principal causa de los accidentes que conllevan el ingreso de personas mayores en centros hospitalarios, así como en la principal causa de muertes acarreadas por heridas. En relación con estas situaciones de riesgo, es necesario realizar una distinción entre caídas en las cuales la persona mayor se encuentra acompañada por alguien, de aquellas en las que la persona se encuentra sola y queda en una situación donde le resulta imposible pedir ayuda, permaneciendo grandes períodos de tiempo sin los debidos cuidados médicos. En algunos casos estos períodos se prolongan en el tiempo y conllevan inevitablemente la muerte de la persona. Un caso típico que representa el escenario descrito anteriormente es el suceso de un Accidente Vascular Cerebral (AVC), donde el período de tiempo para prestar una ayuda eficaz es bastante reducido y la persona mayor no dispone de capacidad para pedir auxilio. Teniendo en cuenta todos estos hechos, en la comunidad científica se han llevado a cabo distintos trabajos preliminares con el objetivo de dar una respuesta adecuada al problema de las caídas, sobre todo en aquellos escenarios donde las personas se encuentran solas. A este respecto, se destaca el desarrollo de nuevos dispositivos para la adquisición de datos (nodos sensoriales), el diseño de una arquitectura de comunicaciones escalable y la implementación de algoritmos específicos para la detección de caídas normales, entendiendo por normal aquella caída donde la persona no choca contra ningún objeto y su movimiento no se interrumpe durante el desplome. En este contexto, el problema surge cuando existe una desaceleración intermedia causada, por ejemplo, porque la persona intenta evitar la caída agarrándose a algún objeto presente en la estancia. Este problema representa el punto de partida de la presente propuesta, que pretende explorar las tecnologías existentes y adaptarlas para la detección eficaz de este tipo de caídas mediante la construcción de un modelo evolutivo de detección. El modo en el que se pretende resolver el problema planteado es mediante la creación de perfiles de movimiento evolutivos, generados mediante el empleo de agentes inteligentes. A través de la utilización de perfiles, se espera no sólo mejorar la detección de caídas normales, sino identificar caídas que no eran detectables en la actualidad como caídas con obstáculos o caídas causadas por enfermedades súbitas (como por ejemplo el AVC). Además, la utilización de agentes inteligentes permitirá analizar de forma constante las variaciones de los perfiles de movimiento, siendo de utilidad para diagnosticar deterioros de la postura del individuo y prevenir la posible ocurrencia de caídas. A tendencia de envellecemento da poboación, mais significativa en países desenvolvidos, constitúe unha alerta ante a necesidade de adaptación das tecnoloxías existentes para os desafíos que este fenómeno posúe. Neste senso, un estudo realizado no 2008 por Eurostat prevé que a porcentaxe de persoas con mais de 65 anos aumentará dun 17.1% a un 30% no 2060, pasando de existir 84,6 millóns de persoas maiores de 65 años en 2008, a 151,1 millóns en 2060. Paralelamente, un informe realizado no ano 2004 pola HealthEvidence Network para a Organización Mundial da Saúde establece que o 30% da poboación con idade superior a 65 anos sofre una caída polo menos una vez ó año. Este porcentaxe aumenta de xeito significativo segundo avanza o rango estudado, alcanzando un 50% en persoas maiores de 80 anos. Estas caídas tradúcense na principal causa dos accidentes que teñen como causa o ingreso de persoas maiores en centros hospitalarios, así como na principal causa de mortes causadas por feridas. En relación con estas situacións de risco, é necesario realizar unha distinción entre caídas nas que a persoa maior se atopa acompañada por alguén, de aquelas nas que a persoa se atopa soa e queda nunha situación na que lle resulta imposible pedir axuda, permanecendo grandes períodos de tempo sen os debidos coidados médicos. Nalgúns casos estes períodos prolónganse no tempo e teñen como consecuencia inevitable la morte da persoa. Un caso típico que representa o escenario descrito anteriormente é o suceso dun Accidente Vascular Cerebral (AVC), onde o período de tempo para prestar unha axuda eficaz é bastante reducido e a persoa maior non dispón de capacidade para pedir auxilio. Tendo en conta todos estes feitos, na comunidade científica leváronse a cabo distintos traballos preliminares co obxectivo de dar unha resposta adecuada ó problema das caídas, sobre todo en aqueles escenarios onde as persoas se atopan solas. A este respecto, destácase o desenvolvemento de novos dispositivos para a adquisición de datos (nodos sensoriais), o deseño dunha arquitectura de comunicacións ampliable e a implementación de algoritmos específicos para a detección de caídas normais, entendendo por normal aquela caída onde a persoa no tropeza contra ningún obxecto e o seu movemento non se interrompe durante o seu desplome. Neste contexto, o problema xurde cando existe unha desaceleración intermedia causada, por exemplo, porque a persoa intenta evitar a caída agarrándose a algún obxecto presente na estancia. Este problema representa o punto de partida da presente proposta, que pretende explorar as tecnoloxías existentes e adaptalas para a detección eficaz deste tipo de caídas mediante a construción dun modelo evolutivo de detección. O modo no que se pretende resolver o problema plantexado é mediante a creación de perfís de movemento evolutivos, xerados mediante o emprego de axentes intelixentes. A través da utilización de perfís, se espera non so mellorar a detección de caídas normais, senón identificar caídas que non eran detectables na actualidade como caídas con obstáculos ou caídas causadas por enfermidades súbitas (como por exemplo o AVC). Ademais, a utilización de axentes intelixentes permitirá analizar de forma constante as variacións dos perfís de movemento, sendo de utilidade para diagnosticar problemas na postura do individuo e prever a posible ocorrencia de caídas.

In Mexico, many seniors are alone for most of the day or live in public nursing homes. Simple interaction with computer systems is required for older people. This is why we propose the exploration of a medium well known by seniors, such as the television (TV). The primary objective of this study is to improve the quality of life of seniors through an easier reminder system, using the television set. A technological platform was designed based on interactive television, through which seniors and their caregivers can have a better way to track their daily activities. Finally, an evaluation of the technology adoption was performed with 50 seniors living in two public nursing homes. The evaluation found that the elderly perceived the system as useful, easy to use, and they had a positive attitude and good intention to use it. This helped to generate initial evidence that the system supported them in achieving a better quality of life, by reminding them to take their medications and increasing their rate of attendance to their medical appointments.

Los sucesos adversos que tienen lugar durante el proceso de asistencia médica suelen ser el centro de atención de todas las organizaciones sanitarias. Dentro de esta categoría se encuentran las infecciones nosocomiales (INs), que tienen un peso notable en la morbimortalidad. En concreto, las INs representan una morbilidad evitable que constituye una carga social y económica significativa para el sistema de salud, y que en ocasiones conlleva consecuencias graves para el paciente. En este sentido, su detección representa un objetivo prioritario en los programas de seguridad de pacientes y de calidad hospitalaria. En relación con la detección de este tipo de sucesos, existen situaciones en las que el experto tiene dificultades para encontrar evidencias y aplicar reglas que permitan la identificación correcta de INs. En este sentido, el presente trabajo de investigación propone un sistema inteligente capaz de llevar a cabo la búsqueda inicial, y posterior clasificación, de casos de IN en el ámbito hospitalario. El modelo propuesto utiliza un sistema de razonamiento basado en casos que incorpora un motor de reglas para el manejo de conocimiento directamente proporcionado por el experto o extraído de forma automática a partir de casos previamente clasificados. Adicionalmente, incorpora técnicas de procesamiento de lenguaje natural para la generación de un conjunto de clasificadores, encargados de valorar automáticamente aquellas evidencias almacenadas como texto libre que contienen indicios de infección. La justificación de la hipótesis defendida en este trabajo, la definición de un sistema inteligente capaz de identificar posibles casos de IN y realizar una clasificación posterior del tipo de infección subyacente, se realiza de manera experimental probando diferentes estrategias, lo que permite el análisis cuantitativo y cualitativo del grado de efectividad del sistema desarrollado ante el problema propuesto.

[ES] Los millones de neuronas localizadas en el cerebro reciben constantemente información que elaboran y procesan para, en muchos casos, tomar decisiones. Esta fuente de información está constituida principalmente por los sentidos. A su vez, el sistema nervioso central puede tomar la iniciativa y actuar sobre diversos órganos de los sentidos para regular su rendimiento. Una gran parte de la información que recibe el cerebro humano procede del sistema de recepción visual. El sistema de información óptica está especializado en captar y procesar la información de las variaciones del campo electromagnético que se producen en nuestro entorno., [EN] The millions of neurons located in the brain are constantly receiving information they produce and processed for in many cases, make decisions. This source consists mainly of the senses. In turn, the central nervous system can take the initiative and act on various organs of the senses to regulate its performance.Much of the information received by the human brain comes from the visual input system. The optical information system specialized in capturing and processing information from the electromagnetic field variations that occur in our environment.