RESUMEN

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, responsible for 32% of all deaths, with the annual death toll projected to reach 23.3 million by 2030. The early identification of individuals at high risk of CVD is crucial for the effectiveness of preventive strategies. In the field of deep learning, automated CVD-detection methods have gained traction, with phonocardiogram (PCG) data emerging as a valuable resource. However, deep-learning models rely on large datasets, which are often challenging to obtain. In recent years, data augmentation has become a viable solution to the problem of scarce data. In this paper, we propose a novel data-augmentation technique named PCGmix, specifically engineered for the augmentation of PCG data. The PCGmix algorithm employs a process of segmenting and reassembling PCG recordings, incorporating meticulous interpolation to ensure the preservation of the cardinal diagnostic features pertinent to CVD detection. The empirical assessment of the PCGmix method was utilized on a publicly available database of normal and abnormal heart-sound recordings. To evaluate the impact of data augmentation across a range of dataset sizes, we conducted experiments encompassing both limited and extensive amounts of training data. The experimental results demonstrate that the novel method is superior to the compared state-of-the-art, time-series augmentation. Notably, on limited data, our method achieves comparable accuracy to the no-augmentation approach when trained on 31% to 69% larger datasets. This study suggests that PCGmix can enhance the accuracy of deep-learning models for CVD detection, especially in data-constrained environments.

RESUMEN

The objective of the URBANITE project is to design an open-data, open-source, smart-city framework to enhance the decision-making processes in European cities. The framework's basis is a robust and user-friendly simulation tool that is supplemented with several innovative service modules. One of the modules, a multi-output, machine-learning unit, is deployed on the simulation results, enabling city officials to more effectively analyse vast quantities of data, discern patterns and trends, and so facilitate advanced policy decisions. The city's decision makers define potential city scenarios, key performance indicators, and a utility function, while the module assists in identifying the policy that is best aligned with the stipulated constraints and preferences. One of the main improvements is a speeding up of the policy testing for the decision makers, reducing the time needed for one policy verification from 3 hours to around 10 seconds. The system was evaluated for Bilbao's Moyua area, where it suggested strategies that could result in a decrease in emissions of more than 5% CO2, NOx, PM in the selected area and a broader part of the city with a machine-learning accuracy of 91%. The system was therefore able to provide valuable insights into effective policies for restricting private traffic in specific districts and identifying the most advantageous times for these restrictions.

RESUMEN

Falls by the elderly pose considerable health hazards, leading not only to physical harm but a number of other related problems. A timely alert about a deteriorating gait, as an indication of an impending fall, can assist in fall prevention. In this investigation, a comprehensive comparative analysis was conducted between a commercially available mobile phone system and two wristband systems: one commercially available and another representing a novel approach. Each system was equipped with a singular three-axis accelerometer. The walk suggestive of a potential fall was induced by special glasses worn by the participants. The same standard machine-learning techniques were employed for the classification with all three systems based on a single three-axis accelerometer, yielding a best average accuracy of 86%, a specificity of 88%, and a sensitivity of 86% via the support vector machine (SVM) method using a wristband. A smartphone, on the other hand, achieved a best average accuracy of 73% also with an SVM using only a three-axis accelerometer sensor. The significance analysis of the mean accuracy, sensitivity, and specificity between the innovative wristband and the smartphone yielded a p-value of 0.000. Furthermore, the study applied unsupervised and semi-supervised learning methods, incorporating principal component analysis and t-distributed stochastic neighbor embedding. To sum up, both wristbands demonstrated the usability of wearable sensors in the early detection and mitigation of falls in the elderly, outperforming the smartphone.

Asunto(s)

RESUMEN

One key task in the early fight against the COVID-19 pandemic was to plan non-pharmaceutical interventions to reduce the spread of the infection while limiting the burden on the society and economy. With more data on the pandemic being generated, it became possible to model both the infection trends and intervention costs, transforming the creation of an intervention plan into a computational optimization problem. This paper proposes a framework developed to help policy-makers plan the best combination of non-pharmaceutical interventions and to change them over time. We developed a hybrid machine-learning epidemiological model to forecast the infection trends, aggregated the socio-economic costs from the literature and expert knowledge, and used a multi-objective optimization algorithm to find and evaluate various intervention plans. The framework is modular and easily adjustable to a real-world situation, it is trained and tested on data collected from almost all countries in the world, and its proposed intervention plans generally outperform those used in real life in terms of both the number of infections and intervention costs.

Asunto(s)

RESUMEN

Hidradenitis suppurativa (HS) is a recurrent inflammatory skin disease with a complex etiopathogenesis whose treatment poses a challenge in the clinical practice. Here, we present a novel integrated pipeline produced by the European consortium BATMAN (Biomolecular Analysis for Tailored Medicine in Acne iNversa) aimed at investigating the molecular pathways involved in HS by developing new diagnosis algorithms and building cellular models to pave the way for personalized treatments. The objectives of our european Consortium are the following: (1) identify genetic variants and alterations in biological pathways associated with HS susceptibility, severity and response to treatment; (2) design in vitro two-dimensional epithelial cell and tri-dimensional skin models to unravel the HS molecular mechanisms; and (3) produce holistic health records HHR to complement medical observations by developing a smartphone application to monitor patients remotely. Dermatologists, geneticists, immunologists, molecular cell biologists, and computer science experts constitute the BATMAN consortium. Using a highly integrated approach, the BATMAN international team will identify novel biomarkers for HS diagnosis and generate new biological and technological tools to be used by the clinical community to assess HS severity, choose the most suitable therapy and follow the outcome.

Asunto(s)

RESUMEN

From 2018 to 2021, the Sussex-Huawei Locomotion-Transportation Recognition Challenge presented different scenarios in which participants were tasked with recognizing eight different modes of locomotion and transportation using sensor data from smartphones. In 2019, the main challenge was using sensor data from one location to recognize activities with sensors in another location, while in the following year, the main challenge was using the sensor data of one person to recognize the activities of other persons. We use these two challenge scenarios as a framework in which to analyze the effectiveness of different components of a machine-learning pipeline for activity recognition. We show that: (i) selecting an appropriate (location-specific) portion of the available data for training can improve the F1 score by up to 10 percentage points (p. p.) compared to a more naive approach, (ii) separate models for human locomotion and for transportation in vehicles can yield an increase of roughly 1 p. p., (iii) using semi-supervised learning can, again, yield an increase of roughly 1 p. p., and (iv) temporal smoothing of predictions with Hidden Markov models, when applicable, can bring an improvement of almost 10 p. p. Our experiments also indicate that the usefulness of advanced feature selection techniques and clustering to create person-specific models is inconclusive and should be explored separately in each use-case.

Asunto(s)

RESUMEN

The EU PlatformUptake project's main goal is to investigate the usage of EU open and partly-open platforms in active and healthy aging (AHA) and ambient-assisted living (AAL) domains, from a software viewpoint. The aim of the project was to provide tools for a deeper interpretation and examination of the platforms, gather user feedback, and use it to improve the state-of-the-art approach in the AHA and AAL domains, and define instructions to enhance the platforms within the recommended order. The emphasis is on the software viewpoint for decision makers. In this paper, we present (i) the PlatformUptake methodology for AHA open platform assessments and its main objectives; (ii) clustering of the analyzed platforms; and (iii) the taxonomies generated from the text descriptions of the chosen platforms. With the use of the clustering tools, we present which platforms could be grouped together due to their similarities. Different numbers of clusters were obtained with two clustering approaches, resulting in the most informative two and four cluster groups. The platforms could be rather neatly presented in this way and, thus, potentially guide future platform structuring. Moreover, taxonomies, i.e., decision trees of platforms, were generated to easily determine each specific platform or to find platforms with the desired properties. Altogether, the computer comprehension of the platforms may be important additions to the human way of dealing with the AHA platforms, influencing future design, publications, related work, and research.

RESUMEN

The COVID-19 pandemic affected the whole world, but not all countries were impacted equally. This opens the question of what factors can explain the initial faster spread in some countries compared to others. Many such factors are overshadowed by the effect of the countermeasures, so we studied the early phases of the infection when countermeasures had not yet taken place. We collected the most diverse dataset of potentially relevant factors and infection metrics to date for this task. Using it, we show the importance of different factors and factor categories as determined by both statistical methods and machine learning (ML) feature selection (FS) approaches. Factors related to culture (e.g., individualism, openness), development, and travel proved the most important. A more thorough factor analysis was then made using a novel rule discovery algorithm. We also show how interconnected these factors are and caution against relying on ML analysis in isolation. Importantly, we explore potential pitfalls found in the methodology of similar work and demonstrate their impact on COVID-19 data analysis. Our best models using the decision tree classifier can predict the infection class with roughly 80% accuracy.

Asunto(s)

RESUMEN

To further extend the applicability of wearable sensors in various domains such as mobile health systems and the automotive industry, new methods for accurately extracting subtle physiological information from these wearable sensors are required. However, the extraction of valuable information from physiological signals is still challenging-smartphones can count steps and compute heart rate, but they cannot recognize emotions and related affective states. This study analyzes the possibility of using end-to-end multimodal deep learning (DL) methods for affect recognition. Ten end-to-end DL architectures are compared on four different datasets with diverse raw physiological signals used for affect recognition, including emotional and stress states. The DL architectures specialized for time-series classification were enhanced to simultaneously facilitate learning from multiple sensors, each having their own sampling frequency. To enable fair comparison among the different DL architectures, Bayesian optimization was used for hyperparameter tuning. The experimental results showed that the performance of the models depends on the intensity of the physiological response induced by the affective stimuli, i.e., the DL models recognize stress induced by the Trier Social Stress Test more successfully than they recognize emotional changes induced by watching affective content, e.g., funny videos. Additionally, the results showed that the CNN-based architectures might be more suitable than LSTM-based architectures for affect recognition from physiological sensors.

Asunto(s)

RESUMEN

Falls are a significant threat to the health and independence of elderly people and represent an enormous burden on the healthcare system. Successfully predicting falls could be of great help, yet this requires a timely and accurate fall risk assessment. Gait abnormalities are one of the best predictive signs of underlying locomotion conditions and precursors of falls. The advent of wearable sensors and wrist-worn devices provides new opportunities for continuous and unobtrusive monitoring of gait during daily activities, including the identification of unexpected changes in gait. To this end, we present in this paper a novel method for determining gait abnormalities based on a wrist-worn device and a deep neural network. It integrates convolutional and bidirectional long short-term memory layers for successful learning of spatiotemporal features from multiple sensor signals. The proposed method was evaluated using data from 18 subjects, who recorded their normal gait and simulated abnormal gait while wearing impairment glasses. The data consist of inertial measurement unit (IMU) sensor signals obtained from smartwatches that the subjects wore on both wrists. Numerous experiments showed that the proposed method provides better results than the compared methods, achieving 88.9% accuracy, 90.6% sensitivity, and 86.2% specificity in the detection of abnormal walking patterns using data from an accelerometer, gyroscope, and rotation vector sensor. These results indicate that reliable fall risk assessment is possible based on the detection of walking abnormalities with the use of wearable sensors on a wrist.

Asunto(s)

RESUMEN

BACKGROUND: Blood pressure (BP) measurements have been used widely in clinical and private environments. Recently, the use of ECG monitors has proliferated; however, they are not enabled with BP estimation. We have developed a method for BP estimation using only electrocardiogram (ECG) signals. METHODS: Raw ECG data are filtered and segmented, and, following this, a complexity analysis is performed for feature extraction. Then, a machine-learning method is applied, combining a stacking-based classification module and a regression module for building systolic BP (SBP), diastolic BP (DBP), and mean arterial pressure (MAP) predictive models. In addition, the method allows a probability distribution-based calibration to adapt the models to a particular user. RESULTS: Using ECG recordings from 51 different subjects, 3129 30-s ECG segments are constructed, and seven features are extracted. Using a train-validation-test evaluation, the method achieves a mean absolute error (MAE) of 8.64 mmHg for SBP, 18.20 mmHg for DBP, and 13.52 mmHg for the MAP prediction. When models are calibrated, the MAE decreases to 7.72 mmHg for SBP, 9.45 mmHg for DBP and 8.13 mmHg for MAP. CONCLUSION: The experimental results indicate that, when a probability distribution-based calibration is used, the proposed method can achieve results close to those of a certified medical device for BP estimation.

Asunto(s)

RESUMEN

Being able to detect stress as it occurs can greatly contribute to dealing with its negative health and economic consequences. However, detecting stress in real life with an unobtrusive wrist device is a challenging task. The objective of this study is to develop a method for stress detection that can accurately, continuously and unobtrusively monitor psychological stress in real life. First, we explore the problem of stress detection using machine learning and signal processing techniques in laboratory conditions, and then we apply the extracted laboratory knowledge to real-life data. We propose a novel context-based stress-detection method. The method consists of three machine-learning components: a laboratory stress detector that is trained on laboratory data and detects short-term stress every 2min; an activity recognizer that continuously recognizes the user's activity and thus provides context information; and a context-based stress detector that uses the outputs of the laboratory stress detector, activity recognizer and other contexts, in order to provide the final decision on 20-min intervals. Experiments on 55days of real-life data showed that the method detects (recalls) 70% of the stress events with a precision of 95%.

Asunto(s)

RESUMEN

Although wearable accelerometers can successfully recognize activities and detect falls, their adoption in real life is low because users do not want to wear additional devices. A possible solution is an accelerometer inside a wrist device/smartwatch. However, wrist placement might perform poorly in terms of accuracy due to frequent random movements of the hand. In this paper we perform a thorough, large-scale evaluation of methods for activity recognition and fall detection on four datasets. On the first two we showed that the left wrist performs better compared to the dominant right one, and also better compared to the elbow and the chest, but worse compared to the ankle, knee and belt. On the third (Opportunity) dataset, our method outperformed the related work, indicating that our feature-preprocessing creates better input data. And finally, on a real-life unlabeled dataset the recognized activities captured the subject's daily rhythm and activities. Our fall-detection method detected all of the fast falls and minimized the false positives, achieving 85% accuracy on the first dataset. Because the other datasets did not contain fall events, only false positives were evaluated, resulting in 9 for the second, 1 for the third and 15 for the real-life dataset (57 days data).

Asunto(s)

RESUMEN

We developed a new machine learning-based method in order to facilitate the manufacturing processes of pharmaceutical products, such as tablets, in accordance with the Process Analytical Technology (PAT) and Quality by Design (QbD) initiatives. Our approach combines the data, available from prior production runs, with machine learning algorithms that are assisted by a human operator with expert knowledge of the production process. The process parameters encompass those that relate to the attributes of the precursor raw materials and those that relate to the manufacturing process itself. During manufacturing, our method allows production operator to inspect the impacts of various settings of process parameters within their proven acceptable range with the purpose of choosing the most promising values in advance of the actual batch manufacture. The interaction between the human operator and the artificial intelligence system provides improved performance and quality. We successfully implemented the method on data provided by a pharmaceutical company for a particular product, a tablet, under development. We tested the accuracy of the method in comparison with some other machine learning approaches. The method is especially suitable for analyzing manufacturing processes characterized by a limited amount of data.

Asunto(s)

RESUMEN

A system for diagnosing health problems from gait patterns of elderly to support their independent living is proposed in this paper. Motion capture system, which consists of tags attached to the body and sensors situated in the apartment, is used to capture gait of elderly. Position of the tags is acquired by the sensors and the resulting time series of position coordinates are analyzed with machine learning algorithms in order to recognize the specific health problem. We propose novel features for training a machine learning classifier that classifies the user's gait into four health problems and a normal health state. Results showed that decision tree classifier was able to reach 95% of classification accuracy using 7 tags and 5 mm standard deviation of noise. Neural network outperformed it with classification accuracy over 99% using 8 tags with 0-20 mm noise. Control panel prototype has been developed to provide explanation of the automatic diagnosis.

Asunto(s)