Detecting Respiratory Pathologies Using Convolutional Neural Networks and Variational Autoencoders for Unbalancing Data.

The aim of this paper was the detection of pathologies through respiratory sounds. The ICBHI (International Conference on Biomedical and Health Informatics) Benchmark was used. This dataset is composed of 920 sounds of which 810 are of chronic diseases, 75 of non-chronic diseases and only 35 of healthy individuals. As more than 88% of the samples of the dataset are from the same class (Chronic), the use of a Variational Convolutional Autoencoder was proposed to generate new labeled data and other well known oversampling techniques after determining that the dataset classes are unbalanced. Once the preprocessing step was carried out, a Convolutional Neural Network (CNN) was used to classify the respiratory sounds into healthy, chronic, and non-chronic disease. In addition, we carried out a more challenging classification trying to distinguish between the different types of pathologies or healthy: URTI, COPD, Bronchiectasis, Pneumonia, and Bronchiolitis. We achieved results up to 0.993 F-Score in the three-label classification and 0.990 F-Score in the more challenging six-class classification.

Feasibility of Social-Network-Based eHealth Intervention on the Improvement of Healthy Habits among Children.

This study shows the feasibility of an eHealth solution for tackling eating habits and physical activity in the adolescent population. The participants were children from 11 to 15 years old. An intervention was carried out on 139 students in the intervention group and 91 students in the control group, in two schools during 14 weeks. The intervention group had access to the web through a user account and a password. They were able to create friendship relationships, post comments, give likes and interact with other users, as well as receive notifications and information about nutrition and physical activity on a daily basis and get (virtual) rewards for improving their habits. The control group did not have access to any of these features. The homogeneity of the samples in terms of gender, age, body mass index and initial health-related habits was demonstrated. Pre- and post-measurements were collected through self-reports on the application website. After applying multivariate analysis of variance, a significant alteration in the age-adjusted body mass index percentile was observed in the intervention group versus the control group, as well as in the PAQ-A score and the KIDMED score. It can be concluded that eHealth interventions can help to obtain healthy habits. More research is needed to examine the effectiveness in achieving adherence to these new habits.

Improving Engagement of Mild to Moderate Dementia Alzheimer's Disease Patients Using Evidence-Based Visual Cognitive Stimulation Exercises.

INTRODUCTION: Different studies have proven the effectiveness of cognitive stimulation (CS) for people with mild to moderate dementia, but further research is needed to gain insight into how CS interventions should be designed and developed. OBJECTIVES: The objective of this study was to gather and analyze data about the development of a series of CS sessions with Alzheimer's disease (AD) patients, to gain insight into how different individuals engage to different CS activities. METHODS: 24 AD patients with mild to moderate dementia (GDS = 4 and 5) participated in the study. Twelve different sessions were held with a different stimulation exercise each. Information about the achievement and engagement for each of the exercises were recorded for each patient. RESULTS: A significant correlation was found between the global engagement and the GDS level, and between engagement and gender (and also with educational level) for one of the exercises. These results may be useful for designing CS sessions depending on the composition of the group. For example, five exercises got very different engagement results when comparing patients with GDS = 4 and GDS = 5; if the session group consists of patients with both GDS levels, these kinds of exercises should be avoided to gain homogeneity in the engagement and prevent discouragement. CONCLUSIONS: The type and characteristics of CS exercises have an impact on the engagement level of AD patients with mild to moderate dementia. Further studies are necessary to better understand which characteristics of the exercises affect the engagement of the patient according to their particularities. This kind of study may help the design of CS sessions and improve the results obtained.

Friendship and Consumption Networks in Adolescents and Their Relationship to Stress and Cannabis Use Intention.

BACKGROUND: Cannabis is an illegal psychoactive substance that's use is widespread among adolescents. During adolescence, many changes can cause stress. In this phase, the group of friends becomes increasingly important, being a situation of vulnerability for the beginning of cannabis use, either as an escape mechanism or due to peer's influence. Therefore, the purpose of this study is to describe and analyze the structure of the consumption and friendship network, the intention to use cannabis, and the stress in a secondary school class. METHODS: An online platform with validated self-reported questionnaires were used for data collection. RESULTS: The sample consisted of adolescents (n = 20) aged 14-16 from a third-year class of compulsory secondary education in Ponferrada (León, Spain). Significant differences were obtained concerning consumption intention and the different network metrics in both the friendship and consumption networks. Subsequently, the representation of these networks was carried out. CONCLUSIONS: Social Network Analysis is a very useful tool that provides a picture of the context in which adolescents are located. In the consumption network, there are central actors who have not yet consumed cannabis; this is a crucial moment to implement prevention strategies.

Diabetes detection using deep learning techniques with oversampling and feature augmentation.

BACKGROUND AND OBJECTIVE: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential. METHODS: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated. RESULTS: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art. CONCLUSIONS: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.

Stress, Emotional Intelligence and the Intention to Use Cannabis in Spanish Adolescents: Influence of COVID-19 Confinement.

The disease brought about by the SARS-CoV-2, COVID-19 coronavirus has had an unprecedented global impact. Confinement to control the outbreak may have mental health consequences for the most vulnerable in the population, including adolescents. This study aims to describe and analyze the relationships between the stress variables, Emotional Intelligence and the intention to use cannabis in healthy adolescents, before and after the end of the COVID-19 pandemic containment stage. A comparative correlational study was carried out with validated self-completed questionnaires through an online platform. The sample is made up of adolescents (n = 300) aged 13-17 from two different schools in Ponferrada (León, Spain). The analysis of correlation and differences between the groups indicate that confinement has had effects on the mental health of the adolescents, specifically on the emotional manifestations of stress. Furthermore, significant gender differences were found for stress values and Emotional Intelligence. However, no differences have been found for cannabis use intention.

Networks and Emotions in Cooperative Work: A Quasi-Experimental Study in University Nursing and Computer Engineering Students.

University students establish networks that impact on their behavior. Social Network Analysis (SNA) allows us to analyze the reticular structures formed and find patterns of interaction between university students. The main objective of this study was to observe the impact of interdisciplinary collaborative work between nursing and computer engineering students on the collaboration and friendship networks, emotions and performance of the participants. It is a quasi-experimental descriptive study with pre- and post-intervention measurements. The contact networks analyzed showed an increase in density in the post-intervention period. The most central people in the network corresponded with those who considered positive emotions most in their academic environment, while the less central people coincided with those who highlighted negative emotions. Academic performance was only significantly associated in the collaboration network, between this and OutdegreeN. This study shows the impact of interdisciplinary activities on teaching methodologies and the repercussions of emotions on curricular activity.

The consumption of alcohol by adolescent schoolchildren: Differences in the triadic relationship pattern between rural and urban environments.

OBJECTIVE: Excessive alcohol consumption in adolescents is one of the most significant public health problems currently facing society. Social and geographical contexts contribute to the development of alcohol-related behavior in adolescents. The aim of this research is to analyze the social pattern related to alcohol consumption in adolescents based on their geographical environment. METHODOLOGY: We designed a descriptive cross-sectional study based on social network analysis. We recruited 196 high school students between 16 and 18 years of age to participate in the study. The methodology applied was social network analysis by means of transitivity and homophily social triads. The data were analyzed using STATA statistical software. RESULTS AND CONCLUSIONS: A total of 58.48% of rural adolescents consumed alcohol compared to 49.52% of urban adolescents. These results demonstrate that adolescents who live in rural areas exhibit a greater risk of drinking alcohol than those who live in urban areas. The presence of transitive triads increases the probability of sharing sociodemographic attributes in such a way that it may be considered one of the causes of homophily, contributing to adolescents taking greater risks, such as consuming alcohol.