Search

Electrocardiogram (ECG) data collection during emergency situations is challenging, making ECG data generation an efficient solution for dealing with highly imbalanced ECG training datasets. In this paper, we propose a novel approach for ECG signal generation using Generative Adversarial Networks (GANs) and statistical ECG data modeling. Our approach leverages prior knowledge about ECG dynamics to synthesize realistic signals, addressing the complex dynamics of ECG signals. To validate our approach, we conducted experiments using ECG signals from the MIT-BIH arrhythmia database. Our results demonstrate that our approach, which models temporal and amplitude variations of ECG signals as 2-D shapes, generates more realistic signals compared to state-of-the-art GAN based generation baselines. Our proposed approach has significant implications for improving the quality of ECG training datasets, which can ultimately lead to better performance of ECG classification algorithms. This research contributes to the development of more efficient and accurate methods for ECG analysis, which can aid in the diagnosis and treatment of cardiac diseases.

Background: Food allergy (FA) has become a major public health concern affecting millions of children and adults worldwide. In Tunisia, published data on FA are scarce. Methods: This study, was intended to fill the gap and estimate the frequency of allergy to different foods in the Sfax region, Tunisia, within self-reported FA. One hundred twenty-five (125) children (56% males, 1–17 years old), and 306 adults (17% males, 18–70 years old) were interviewed using a bilingual questionnaire. Results: The number of self-reported food allergens in this sample was 105; allergens were clustered in 8 foods: fruits, seafood, eggs, milk and dairy, cereals, nuts, vegetables, and peanuts. Cutaneous reactions were the most frequent symptoms, in both children and adults. About 40% of children and 30% of adults had a family history of FA. About 81% of adults and 38% of children are allergic to at least 1 non-food allergen. The most prevalent food allergen was the fruit group in both adults and children, followed by seafood. Most food allergies were mutually exclusive and 90% of individuals have a single FA. The relationship between self-declared FA was modeled using a Bayesian network graphical model in order to estimate conditional probabilities of each FA when other FA is present. Conclusions: Our findings suggest that the prevalence of self-reported FA in Tunisia depends on dietary habits and food availability since the most frequent allergens are from foods that are highly consumed by the Tunisian population.

Although recognized as effective measures to curb the spread of the COVID19 outbreak, social distancing and home confinement have generated a mental health burden with older adults who are considered to be more vulnerable to psychosocial strains. To date, the application of digital technologies in response to COVID-19 pandemic has been narrowed to public-health needs related to containment and mitigation. However, information and communications technology (ICT)-based initiatives directed toward prediction and prevention of psychosocial support are still limited. Given the power of digital health solutions to allow easy and accurate characterization and intervention for health and disease, as well as to flatten the COVID19 incidence curves in many countries, our ECLB-COVID19 consortium is highlighting the importance of providing innovative ICT-based solutions (ICT-COVID-Companion) to improve elderly physical and mental health, thereby preventing/dampening psychosocial strain during pandemics. Based on innovative approaches (e.g., emotional/social computing, open social platform, interactive coaching, gamification, fitness-tracker, internet of things) and smart digital solutions (smartwatch/smartphone), smart companions must provide safe personalised physical, mental and psychosocial health surveillance. Additionally, by delivering personalised multi-dimension crisis-oriented health recommendations, such innovative crisis-oriented solutions would help (i) facilitate a user’s adherence to active and healthy confinement lifestyle (AHCL), (ii) achieve a rapid psychosocial recovery in case of depression issues and (iii) enhance preparedness for eventual future pandemics.

On 30 January 2020, the World Health Organization announced a new coronavirus, which later turned out to be very dangerous. Since that date, COVID-19 has spread to become a pandemic that has now affected practically all regions in the world. Since then, many researchers in medicine have contributed to fighting COVID-19. In this context and given the great growth of scientific publications related to this global pandemic, manual text and data retrieval has become a challenging task. To remedy this challenge, we are proposing CovBERT, a pre-trained language model based on the BERT model to automate the literature review process. CovBERT relies on prior training on a large corpus of scientific publications in the biomedical domain and related to COVID-19 to increase its performance on the literature review task. We evaluate CovBERT on the classification of short text based on our scientific dataset of biomedical articles on COVID-19 entitled COV-Dat-20. We demonstrate statistically significant improvements by using BERT.

The increase of mobile and interconnected devices leads to the growth of demands for context aware applications. These applications deployed on top of pervasive environments must adapt themselves to context changes. Context aware applications have to continuously sense their physical environment, and adapt their behavior accordingly. These applications must perform four phases starting by collecting and monitoring context, then analyzing context, deciding adaptation actions and finally executing the planned adaptation actions to deal with the context changes. In this paper, we focus on the second phase.We propose a context analysis approach that relies on different thresholds defined according to the user needs to detect context changes and raise notifications when changes occur. The analysis approach is performed according to three different steps. A context storage step, a context classification step, and a threshold calculation step.