Explainable hypoglycemia prediction models through dynamic structured grammatical evolution.

Effective blood glucose management is crucial for people with diabetes to avoid acute complications. Predicting extreme values accurately and in a timely manner is of vital importance to them. People with diabetes are particularly concerned about suffering a hypoglycemia (low value) event and, moreover, that the event will be prolonged in time. It is crucial to predict hyperglycemia (high value) and hypoglycemia events that may cause health damages in the short term and potential permanent damages in the long term. This paper describes our research on predicting hypoglycemia events at 30, 60, 90, and 120 minutes using machine learning methods. We propose using structured Grammatical Evolution and dynamic structured Grammatical Evolution to produce interpretable mathematical expressions that predict a hypoglycemia event. Our proposal generates white-box models induced by a grammar based on if-then-else conditions using blood glucose, heart rate, number of steps, and burned calories as the inputs for the machine learning technique. We apply these techniques to create three types of models: individualized, cluster, and population-based. They all are then compared with the predictions of eleven machine learning techniques. We apply these techniques to a dataset of 24 real patients of the Hospital Universitario Principe de Asturias, Madrid, Spain. The resulting models, presented as if-then-else statements that incorporate numeric, relational, and logical operations between variables and constants, are inherently interpretable. The True Positive Rate and True Negative Rate metrics are above 0.90 for 30-minute predictions, 0.80 for 60 min, and 0.70 for 90 min and 120 min for the three types of models. Individualized models exhibit the best metrics, while cluster and population-based models perform similarly. Structured and dynamic structured grammatical evolution techniques perform similarly for all forecasting horizons. Regarding the comparison of different machine learning techniques, on the shorter forecasting horizons, our proposals have a high probability of winning, a probability that diminishes on the longer time horizons. Structured grammatical evolution provides advanced forecasting models that facilitate model explanation, modification, and retesting, offering flexibility for refining solutions post-creation and a deeper understanding of blood glucose behavior. These models have been integrated into the glUCModel application, designed to serve people with diabetes.

Welfare Resilience at the Onset of the COVID-19 Pandemic in a Selection of European Countries: Impact on Public Finance and Household Incomes.

This paper assesses the impact on household incomes of the COVID-19 pandemic and governments' policy responses in April 2020 in four large and severely hit EU countries: Belgium, Italy, Spain and the UK. We provide comparative evidence on the level of relative and absolute welfare resilience at the onset of the pandemic, by creating counterfactual scenarios using the European tax-benefit model EUROMOD combined with COVID-19-related household surveys and timely labor market data. We find that income poverty increased in all countries due to the pandemic while inequality remained broadly the same. Differences in the impact of policies across countries arose from four main sources: the asymmetric dimension of the shock by country, the different protection offered by each tax-benefit system, the diverse design of discretionary measures and differences in the household level circumstances and living arrangements of individuals at risk of income loss in each country.

Advanced Graphene-Based Transparent Conductive Electrodes for Photovoltaic Applications.

New architectures of transparent conductive electrodes (TCEs) incorporating graphene monolayers in different configurations have been explored with the aim to improve the performance of silicon-heterojunction (SHJ) cell front transparent contacts. In SHJ technology, front electrodes play an important additional role as anti-reflectance (AR) coatings. In this work, different transparent-conductive-oxide (TCO) thin films have been combined with graphene monolayers in different configurations, yielding advanced transparent electrodes specifically designed to minimize surface reflection over a wide range of wavelengths and angles of incidence and to improve electrical performance. A preliminary analysis reveals a strong dependence of the optoelectronic properties of the TCEs on (i) the order in which the different thin films are deposited or the graphene is transferred and (ii) the specific TCO material used. The results shows a clear electrical improvement when three graphene monolayers are placed on top on 80-nm-thick ITO thin film. This optimum TCE presents sheet resistances as low as 55 Ω/sq and an average conductance as high as 13.12 mS. In addition, the spectral reflectance of this TCE also shows an important reduction in its weighted reflectance value of 2-3%. Hence, the work undergone so far clearly suggests the possibility to noticeably improve transparent electrodes with this approach and therefore to further enhance silicon-heterojunction cell performance. These results achieved so far clearly open the possibility to noticeably improve TCEs and therefore to further enhance SHJ contact-technology performance.