Publications by authors named "Athanasia D Skentou"
The unconfined compressive strength (UCS) of intact rocks is crucial for engineering applications, but traditional laboratory testing is often impractical, especially for historic buildings lacking sufficient core samples. Non-destructive tests like the Schmidt hammer rebound number and compressional wave velocity offer solutions, but correlating these with UCS requires complex mathematical models. This paper introduces a novel approach using an artificial neural network (ANN) to simultaneously correlate UCS with three non-destructive test indexes: Schmidt hammer rebound number, compressional wave velocity, and open-effective porosity.
View Article and Find Full Text PDFArticle Synopsis
- Complement inhibition shows promise for COVID-19 treatment, and the study aims to identify key genetic variants for predicting patient outcomes using an artificial intelligence-based tool.
- Genetic data from 204 hospitalized COVID-19 patients were analyzed, leading to the identification of 30 predictive variants and a 97% accuracy rate in predicting whether patients would need ICU admission.
- The study highlights the effectiveness of the alpha-index and the DERGA algorithm in accurately determining the relevance of numerous genetic variants for disease outcome prediction.
Article Synopsis
- There is a need for better early prediction models for COVID-19 outcomes, specifically morbidity and mortality in hospital settings.
- The study identified critical genetic variants related to the complement system that are linked to severe COVID-19 outcomes and developed a predictive artificial neural network (ANN) using these variants.
- The ANN successfully predicted severe outcomes in nearly 90% of patients, highlighting the role of genetic factors in worsening COVID-19 conditions and confirming that these variants are associated with an impaired immune response.