Publications by authors named "W De Corte"
This paper presents a progressive damage model (PDM) based on the 3D Hashin failure criterion within the ABAQUS/Explicit 2021 framework via a VUMAT subroutine, enhancing the characterization of the mechanical performance and damage evolution in the elastic and softening stages of composite materials via the accurate calculation of damage variables and accommodation of non-monotonic loading conditions. In the subsequent multi-level verification, it is found that the model accurately simulates the primary failure modes at the element level and diminishes the influence of element size, ensuring a reliable behavior representation under non-monotonic loading. At the laminate level, it also accurately forecasts the elastic behavior and damage evolution in open-hole lamina and laminates, demonstrating the final crack band at ultimate failure.
View Article and Find Full Text PDFIntubation for mechanical ventilation (MV) is one of the most common high-risk procedures performed in Intensive Care Units (ICUs). Early prediction of intubation may have a positive impact by providing timely alerts to clinicians and consequently avoiding high-risk late intubations. In this work, we propose a new machine learning method to predict the time to intubation during the first five days of ICU admission, based on the concept of cure survival models.
View Article and Find Full Text PDFCurrently used Pareto-optimal (PO) approaches for balancing diversity and validity goals in selection can deal only with one minority group and one criterion. These are key limitations because the workplace and society at large are getting increasingly diverse and because selection system designers often have interest in multiple criteria. Therefore, the article extends existing methods for designing PO selection systems to situations involving multiple criteria and multiple minority groups (i.
View Article and Find Full Text PDFArticle Synopsis
- Acute Kidney Injury (AKI) is a rapid decline in kidney function commonly found in critically ill patients, and has strong links to chronic kidney disease (CKD) and increased mortality.
- Machine learning models were created using patient data to predict outcomes after severe AKI (stage 3), focusing on the likelihood of developing CKD within three to six months and assessing mortality risks with advanced algorithms like random forests and XGBoost.
- The study included 101 patients, and results indicated that the machine learning models outperformed traditional predictive methods, suggesting they could improve clinical decision-making for AKI patients by identifying those at higher risk for CKD and mortality, especially when supplemented with unlabeled data.
Background: Acute Kidney Injury (AKI) is frequently seen in hospitalized and critically ill patients. Studies have shown that AKI is a risk factor for the development of acute kidney disease (AKD), chronic kidney disease (CKD), and mortality.
Methods: A systematic review is performed on validated risk prediction models for developing poor renal outcomes after AKI scenarios.