ESSLei - Capítulos de livros
Permanent URI for this collection
Browse
Browsing ESSLei - Capítulos de livros by Field of Science and Technology (FOS) "Ciências Médicas::Ciências da Saúde"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Level up! How Gamed-Based Activities Transform Learning and Alleviate Stress in Institutionalized ElderlyPublication . Lacomba-Arnau, Elena; Ribeiro, Anaísa; Sabino, Raquel; Pinheiro, Rafael; Lopes, Susana; Gaspar, Marisa; Navarro-Mateos, Carmen; Sousa, Micael; Rosa, MarleneMental health issues are a critical concern for the elderly, as the inability to manage stress during stimulation activities can significantly impair their ability to accept and effectively learn new tasks, thereby affecting their performance in daily life activities. Serious games are increasingly recognized as valuable in the context of rehabilitation; however, there is a paucity of studies examining how elderly individuals manage stress and learn in regular practice using such games. In this study, 10 institutionalized elderly participants underwent 6 game-based stimulation sessions playing the serious games Ta!Ti! and Mexerico. Learning variables, including time and error rates, were assessed at baseline (T0), mid-point (T1), and the final session (T2), along with stress management indicators, specifically cortisol levels, at T0 and T2. The findings revealed that learning profiles improved throughout the program, with more pronounced gains observed initially. Additionally, stress levels decreased following each game-based session. The study identified significant relationships between stress management and learning profiles, suggesting that game-based activities can effectively enhance both learning outcomes and stress reduction in the elderly.
- STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient NetworksPublication . Geissbuhler, Damien; Bornet, Alban; Marques, Catarina; Anjos, André; Pereira, Sónia; Teodoro, DouglasHospital-acquired infections (HAIs), particularly those caused by multidrug-resistant (MDR) bacteria, pose significant risks to vulnerable patients. Accurate predictive models are important for assessing infection dynamics and informing infection prediction and control (IPC) programmes. Graph-based methods, including graph neural networks (GNNs), offer a powerful approach to model complex relationships between patients and environments but often struggle with data sparsity, irregularity, and heterogeneity. We propose the space-time-and-memory (STM)-GNN, a temporal GNN enhanced with recurrent connectivity designed to capture spatiotemporal infection dynamics. STM-GNN effectively integrates sparse, heterogeneous data combining network information from patient-environment interactions and internal memory from historical colonization and contact patterns. Using a unique IPC dataset containing clinical and environmental colonization information collected from a long-term healthcare unit, we show that STM-GNN effectively addresses the challenges of limited and irregular data in an MDR prediction task. Our model reaches 0.84 AUROC, and achieves the most balanced performance overall compared to classic machine learning algorithms, as well as temporal GNN approaches.