80936 research outputs found
Sort by
Lección 20. Inteligencia artificial en el ámbito sanitario
No full text1. ¿Qué es la inteligencia artificial? 1.1. IA aplicada al ámbito sanitario 1.2. Retos de la
IA para el ordenamiento jurídico 2. IA como producto sanitario 3. Reglamento Europeo de IA: sistemas sanitarios de IA de alto riesgo. 4. Automatización de la práctica clínica: responsabilidad profesional sanitaria 5. Derechos de los pacientes ante la IA. 5.1. Elaboración de perfiles y el derecho de información 5.2. Prohibición de la toma de decisiones automatizada. 6. Materiales didácticos: Lecturas recomendadas. Normativa básica. Ejercicio complementario. Cuestionarios de autoevaluación
Heart failure with supranormal ejection fraction: clinical characteristics and outcomes compared to mildly reduced and preserved ejection fraction
No full textBackground: Little is known about the recently emerging entity, heart failure with supranormal ejection fraction (HFsnEF). Objective: To describe the clinical characteristics and outcome of HFsnEF, compared to HF with mildly reduced EF (HFmrEF) and HF with preserved EF (HFpEF) patients. Design: A single center retrospective analysis. Patients: Hospitalized and ambulatory heart failure (HF) patients who underwent echocardiography with left ventricular ejection fraction (LVEF) > 40%. Main measures: Clinical and echocardiographic parameters, hospitalization rates and mortality. Key results: A total of 6,202 patients (mean age 81.4 ± 14.1 years, 52% females) were analyzed: 750 in the HFmrEF group (LVEF 41–49%), 4360 in the HFpEF group (LVEF 50–64%), and 1092 in the HFsnEF group (LVEF ≥ 65%). Patients were followed for a median of 32 (11–65) months. HFsnEF patients were older, predominantly female, exhibited higher hypertension prevalence, more severe LV hypertrophy, smaller LV dimensions, and higher filling pressures compared to the other groups (p < 0.001 for all). These features were consistent in both hospitalized and ambulatory patients. In a univariable model, HFsnEF patients had higher mortality rates compared to HFmrEF and HFpEF patients (HR 1.258, 95% CI 1.117–1.418; p < 0.001 and HR 1.112, 95% CI 1.023–1.208; p = 0.012, respectively). However, in a multivariable model, adjusted for age, sex, comorbidities, and echocardiographic parameters, there was no significant difference in the mortality rates between all groups. The total hospitalization rate was similar between the HFpEF and HFsnEF groups, and lower in the HFmrEF group (p = 0.022). However, the HFsnEF group had the lowest rate of HF-related hospitalizations (p = 0.002). Conclusion: HFsnEF represents a group of patients with a distinct clinical and echocardiographic profile accompanied by worse outcomes, likely mediated by older age and a higher comorbidity burden, compared to HFmrEF and HFpEF. Therefore, the supranormal EF may serve as a marker rather than an independent prognostic factor
On Planning through LLMs
Full text linkIn recent years, various studies have been carried out to assess whether Large Language Models (LLMs) possess different reasoning capabilities, including those required in automated planning. Typically, these studies provide the LLM with a planning domain and a problem, specified by an initial state and a goal, and require the LLM model to generate a plan solving the problem. Despite this common configuration, such studies significantly differ in the used models, the information provided to the model, the possible involvement of symbolic planners, and the experimental approaches used for the evaluation. Motivated by the growing interest in LLMs and in the understanding of their reasoning abilities, in this work we offer a concise review of recent studies on using LLMs for planning. We outline the main research trends and discuss their most notable findings. Furthermore, we identify key challenges and highlight critical aspects to consider when evaluating a LLM in terms of learning to plan and generating solution plans
Enhancing DL-based Cell Segmentation of Microalgae with Classical Image Processing Priors
No full textWe present a hybrid approach for the automatic de- tection and segmentation of Nannochloropsis Oceanica, Wild Type (NocWT) microalgae cells, combining classical image processing techniques with deep learning. Initially, we apply traditional computer vision methods to detect and count cells efficiently, but these struggle with challenges such as morphological variability and overlapping structures. To overcome these limitations, we incorporate the Segment Anything Model (SAM), a state-of-the- art segmentation framework leveraging a transformer archi- tecture pre-trained on large-scale datasets. Instead of relying solely on SAM’s general capabilities, we guide its segmentation using pre-segmented regions derived from classical methods, improving accuracy in delineating complex cell boundaries. The proposed method is evaluated on a manually annotated dataset of bright-field microscopic images, ensuring reliable performance assessment despite the dataset’s limited size. By integrating the interpretability of traditional approaches with the adaptability of deep learning, our method achieves robust and precise microalgae segmentation, demonstrating the advantages of a complementary strategy over standalone state-of-the-art techniques
On Polymorphic Attacks in the ASPIC+ and ASPICR Formalisms
No full textThe recently proposed ASPICR, standing for ASPIC+ revisited is an evolution of the prominent ASPIC+ formalism for structured argumentation, which overcomes some limitations of ASPIC+ by resorting in particular to an alternative notion of attack referring to sets of arguments. While this notion of attack is a key element for achieving the technical advantages offered by ASPICR, it also gives rise to some peculiar situations, where some attacks are, in a sense, polymorphic since there are multiple reasons by which a given set of arguments can attack an argument. After pointing out that polymorphic attacks are also possible in ASPIC+, we provide some examples of polymorphic attacks in ASPIC+ and ASPICR, discuss the underlying technical and conceptual issues and provide a preliminary discussion about how to revise the formalisms in order to encompass alternative options for their management
Multidisciplinarità nella gestione del patrimonio storico: Valutazioni idrauliche e proposte di restauro per la ex stazione ferroviaria di Stupizza (UD)
Full text linkThe restoration of Poiana railway station in Stupizza (UD) requires collaboration among experts to preserve its historical and environmental value. The site, once part of the Cividale-Kobarid railway, was considered for a cycling path under the “Bimobis” project but was excluded due to hydraulic risk.
Built in the early 1900s with Austro-Hungarian influences, the station suffered damage during World War I and was abandoned after the railway had been closed in 1932. Today, it is in severe decay, with structural collapses and invasive vegetation.
A study by the Università degli studi di Brescia and Acquedotto Poiana used advanced 3D scanning and photogrammetry to assess the building’s condition and develop a conservation model. However, the station is at high flood risk, with water levels reaching 1.5 meters during extreme events. Restoration efforts must address these challenges through protective engineering solutions. Ongoing research focuses on documenting the site’s infrastructure, analyzing historical data, and exploring sustainable conservation strategies. Experts emphasize the importance of integrating the station into the region’s cultural and tourism network, potentially repurposing it as a historical landmark or educational center while ensuring environmental compatibility. Despite the challenges, the project represents an opportunity to enhance local heritage and promote cross-border cooperation between Italy and Slovenia. Future restoration plans may involve European funding programs and collaborations with cultural institutions, ensuring a balanced approach between preservation and sustainable development
Toward a Sustainable and Efficient Design Process: A BIM-Based Organisational Framework for Public Agencies—An Italian Case Study
No full textThe implementation of Building Information Modelling (BIM) in public design processes enhances efficiency, transparency, and sustainability. However, public agencies often encounter significant barriers, particularly regarding organisational and managerial readiness. This study develops a BIM implementation framework tailored to the specific needs of an Italian public agency. The research adopts a qualitative approach, combining 15 semi-structured interviews with process mapping Using (Business Process Modeling Notation) BPMN. The current as-is workflows were analysed and validated by internal stakeholders. Based on this analysis, strategic objectives were defined, relevant (Building Information Modelling) BIM uses were selected, and revised to-be processes were proposed, integrating new roles and responsibilities according to the standards. The framework addresses both technical and organisational dimensions of BIM adoption, highlighting the need for training, coordination, and stakeholder engagement. The main outcomes include a structured process model, a priority-based selection of BIM uses, and a role matrix supporting organisational transformation. The added value for researchers lies in the replicable methodology that combines empirical process mapping with implementation planning. For practitioners, especially consultants in sustainable design, the study offers a practical roadmap for aligning BIM adoption with project goals, regulatory compliance, and environmental performance targets in complex public sector contexts
From PID to PIDD2alpha: Performance improvement with a fractional double derivative action
No full textThis paper analyzes the performance achievable by means of PIDD2α controllers, that is, PID controllers with an additional fractional double derivative action. In particular, the performance obtained with an optimized tuning of the parameters is compared with those of standard PID controllers, of fractional-order PID (FOPID) controllers and of Proportional–Integral–Double-Derivative (PIDD or PIDD2) controllers. In all the cases the parameters are determined by minimizing the integrated absolute error either in the set-point or load disturbance step response, with a constraint on the maximum sensitivity. A wide set of benchmark processes (both self and non self-regulating) are considered so that general conclusions about the impact that these controllers can have in the process industry can be drawn