Enseñanzas Técnicas

Lightweight Skin Lesion Segmentation for Edge Deployment: A Critical Review of Architectures, Accuracy Compensation, and Clinical Translation

2026-07-24T00:01:18Z

[EN]Automated skin lesion segmentation via deep learning has achieved remarkable accuracy in controlled laboratory settings, yet its clinical translation to point-of-care (PoC) edge devices remains fundamentally constrained by the computational demands of state-of-the-art architectures. This review systematically bridges the gap between algorithmic innovation and hardware-aware deployment by presenting a critical analysis spanning three interconnected dimensions: 1) architectural evolution from convolutional neural networks (CNNs) through Vision Transformers to emerging linear-complexity State Space Models (e.g., Mamba), evaluated against a unified efficiency–accuracy Pareto framework rather than isolated accuracy rankings; 2) mathematical formalisation of lightweighting-induced precision degradation and its compensation via knowledge distillation, structural reparameterisation, and frequency-domain enhancement, with explicit assessment of evidence quality and reproducibility across studies; and 3) empirical deployment profiling across heterogeneous edge platforms including NVIDIA Jetson, Intel OpenVINO, and mobile processors. Through a multi-dimensional evaluation framework integrating spatial overlap (Dice), boundary fidelity (HD95), and on-device throughput (FPS), supplemented by a meta-analysis of dataset usage biases and validation protocol inconsistencies, we establish that heterogeneous multi-paradigm fusion architectures can preserve clinical-grade segmentation quality under severe resource constraints—provided that evaluation methodologies are standardised. Critically, our quantitative analysis of 36 reviewed studies reveals that approximately 65% of reported performance figures are derived from non-standardised data splits, rendering direct cross-study comparisons statistically unreliable. We further identify critical open challenges—including cross-domain generalisation, hardware–algorithm co-design, demographic fairness, and edge-native federated learning—an...

Engineering a dual stimuli-responsive platform for post-surgical breast cancer treatment

2026-07-24T01:04:40Z

[ES] Esta tesis doctoral se ha centrado en el desarrollo de una plataforma dual termo/pH-sensible para el tratamiento localizado del cáncer de mama tras la resección quirúrgica del tumor para la erradicación de células tumorales en el tejido mamario y prevención de recurrencias locales. El objetivo principal ha sido combinar la administración local de fármacos, mediante el desarrollo de una matriz de hidrogel inyectable y termosensible, con mecanismos de liberación pH-sensible basados en nanocarriers, capaces de aumentar la eficacia terapéutica y reducir los efectos adversos de las terapias sistémicas convencionales. La novedad en esta tesis doctoral respecto a los sistemas de respuesta dual reportados reside en la transferencia de la pH-sensibilidad de la matriz del hidrogel al nanocarrier incorporado, estableciendo un proceso de síntesis y optimización de las estrategias en cada componente del sistema híbrido de forma paralela, presentando la oportunidad de un diseño más adaptable a cada estrategia y mayor potencial sinérgico, incrementando su actividad anticancerígena. La primera etapa de la investigación estuvo dedicada al estudio de coacervados basados en alginato y gelatina A, buscando la síntesis del nanocarrier pH-sensible. Se analizó de forma detallada la influencia de variables como el pH, la temperatura de síntesis, el pretratamiento térmico de la gelatina y la relación Alginato:Gelatina A. Los resultados demostraron que el estado estructural de la gelatina desempeña un papel fundamental en la formación y estabilidad de los coacervados. El calentamiento favoreció el desenredo parcial de las cadenas de gelatina, permitiendo obtener coacervados más homogéneos y estables, incrementando el número de interacciones electrostáticas. La caracterización mediante dispersión dinámica y estática de luz (zetasizer) y turbidimetría permitió identificar formulaciones con tamaños nanométricos y baja polidispersión. Sin embargo, se observó un fenómeno de histéresis térmica por el cual las propiedades de los coacervados se deterioraban tras varios días a temperatura ambiente, a pesar de poder recuperarse parcialmente mediante ciclos de recalentamiento. Este comportamiento también fue confirmado mediante estudios reológicos, que pusieron de manifiesto la incompatibilidad de estas partículas coacervadas con una matriz que pudiera ser usada como reservorio de principios activos en administración local. Por lo tanto, la siguiente etapa de la tesis estuvo centrada en el desarrollo de otra alternativa para el componente pH-sensible del sistema dual. Para ello se sintetizaron liposomas mediante hidratación de capa fina y extrusión, optimizando tanto las condiciones de preparación como la composición lipídica. Los sistemas obtenidos presentaron tamaños próximos a 100 nm, muy baja polidispersión y una elevada estabilidad por periodos superiores a 3 semanas. Para conferir la pH-sensibilidad, se desarrolló una estrategia basada en el recubrimiento de liposomas con polímeros Eudragit (EU). Más concretamente, el uso de dos formulaciones que presentaban perfiles de liberación con respuesta opuesta al pH se llevó a cabo para expandir el uso de liberaciones de fármaco en sistemas liposomales. Para el primer recubrimiento (EU S100, liberaciones alcalinas) fue necesario modificar previamente la carga superficial de los liposomas mediante estearilamina, permitiendo posteriormente su recubrimiento mediante interacciones electrostáticas, formando agregados micrométricos. Por otro lado, el recubrimiento con EU EPO (liberaciones ácidas) sí presentó sistemas coloidales de tamaños nanométricos. Los estudios de tamaño, potencial zeta y microscopía confirmaron la formación de estructuras recubiertas estables y reproducibles. Una vez seleccionadas las formulaciones más prometedoras, se evaluó la encapsulación y liberación del fármaco antitumoral 5-fluorouracilo (5FU). La eficiencia de encapsulación superó el 90% y los ensayos de liberación demostraron una clara dependencia del pH. Los sistemas recubiertos mostraron una capacidad significativamente mayor para modular la liberación dentro de cada rango de respuesta de la formulación de EU seleccionada, validando la estrategia de respuesta al pH. Adicionalmente, se estudió validación biológica de los sistemas desarrollados. Para ello se realizó una estancia de investigación en la Universidad de Birmingham, donde se adquirió experiencia en cultivos celulares y técnicas de evaluación de actividad terapéutica. En primer lugar, se determinó la sensibilidad al 5FU de fibroblastos sanos HS-5 y de la línea celular de cáncer de mama BT-474. Posteriormente, los estudios de viabilidad celular demostraron que las formulaciones liposomales eran biocompatibles. Adicionalmente, cuando el fármaco era encapsulado, las formulaciones pH-sensibles mostraban un comportamiento dependiente del microambiente celular. Teniendo en cuenta la aplicación en terapias anticancerígenas, los liposomas recubiertos con Eudragit EPO combinaron una elevada internalización celular con una liberación favorecida en condiciones ácidas. Como resultado, se alcanzaron niveles de mortalidad superiores al 95% en células tumorales, manteniendo simultáneamente una elevada viabilidad en fibroblastos sanos, confirmado la compatibilidad con la aplicación. Posteriormente, la investigación se orientó hacia el desarrollo de hidrogeles termosensibles basados en el poloxámero PF-127. Este polímero presenta la capacidad de formar geles al aumentar la temperatura debido a fenómenos de agregación micelar, lo que lo convierte en un candidato atractivo para aplicaciones inyectables. Sin embargo, los hidrogeles obtenidos únicamente con PF-127 mostraban una liberación demasiado rápida del fármaco. Con el fin de reforzar la estructura del hidrogel, se estudió la incorporación de diferentes polisacáridos con diferentes conformaciones estructurales: alginato (lineal), goma gellan (ramificado), goma santana (helicoidal) y levan (coloides auto-ensamblados). Cada uno de ellos mostró interacciones específicas con la red micelar del poloxámero, mejorando su comportamiento reológico, su temperatura de gelificación y su estabilidad estructural. Los ensayos reológicos demostraron que la incorporación de polisacáridos permitía mantener la transición sol-gel a temperaturas compatibles con la aplicación biomédica, mientras que aumentaba su elasticidad y resistencia. En estudios de liberación de fármaco, los hidrogeles con polisacáridos incorporados eliminaron prácticamente la liberación rápida inicial observada en el poloxámero puro, y prolongaron la liberación del fármaco más de cuatro veces respecto al sistema original. Estos resultados confirmaron que la incorporación de polisacáridos reducía la porosidad efectiva de la red y dificultaba tanto la difusión del medio como la degradación de la estructura, soportados por tasas de degradación y constantes cinéticas obtenidas por el ajuste a un modelo matemático. Una vez optimizados ambos componentes por separado, los liposomas pH-sensibles fueron incorporados a la matriz del hidrogel termosensible para generar la plataforma híbrida de respuesta dual. Los estudios reológicos confirmaron que la presencia de los liposomas no alteraba la capacidad de agregación micelar del poloxámero. Adicionalmente, su combinación permitió conservar el comportamiento dual del sistema. Los hidrogeles mostraron una elevada biocompatibilidad y mantuvieron la capacidad de liberar selectivamente el fármaco hacia entornos tumorales. Aunque la liberación fue más lenta debido a la resistencia difusional impuesta por la matriz polimérica, la actividad terapéutica siguió siendo eficiente. Finalmente, la formulación híbrida fue evaluada en esferoides tridimensionales de cáncer de mama, un modelo más representativo del entorno tumoral real. Los resultados demostraron una capacidad superior para desintegrar la estructura de los esferoides y reducir la viabilidad celular respecto al fármaco libre. En conjunto, los resultados obtenidos validan una estrategia basada en la combinación de un hidrogel termosensible inyectable y liposomas pH-sensibles como plataforma para el tratamiento localizado del cáncer de mama post-quirúrgico. El sistema desarrollado permitió aprovechar simultáneamente la administración local, la liberación sostenida y el direccionamiento hacia el microambiente tumoral, constituyendo una alternativa prometedora para futuras aplicaciones en terapia postquirúrgica.; [EN] Nowadays, the procedure for an early stage non-metastatic diagnosed breast cancer is the breast-conserving therapy, consisting of tumour resection therapy by lumpectomy followed by breast irradiation to prevent local recurrences. Despite late advances, the radiotherapy off-targeting toxicity, as well as the alternative chemotherapies based on drug delivery systems systemically administered present major drawbacks. The poor therapeutic efficiency, resulting from limited drug accumulation at tumour site, together with systemic toxicity, constitute the main limitations of systemic administration. Since residual tumour cells responsible for recurrence are predominantly located within the surgical bed, the development of local therapies targeting these cells can help overcome the current limitations associated with tumour relapse. Therefore, this doctoral thesis addresses this challenge through the design and development of a dual stimuli-responsive local drug delivery platform for post-surgical therapy which presents combined thermo-sensitivity by an injectable hydrogel matrix, and pH-sensitivity by an engineered nanocarrier. These responses exploit two basic features that can be found in the surgical bed: Physiological temperature to induce gelation after injection, providing a locally administered strong drug depot, and the acidic tumour microenvironment, providing a reproducible targeting strategy. The final drug delivery system is based on a PF-127 hydrogel network incorporating Eudragit® EPO coated liposomes encapsulating the anticancer drug 5-fluorouracil (5-FU) as a model chemotherapeutic agent. However, the first approach consisted of developing alginate-gelatin A coacervates for pH-responsive strategy. Their synthesis optimization was accomplished by the study of process variables, including temperature and pH, obtaining nano sized coacervates systems of 500-750 nm with low polidispersity index (PDI <0.25). Nonetheless, their dependence on temperature and pH resulted in instability under physiological conditions, preventing their use for the intended application. Consequently, new pH-responsive approaches were explored. In this case, liposomes were selected due to their current use in clinic, showing their high biocompatibility, efficiency, and versatility as vesicles resembling cellular membranes. Conventional liposomes were successfully synthesized and optimized via sonication and extrusion, obtaining a stable small unilamellar vesicle system (85 nm) with narrow size distribution (PDI < 0.1) for a 3-week period, able to encapsulate more than 90% of loaded 5-FU. Nevertheless, they exhibited fast drug release (under 8h) with no pH-response, evidencing a non-specific mechanism. Therefore, strategies to introduce pH-responsive release were investigated. In order to preserve the liposomes stability at physiological conditions, a surface modification rather than the conventional method of composition alteration was preferred. Regarding this, an innovative coating procedure with Eudragit® family of polymers offered a promising alternative. Moreover, the broad range of Eudragit® formulations, providing opposite pH-responsive behaviours depending on the intended application, enabled the optimization of the coating process to obtain a versatile liposomal platform. Accordingly, two oppositely pH-responsive coatings (Eudragit® S100 and EPO) were implemented to evaluate drug release under contrasting conditions, thereby expanding the potential applicability of stable liposomes at physiological conditions for enhancing cancer therapy through different administration routes. Eudragit® S100 (EU S100, designed for alkaline releases) coating procedure provided liposomal micron scale aggregates due to its high molecular weight and behaviour in aqueous solution. Meanwhile, Eudragit® EPO (EU EPO, designed for acidic releases) showed stable liposomal systems slightly larger (114 nm) but still monodisperse (PDI <0.15), presenting a promising formulation for the thesis objective. Moreover, both coatings showed higher encapsulation efficiencies than the conventional liposomes, and their releases were delayed until 24 h, preventing up to 50% of drug release in insoluble pH ranges for each coating. Mathematical modelling supported that insoluble coatings introduced a change in release mechanism, whilst supporting diffusion as the predominant one in Higuchi and first order fittings. This presented potential applications for alkaline delivery in colon or intestine from oral formulations (EU S100), and more importantly, acidic tumour microenvironment targeting (EU EPO). In fact, cell viability studies showed biocompatibility of all developed liposomal formulations. The pH-response of both coatings was validated through MTT assays in healthy fibroblast (HS-5) and breast cancer (BT-474) cell lines. Specifically, EU EPO coated liposomes enhanced cytotoxicity over 30% more than the rest of formulations in breast cancer cells after 72h, preserving fibroblasts viability. Therefore, tumour targeting was confirmed by in vitro studies. In parallel, a thermo-responsive injectable PF-127 hydrogel platform was developed for the local drug delivery reservoir. Comprehensive rheological analyses were used to characterize the thermo-response and evaluate the gelation completion temperature, the viscoelasticity and viscosity of the system, and ultimately, the suitability for injection and sustained release. Since PF-127 hydrogel showed fast degradation, different polysaccharides were implemented in the hydrogel network and the effect of their concentrations as well as their structural conformations was studied. Implemented polysaccharides matrices presented improved rheological properties (G’ from 8 to 11-18 kPa) and more resistance against flow (viscosities from 4.1 to 6.1-7.1 Pa·s), establishing final optimal formulations for local administration. These formulations provided a more prolonged 5-FU release, reaching up to four times (450 min) the release time that PF-127 hydrogel exhibited (90 min). Moreover, mathematical modelling confirmed that the polysaccharides implementation caused an additional diffusional resistance based on their concentration and structural complexity, decreasing the degradation rate and resisting water permeation through the matrix. The final hybrid dual-responsive platform was synthesized by incorporating the pH-responsive Eudragit® EPO coated liposomes into the thermo-responsive injectable PF-127 hydrogel matrix. Characterization techniques showed the successful liposomal incorporation into the hydrogel matrix via scanning electron microscopy, as well as improved viscoelastic properties (G’ of 15 kPa, and viscosity of 6.8 Pa·s) of the system via rheology. Moreover, the pH-responsiveness was preserved, as demonstrated by drug release studies. In fact, hydrogel incorporation introduced an additional diffusion barrier, leading to a sustained 5-FU release for up to 48h, where up to 50% of drug release was prevented for coating insolubility range. This insolubility proved once again a change of release mechanism in one and two-stage models fitting, whilst the hydrogel matrix delayed release was supported by lower kinetic constants. Finally, biological validation of the dual-responsive system was performed in 2D cell cultures and 3D breast tumour spheroids, for a better prediction of its in vivo behaviour. 2D cell assays replicated the results shown in liposomal systems, with the only exception that tumour cell mortality was slightly reduced (from 5% cell viability to 15% in 3 days) for the dual-responsive formulation, which was attributed to the delayed 5-FU release. However, the tumour targeting capacity was preserved. This was further supported by the results obtained in 3D tumour spheroids assays, where the dual-responsive hydrogel targeted successfully cancer cells promoting its therapeutic efficiency, showing disaggregated and disintegrated spheroids compared to off-targeting drug solution (from 40% cell viability in 5-FU solution to 28% in dual-responsive hydrogel after 3 days). Overall, this thesis presents an engineered dual-responsive local drug delivery platform for post-surgical breast cancer treatment. The innovative strategy of combining two separately optimized stimuli-responses for local administration and tumour targeting presented improvements regarding the current therapies: High therapeutic efficiency, and decreased systemic toxicity.

Localización, diagnosis y puesta en valor del Imperial Monasterio Cisterciense de Santa María de Valparaíso. Mediante la aplicación de técnicas geofísicas, fotogrametría, y láser 3D

2026-07-15T08:45:25Z

[ES] Este artículo documenta un proyecto de investigación integral centrado en el Imperial Monasterio de Santa María de Valparaíso (Zamora), un cenobio cisterciense en estado de ruina y enterramiento. La metodología se fundamenta en un enfoque rigurosamente multidisciplinar que articula el análisis histórico-documental con tres campos tecnológicos de vanguardia: prospección geofísica, diagnóstico de ingeniería civil y documentación geométrica digital (HBIM). Mediante la aplicación de la Tomografía de Resistividad Eléctrica 3D (ERT 3D), se logró la localización precisa de estructuras subterráneas, destacando el descubrimiento de una galería abovedada perteneciente a uno de los claustros. Esta detección se validó al contrastar los altos valores de resistividad con las referencias documentales previas (Ferrero, 1986; Rodríguez Miguel, 1910-1911). Complementariamente, el escaneo láser (LIDAR) y la fotogrametría generaron datos de alta densidad para la reconstrucción virtual hipotética en 3D (HBIM) de la iglesia (crucero y nave central) y del conjunto del resto de edificaciones, permitiendo el estudio paramétrico de sus elementos (dovelas y sillares). El trabajo persigue el levantamiento gráfico, la puesta en valor y la divulgación inmersiva (RV/RA) de este crucial patrimonio castellano, proporcionando una hoja de ruta metodológica para la gestión de ruinas monásticas.; [EN] This article documents a comprehensive research project centered on the Imperial Monastery of Santa María de Valparaíso (Zamora), a Cistercian monastery in a state of ruin and burial. The methodology is grounded in a rigorously multidisciplinary approach that integrates historical-documentary analysis with three cutting-edge technological fields: geophysical prospection, civil engineering diagnosis, and digital geometric documentation (HBIM). Through the application of 3D Electrical Resistivity Tomography (3D ERT), the precise location of underground structures was achieved, highlighted by the discovery of a vaulted gallery belonging to one of the cloisters. This detection was validated by crossreferencing the high resistivity values with previous documentary references (Ferrero, 1986; Rodríguez Miguel, 1910-1911). Additionally, laser scanning (LiDAR) and photogrammetry generated high-density data for the hypothetical 3D virtual reconstruction (HBIM) of the church (transept and central nave) and the rest of the architectural complex, enabling the parametric study of its elements (voussoirs and ashlars). This work aims to carry out the architectural survey, heritage enhancement, and immersive dissemination (VR/AR) of this crucial Castilian heritage, providing a methodological roadmap for the management of monastic ruins.

Harnessing Low-Enthalpy Geothermal Energy to Enhance Road Infrastructure Resilience: Insights from GEO-ROAD Project

2026-07-14T00:01:17Z

‎[EN] Geothermal systems offer an effective solution for enhancing the resilience of road infrastructure to extreme weather events. Their key advantages (such as independence from external climatic conditions and the potential for continuous operation) make them significant improvement over conventional approaches, including de-icing or protecting road surfaces from high temperatures. Within this context, the GEO-ROAD project aims to develop a predictive platform to identify the most promising locations for the deployment of geothermal energy in road infrastructure. A central component of this research is the methodology used to characterize the subsurface energy resource across the study area (Spain) and to develop corresponding geothermal potential models. Following an initial geological and thermal assessment, a refined model is presented that integrates geophysical data from satellite missions, airborne surveys, and field measurements. Finally, this work highlights the importance of high-precision geothermal potential models, which provide a robust foundation for optimizing the use of geothermal energy, particularly in the road sector considered.

Immersive UAV training through simulated environments as a cross-disciplinary educational methodology for architecture and engineering education

2026-06-27T00:01:06Z

[ES] La creciente integración de los UAV en arquitectura e ingeniería exige nuevas metodologías formativas adaptadas a contextos profesionales reales. Sin embargo, la enseñanza universitaria continúa limitada por restricciones normativas y condicionantes logísticos que reducen la práctica real de vuelo. Este trabajo presenta una metodología educativa inmersiva basada en simuladores profesionales combinados con controladores físicos, que permite desarrollar competencias técnicas, operativas y de toma de decisiones en un entorno seguro y repetible. La propuesta integra aprendizaje activo, misiones basadas en retos y evaluación por competencias, estructurándose en fases progresivas: selección de herramientas de simulación, aplicación de rúbricas iniciales y finales, análisis de resultados, transición a prácticas reales y mejora continua. Desde la perspectiva arquitectónica y de la edificación, la metodología facilita la formación en inspección de edificios, planificación de vuelos y captura de datos mediante fotogrametría y análisis térmico, ofreciendo un modelo escalable y transferible para la innovación educativa en educación superior.

Oppida y Verracos: investigación y divulgación del patrimonio de la Edad del Hierro en el occidente de la meseta

2026-06-27T00:01:10Z

[ES] Oppida y Verracos: investigación y divulgación del patrimonio de la Edad del Hierro en el occidente de la meseta

Propuesta metodológica a través de las tecnologías de la información y la comunicación para la revitalización de zonas rurales con problemas demográficos: el patrimonio como vector estratégico de desarrollo

2026-06-27T00:01:05Z

[ES] Propuesta metodológica a través de las tecnologías de la información y la comunicación para la revitalización de zonas rurales con problemas demográficos: el patrimonio como vector estratégico de desarrollo.

Unified Multi-Task Learning vs. Decoupled Transformer-based Perception: A Comparative Analysis

2026-06-11T00:00:24Z

[EN]Efficient environmental perception is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. A persistent architectural dilemma in this domain is whether to employ unified Multi-Task Learning (MTL) frameworks, which optimize computation through shared backbones, or modular multi-model pipelines, which prioritize task-specific accuracy. This paper presents a comparative analysis of these two paradigms for joint object detection and drivable area estimation. Specifically, we evaluate YOLOPX, a representative anchor-free MTL architecture, against a decoupled multi-model system that integrates RT-DETRv2 for vehicle detection and the lightweight YOLO11n-seg for drivable area segmentation on the BDD100K benchmark under identical hardware conditions. The results show that, although the MTL YOLOPX model achieves higher throughput, the decoupled system delivers substantially better detection performance, particularly in the stricter 𝑚𝐴𝑃 50:95 metric, while preserving competitive segmentation quality and maintaining real-time latency suitable for edge deployment. These findings suggest that modular designs, rather than monolithic MTL models, can offer a more favorable balance between safety-critical detection accuracy and computational efficiency for next-generation intelligent vehicles.

Mining patient data from heterogeneous sources for decision making on administration of non invasive mechanical ventilation in intensive care units.

2026-06-02T00:02:03Z

[EN]This paper addresses the problem of decision making regarding the administration of non invasive mechanical ventilation in intensive care units. The great number of factors to take into account, its heterogeneity and diverse origin make very difficult this process. In order to facilitate this task we propose the application of data mining methods to extract knowledge from the wide and complex information available. The aim is to find out the factors influencing the success/failure of NIMV and to predict the results in future patients. These methods have not been previously applied in this field in spite of the good results obtained in other medical areas. In this work a comparative study of different algorithms has been carried out using a wide spectrum of data obtained during 6 years about 389 patients that received treatment with NIMV. The results reveal that some multiclasifiers can be useful tools for helping physicians in the choice of the best action.

Machine Learning Methods for Mortality Prediction of Polytraumatized Patients in Intensive Care Units – Dealing with Imbalanced and High-Dimensional Data

2026-06-02T00:02:02Z

[EN]The aim of this study is the prediction of death of polytraumatized patients based on epidemiological, clinical and health treatment variables by means of data-mining methods. The main problems to be addressed were high dimensionality and imbalanced data. Since the techniques usually used to deal with these drawbacks, as feature selection methods and sampling strategies respectively, did not provided satisfactory results, the aim of the study was to find out the data mining algorithms showing the best behavior in this kind of scenarios. The study was carried out with data from 497 patients diagnosed with severe trauma who were hospitalized in the Intensive Care Unit (ICU) of the University Hospital of Salamanca. The results of the study reveal the better behavior of multiclassifiers as compared with simple classifiers in contexts of high dimensionality and imbalanced datasets, without the need to resort to undersampling and oversampling strategies, which can lead to the loss of valuable data and overfitting problems respectively.

Computational study of the effect of forced exercise (swim stress) on the NADPH- diaphorase activity in the supraoptic nucleus

2026-06-02T00:02:02Z

[EN]Nitric oxide synthesizing neurons of the hypothalamus show changes following a variety of experimental and pathological conditions, such as salt loading, hypotension, cholestasis, water deprivation, and several types of stress including immobilization, exposure to low temperature and changes of environment. Recently, our group has shown that forced exercise (swim stress) is an additional stressor for the nitrergic neurons located in the paraventricular nucleus of the hypothalamus. On the other hand it is currently well-known, by means of histochemical (NADPH-diaphorase), immunohistochemical and hybridization methods, that the supraoptic nucleus contains an important nitrergic population of neurons. In the present study, the effect of forced exercise on these neurons was investigated in a computational study of the NADPH-diaphorase positive population of the supraoptic nucleus. A significant increase in the number of positive neurons was observed following forced swimming, especially after 30 and 40 min. These data indicate: 1.– The influence of stress on the NADPH-diaphorase-activity in the supraoptic nucleus. 2.– The involvement of hypothalamic nitric oxide synthesizing-neurons in the response to different types of acute stressors. 3.– The excellence of a combination of morphological and computational tecniques for the detection of changes in plasticity of the hypothalamic neurons.

Predictors of the post-stroke status in the discharge from the hospital. Importance in nursing

2026-06-02T00:02:01Z

[ES]A menudo, por parte del paciente y de la familia, se solicita a los profesionales de enfermería que predigan los factores que influyen en el estado post-ictus. Se han realizado numerosos estudios para determinar los factores que influyen en el estado neurológico post-ictus en el momento del alta hospitalaria. Sin embargo, las técnicas de aprendizaje automático no se han utilizado para este propósito. Con el objetivo de obtener reglas de asociación del pronóstico neurológico, se ha llevado a cabo un doble análisis, tanto clínico como con técnicas de aprendizaje automático, de las posibles asociaciones de factores que influyen en el estado neurológico de los pacientes post-ictus. El algoritmo Apriori detectó varias reglas de asociación con alta confianza (≥ 95%), con el siguiente patrón: En pacientes en el rango de edad de 50-80 años, la asociación de un NIHSS entre 11 y 15 puntos (NIHSS intermedio/bajo), junto con la trombectomía, conduce a la recuperación ad integrum al alta. Con la técnica de remuestreo SMOTE, se alcanzó el 100% de confianza para la asociación de NIHSS elevado (>20) y afectación de las arterias carótida y basilar, con pronóstico nefasto (exitus). Estas reglas confirman, por primera vez con aprendizaje automático, la importancia de la asociación de algunos predictores, en el pronóstico post-ictus. El conocimiento por parte de las enfermeras de estas reglas puede mejorar los resultados del ictus. Adicionalmente, el papel de la enfermería en los programas de educación sobre los factores de riesgo, y pronóstico de un ictus se torna imprescindible.; [EN]Nurses are often asked to predict factors that influence post-stroke outcome by the patient and family. Many studies have been carried out in order to determine the factors that influence the neurological status of the post-stroke patient at the moment of the discharge from the hospital. However, machine learning techniques have not been used for this purpose. Therefore, with the objective of obtaining association rules of neurological prognosis, a double analysis, both clinical and with machine learning techniques of the possible associations of factors that influence the neurological status of the post-stroke patients has been carried out. The Apriori algorithm detected several association rules with high confidence (≥ 95%), from which the following pattern: In patients in the age range of 50-80 years, the association of a NIHSS between 11 and 15 points (intermediate/low NIHSS), along with thrombectomy, leads to recovery ad integrum at discharge. With the SMOTE resampling technique, the 100% confidence was reached for the association of high NIHSS (>20) and involvement of the carotid and basilar arteries, with a dire prognosis (exitus). These rules confirm, for the first time with machine learning, the importance of the association of some predictors, in the post-stroke prognosis. The knowledge by the nurses of these association rules can successfully improve stroke outcome. In addition, the role of nurses in education programs that teach knowledge of risk factors and stroke prognosis becomes essential.

Prognostic factors associated with mortality in patients with severe trauma: From prehospital care to the Intensive Care Unit

2026-06-02T00:01:59Z

[EN]Objective To identify factors related to mortality in adult trauma patients, analyzing the clinical, epidemiological and therapeutic characteristics at the pre-hospital levels, in the Emergency Care Department and in Intensive Care. Design A retrospective, longitudinal descriptive study was carried out. Statistical analysis was performed using SPSS, MultBiplot and data mining methodology. Setting Adult multiple trauma patients admitted to the Salamanca Hospital Complex (Spain) from 2006 to 2011. Main variables of interest Demographic variables, clinical, therapeutic and analytical data from the injury site to ICU admission. Evolution from ICU admission to hospital discharge. Results A total of 497 patients with a median age of 45.5 years were included. Males predominated (76.7%). The main causes of injury were traffic accidents (56.1%), precipitation (18.4%) and falls (11%). The factors with the strongest association to increased mortality risk (p < 0.05) were age > 65 years (OR 3.15), head injuries (OR 3.1), pupillary abnormalities (OR 113.88), level of consciousness according to the Glasgow Coma Scale ≤ 8 (OR 12.97), and serum lactate levels > 4 mmol/L (OR 9.7). Conclusions The main risk factors identified in relation to the prognosis of trauma patients are referred to the presence of head injuries. Less widely known statistical techniques such as data mining or MultBiplot also underscore the importance of other factors such as lactate concentration. Trauma registries help assess the healthcare provided, with a view to adopt measures for improvement.; [ES]Objetivo Identificar los factores relacionados con la mortalidad de los pacientes adultos politraumatizados, analizar las características clínicas, epidemiológicas y terapéuticas en los niveles prehospitalario, Servicio de Urgencias y Cuidados Intensivos. Diseño Estudio retrospectivo, longitudinal y descriptivo. Análisis estadístico a través del programa SPSS, MultBiplot y la metodología de minería de datos. Ámbito Pacientes adultos politraumatizados ingresados en el Complejo Hospitalario de Salamanca entre los años 2006 y 2011. Variables de interés principales Variables demográficas, clínicas, terapéuticas y analíticas desde el lugar del accidente hasta el ingreso en la UCI. Variables evolutivas durante el ingreso en la UCI y hasta el alta hospitalaria. Resultados Se incluyó a 497 pacientes, con una mediana de edad 45,5 años. Predominio de varones (76,7%). La causa principal del traumatismo fueron los accidentes de tráfico (56,1%), precipitaciones (18,4%) y caídas (11%). Los factores con mayor asociación a un incremento del riesgo de mortalidad (p < 0,05) fueron la edad > 65 años (OR 3,15), el traumatismo craneoencefálico (OR 3,1), las alteraciones pupilares (OR 113,88), el nivel de consciencia según la escala de Glasgow ≤ 8 (OR 12,97) y las cifras de lactato > 4 mmol/L (OR 9,7). Conclusiones Los principales factores de riesgo identificados en relación con el pronóstico de los pacientes politraumatizados son los relacionados con la presencia de traumatismo craneoencefálico. Mediante la utilización de distintas técnicas estadísticas menos conocidas como la minería de datos o el MultBiplot también se destaca la importancia de otros factores como el lactato. Los registros de traumatismos ayudan a conocer la asistencia sanitaria realizada para poder establecer medidas de mejora.

La huella de Federico Cantero Villamil en la sociedad e industria de Castilla y León (1874-1946). Recuperación y difusión de su legado

2026-05-08T11:50:53Z

[ES] Compendio de publicaciones, ponencias, exposiciones, conferencias en torno a la figura de Federico Cantero Villamil. Libro realizado por una treintena de colaboradores del ámbito académico universitario, pilotos de aviación y directores de museos nacionales. Han participado y colaborado en la redacción del documento los profesores de la USAL: , Santiago Manuel López García, María Ascensión Rodríguez Esteban y Pedro Hernández Ramos; [EN] A compilation of publications, presentations, exhibitions, and conferences about Federico Cantero Villamil. This book was compiled by some thirty contributors from the academic field, aviation pilots, and directors of national museums.

An Architectural Multi-Agent System for a Pavement Monitoring System with Pothole Recognition in UAV Images

2026-04-28T00:02:46Z

[EN]In recent years, maintenance work on public transport routes has drastically decreased in many countries due to difficult economic situations. The various studies that have been conducted by groups of drivers and groups related to road safety concluded that accidents are increasing due to the poor conditions of road surfaces, even affecting the condition of vehicles through costly breakdowns. Currently, the processes of detecting any type of damage to a road are carried out manually or are based on the use of a road vehicle, which incurs a high labor cost. To solve this problem, many research centers are investigating image processing techniques to identify poor-condition road areas using deep learning algorithms. The main objective of this work is to design of a distributed platform that allows the detection of damage to transport routes using drones and to provide the results of the most important classifiers. A case study is presented using a multi-agent system based on PANGEA that coordinates the different parts of the architecture using techniques based on ubiquitous computing. The results obtained by means of the customization of the You Only Look Once (YOLO) v4 classifier are promising, reaching an accuracy of more than 95%. The images used have been published in a dataset for use by the scientific community.

Semi-automatic roof modelling from indoor laser-acquired data

2026-04-09T00:01:14Z

[EN] Roof modelling provides useful information for energy analysis, but the methodologies traditionally applied are based on data acquired through aerial vehicles. This requirement makes necessary two data acquisition campaigns: one from indoors and another from outdoors. However, most energy studies can be performed using regularized and simplified models where most of the information of the exhaustive acquisitions is not used. Therefore, this paper proposes a semi-automatic procedure for the 3D modelling of roofs using indoor point clouds, reducing the acquisition campaigns to the indoors campaign. The methodology is based on the hypothesis that surfaces have no thickness, which makes the algorithm especially useful in industrial environments where there are no false ceilings and therefore, the contribution of the roof in the energy behaviour of the building is more important. The methodology is tested on six different scenarios, obtaining their regularized models with relative errors lower than 2% in ideal conditions.