Search

El següent projecte de recerca té com a objectiu facilitar l’accés i l’ús d’imatges mèdiques, en específic imatges histopatològiques, als científics, enginyers i professionals de la salut mitjançant la generació d’imatges sintètiques. Aquestes imatges sintètiques, en tractar-se d’imatges considerades anònimes, compleixen amb les regulacions de protecció de privacitat de dades mèdiques. Aquest enfocament permet crear un conjunt de dades diverses i representatives que aborda els reptes de l’accés limitat i sensible a l’accés de dades mèdiques i proporcionar una eina per entrenar models d’aprenentatge automàtic que tinguin la capacitat de diagnosticar malalties, com per exemple, el càncer de mama, millorant la precisió dels models i la fiabilitat dels resultats., El siguiente proyecto de investigación tiene como objetivo facilitar el acceso y uso de imágenes médicas, en específico imágenes histopatológicas, a los científicos, ingenieros y profesionales de la salud mediante la generación de imágenes sintéticas. Estas imágenes sintéticas, al tratarse de imágenes consideradas anónimas, cumplen con las regulaciones de protección de privacidad de datos médicos. Este enfoque permite crear un conjunto de datos diversos y representativos que aborda los retos del acceso limitado y sensible al acceso de datos médicos y proporcionar una herramienta para entrenar modelos de aprendizaje automático que tengan la capacidad de diagnosticar enfermedades, como por ejemplo, el cáncer de mama, mejorando la precisión de los modelos y la confiabilidad de los resultados., The following research project aims to facilitate the access and use of medical images, specifically histopathological images, to scientists, engineers and health professionals through the generation of synthetic images. These synthetic images, as they are considered anonymous images, comply with the regulations for the protection of medical data privacy. This approach makes it possible to create a diverse and representative dataset that addresses the challenges of limited and sensitive access to medical data and provides a tool for training machine learning models that have the ability to diagnose diseases such as for example, breast cancer, improving the accuracy of the models and the reliability of the results.

Aquest treball de final de màster ha estat realitzat en la Universitat Politècnica de Catalunya, a la facultat de l’Escola Tècnica Superior d’Enginyeria Industrial de Barcelona (ETSEIB). Concretament amb el grup de recerca del laboratori d’Enginyeria Biomecànica (BIOMEC) que forma part del Centre de Recerca d’Enginyeria Biomèdica (CREB). El Grup de Recerca del Laboratori d'Enginyeria Biomècnica (BIOMEC) ha estat treballant en el desenvolupament d'un codi centrat en models impulsats torque-driven. El principal propòsit d'aquest codi és possibilitar la precisa predicción escenaris de control òptim en el context de la marxa, utilitzant models de diversa complexitat. A mesura que ens endinsem en aquesta tesi, es fa evident que s'ha concebut un model més exhaustiu que millora significativament la fidelitat de les simulacions de moviment. Aquesta millora s'aconsegueix mitjançant la incorporació de muscle torque generators (MTG). La utilització d'aquests models impulsats per MTGs serveix per a dues finalitats: avançar en la nostra comprensió del moviment humà i optimitzar les seves aplicacions pràctiques. Aquests models ho aconsegueixen millorant substancialment el realisme i la precisió de les simulacions biomecàniques, ja que reproduïxen amb precisió la dinàmica dels músculs que operen al voltant de les articulacions específiques. En aquesta tesi de màster, es realitza un anàlisi de sensibilitat sobre els efectes dels paràmetres de MTG en les solucions del marc de predicció de control òptim desenvolupat al Laboratori BIOMEC. Per tant, aquesta tesi té com a objectiu establir algunes directrius que aclareixi quins paràmetres de MTG haurien de ser personalitzats per a les simulacions de models musculoesquelètics. A més, realitzen diferents captures d’un cicle de marxa saludable i un moviment de flexió de genolls anomenat “squat” per implementar aquest anàlisi de sensibilitat en aquests dos moviments (caminar i “squat”) basats en el model impulsat per MTG per comprendre si l, Este trabajo final de máster fue realizado en la Universidad Politécnica de Catalunya (UPC), en la facultad de Ingeniería Técnica Superior de Barcelona (ETSEIB). Concretamente, con el grupo de investigación del laboratorio de Ingeniería Biomecànica (BIOMEC) que forma parte del Centro de Recerca de Ingeniería Biomédica (CREB) junto con otros grupos de investigación. El Grupo de Investigación del Laboratorio de Ingeniería Biomécanica(BIOMEC) ha estado trabajando diligentemente en el desarrollo de un código centrado en torque-driven models. El propósito principal de este código es permitir la predicción precisa de escenarios de control óptimo en el contexto de la marcha, utilizando modelos de variada complejidad. A medida que nos adentramos en esta tesis, se hace evidente que se ha ideado un modelo más intrincado que mejora significativamente la fidelidad de las simulaciones de movimiento. Esta mejora se logra mediante la incorporación de muscle torque generators (MTGs). La utilización de estos MTG-driven models cumple con el doble propósito de avanzar en nuestra comprensión del movimiento humano y optimizar sus aplicaciones prácticas. Estos modelos logran esto al mejorar sustancialmente el realismo y precisión de las simulaciones biomecánicas, ya que replican con precisión la dinámica de los músculos que operan alrededor de articulaciones específicas. En esta tesis, se realiza un análisis de sensibilidad sobre los efectos de los parámetros de MTG en las soluciones del marco de predicción de control óptimo desarrollado en el Laboratorio BIOMEC. Por lo tanto, esta tesis tiene como objetivo establecer algunas pautas que aclaren qué parámetros de MTG deben personalizarse para las simulaciones de modelos musculoesqueléticos. Además, se captura un ciclo de marcha saludable y un movimiento de sentadilla saludable para implementar este análisis de sensibilidad en estos dos movimientos (caminar y sentadilla) basados en el modelo impulsado por MTG para comprender si la sensibil, This Final Master Project was done in the Polytechnic University of Catalunya, in the Industrial Superior Technical Engineering School of Barcelona(ETSEIB). To be specific, it was done inside the Researching Group of Biomedical Engineering (CREB), being part of the Biomechanical Engineering (BIOMEC) Lab research group. The Biomechanical Engineering Lab Research Group (BIOMEC) has been diligently working on developing a code centered around torque-driven models. This code's primary purpose is to enable the precise prediction of optimal control scenarios in the context of walking, utilizing models of varying complexity. As we delve into this thesis, it becomes evident that a more intricate model has been devised, which significantly improves the fidelity of motion simulations. This enhancement is achieved through the incorporation of muscle torque generators(MTGs) into the existing framework. The utilization of these muscle torque generators-driven models serves the dual purpose of advancing our comprehension of human movement and optimizing their practical applications. These models achieve this by substantially enhancing the realism and precision of biomechanical simulations, as they accurately replicate the dynamics of muscles operating around specific joints. In this master thesis, a sensitivity analysis on the effects of the MTG parameters on the solutions of the optimal control prediction framework developed at BIOMEC Lab is performed. This thesis, therefore, aims to establish some guidelines that clarify which MTG parameters should be personalized for simulations of musculoskeletal models. Moreover, a healthy gait cycle and a healthy squat movement is captured in order to implement this sensitivity analysis into these two motions (walking and squat) based on the MTG-driven model to understand whether the sensitivity of the optimal control solution to the MTG parameters depends on the activity. Along this thesis report, all the processes involved in the sensitiv

Traditional psychiatric hospitalization models have been criticized for being restrictive and for violating fundamental rights, which can be counterproductive for long-term patient recovery. In response to this situation, new hospitalization models have been developed that aim to create a safe therapeutic environment that promotes patient recovery, while minimizing the need for coercive measures. The psychiatry unit from Germans Trias i Pujol Hospital (HGTiP) has designed a dual model that combines a care method, called Safewards, with a risk prediction tool in emergencies and a risk categorization and workload tool on the ward through a global score. The objective of the model is to safely open the unit doors, taking into account the risks and the level of work of the care team. The tools currently used are not scientifically validated, thus hindering the scalability of the model. Therefore, the purpose of this project is to develop a proposal for intervention to develop two Artificial Intelligence (AI) algorithms, using validated variables, that predict the unit environment and patient risk at the time of admission. First, a qualitative study was conducted with expert personnel from the psychiatric unit at HGTiP to objectify the criteria by which risk level and workload on the ward are defined. A total of 35 items were extracted, and a digital platform was developed to store them. These will be used, along with other dynamic variables, as input into a regression algorithm. In addition, classification algorithms will be developed to predict the level of risk in the first 24 hours of admission. The input data will have variables related to symptoms and conflictive events in the last month. For both cases, the performance of different algorithms will be evaluated, and the one with the best predictive character will be chosen. This dual model, which uses Artificial Intelligence as a tool to support clinical decision-making, sets a precedent in risk control in open doo, Los modelos de hospitalización psiquiátrica tradicionales han sido criticados por ser restrictivos y vulnerar derechos fundamentales, lo que puede ser contraproducente para la recuperación de los pacientes a largo plazo. En respuesta a esta situación, se han desarrollado nuevos modelos de hospitalización que pretenden crear un ambiente terapéutico seguro y que promueva la recuperación del paciente, minimizando la necesidad de medidas coercitivas. El Hospital Germans Trias i Pujol, ha diseñado un modelo dual, que combina un método asistencial, llamado Safewards, con una herramienta de predicción de riesgos en urgencias y una categorización de riesgos y de carga asistencial en planta a través de una puntuación global. El objetivo del modelo es abrir las puertas de la unidad de manera segura, teniendo en cuenta los riesgos y el nivel de trabajo del equipo asistencial. Las herramientas que se usan actualmente no están validadas científicamente, dificultando así la escalabilidad del modelo. Por lo que la finalidad de este proyecto es elaborar una propuesta de intervención para desarrollar dos algoritmos de Inteligencia Artificial, con variables validadas, que predigan el ambiente de la unidad y el riesgo de un paciente en el momento de ingreso. En primer lugar, se ha realizado un estudio cualitativo con personal experto de la unidad de psiquiatría del HGTiP para objetivar los criterios por los que se define el nivel de riesgo y la carga asistencial en planta. Se han extraído un total de 35 ítems y se ha desarrollado una plataforma digital para almacenarlos. Estos serán utilizados, junto a otras variables dinámicas, como entrada en un algoritmo de regresión. Por otra parte, se desarrollarán algoritmos de clasificación para predecir el nivel de riesgo en las primeras 24 horas de ingreso. Los datos de entrada serán variables relacionadas con sintomatología y eventos conflictivos en el último mes. Para ambos casos, se evaluará el rendimiento de diferentes algoritmos y se ele, Els models d'hospitalització psiquiàtrica tradicionals han estat criticats per ser restrictius i vulnerar drets fonamentals, cosa que pot ser contraproduent per a la recuperació dels pacients a llarg termini. En resposta a aquesta situació, s'han desenvolupat nous models d'hospitalització que pretenen crear un ambient terapèutic segur i que promogui la recuperació del pacient, minimitzant la necessitat de mesures coercitives. L'Hospital Germans Trias i Pujol, ha dissenyat un model dual, que combina un mètode assistencial, anomenat Safewards, amb una eina de predicció de riscos a urgències i una categorització de riscos i de càrrega assistencial a planta a través d'una puntuació global. L'objectiu del model és obrir les portes de la unitat de manera segura, tenint en compte els riscos i el nivell de treball de l'equip assistencial. Les eines que es fan servir actualment no estan validades científicament, dificultant així l'escalabilitat del model. La finalitat d'aquest projecte és elaborar una proposta d'intervenció per desenvolupar dos algorismes d'Intel·ligència Artificial, amb variables validades, que prediguin l'ambient de la unitat i el risc d'un pacient a l'ingrés. En primer lloc, s'ha fet un estudi qualitatiu amb personal expert de la unitat de psiquiatria de l'HGTiP per objectivar els criteris pels quals es defineix el nivell de risc i la càrrega assistencial a planta. Se n'han extret un total de 35 ítems i s'ha desenvolupat una plataforma digital per emmagatzemar-los. Aquests seran utilitzats, juntament amb altres variables dinàmiques, com a entrada en un algorisme de regressió. D'altra banda, es desenvoluparan algorismes de classificació per predir el nivell de risc en les primeres 24 hores d’ingrés. Les dades d'entrada seran variables relacionades amb simptomatologia i esdeveniments conflictius a l'últim mes. Per a tots dos casos, s'avaluarà el rendiment de diferents algorismes i es triarà el que millor caràcter predictiu tingui. Aquest model dual, que uti

El present treball explora la utilització de xarxes neuronals convolucionals (CNN, per les seves sigles en anglès) per a l'anàlisi d'electrocardiogrames (ECG) amb l'objectiu de detectar i classificar arrítmies. Aquesta recerca es basa en l'aplicació de tècniques d'aprenentatge automàtic, concretament, utilitzant CNN per interpretar les dades d'ECG. En la metodologia, s'ha dissenyat i implementat un prototip que utilitza CNN per processar i analitzar senyals d'ECG. Les dades utilitzades per entrenar aquesta xarxa provenien de bases de dades públiques d'ECG. Les proves van consistir en la identificació i classificació de diferents tipus d'arrítmies a partir d'aquests senyals a familiars i a mi mateix. Els resultats obtinguts indiquen que les xarxes neuronals convolucionals són una eina potent per a l'anàlisi d'ECG. Han demostrat una alta precisió en la detecció i classificació d'arrítmies sobre dades ideals. No obstant això, en el cas de la classificació en temps real s'ha observat que la qualitat del senyal d'ECG i la col·locació correcta dels elèctrodes són factors crítics que poden afectar la precisió del sistema. En les conclusions, malgrat els desafiaments trobats, la utilització de CNN en l'anàlisi d'ECG es mostra prometedora. No obstant això, és necessari seguir treballant per millorar la robustesa i generalització de la xarxa, explorant diferents arquitectures i conjunts de dades d'entrenament més diverses. També es recomana investigar més en l'àmbit de la instrumentació ECG, per millorar la col·locació dels elèctrodes i reduir el soroll, Este trabajo explora el uso de redes neuronales convolucionales (CNN, por sus siglas en inglés) para el análisis de electrocardiogramas (ECG) con el objetivo de detectar y clasificar arritmias. Esta investigación se basa en la aplicación de técnicas de aprendizaje automático, específicamente, utilizando CNN para interpretar los datos del ECG. En la metodología, se ha diseñado e implementado un prototipo que utiliza CNN para procesar y analizar señales de ECG. Los datos utilizados para entrenar esta red provenían de bases de datos públicas de ECG. Las pruebas consistieron en la identificación y clasificación de diferentes tipos de arritmias a partir de estas señales en familiares y en mí mismo. Los resultados obtenidos indican que las redes neuronales convolucionales son una herramienta potente para el análisis de ECG. Han demostrado una alta precisión en la detección y clasificación de arritmias en datos ideales. Sin embargo, en el caso de la clasificación en tiempo real, se ha observado que la calidad de la señal de ECG y la colocación correcta de los electrodos son factores críticos que pueden afectar la precisión del sistema. En las conclusiones, a pesar de los desafíos encontrados, el uso de CNN en el análisis de ECG se muestra prometedor. Sin embargo, es necesario seguir trabajando para mejorar la robustez y generalización de la red, explorando diferentes arquitecturas y conjuntos de datos de entrenamiento más diversos. También se recomienda investigar más en el campo de la instrumentación ECG, para mejorar la colocación de los electrodos y reducir el ruido, This work explores the use of convolutional neural networks (CNN) for the analysis of electrocardiograms (ECG) with the aim of detecting and classifying arrhythmias. This research is based on the application of machine learning techniques, specifically, using CNN to interpret ECG data. In the methodology, a prototype has been designed and implemented that uses CNN to process and analyse ECG signals. The data used to train this network came from public ECG databases. The tests consisted of the identification and classification of different types of arrhythmias from these signals in relatives and in myself. The results obtained indicate that convolutional neural networks are a powerful tool for ECG analysis. They have demonstrated high precision in the detection and classification of arrhythmias on ideal data. However, in the case of real-time classification, it has been observed that the quality of the ECG signal and the correct placement of the electrodes are critical factors that can affect the system's accuracy. In the conclusions, despite the challenges encountered, the use of CNN in ECG analysis is promising. However, it is necessary to continue working to improve the robustness and generalization of the network, exploring different architectures and more diverse training data sets. Further research is also recommended in the field of ECG instrumentation, to improve electrode placement and reduce noise

The quality of life of people with epilepsy is considerably altered by the risk involved in the accidents that epileptic seizures can cause while carrying out their daily live activities. It is for this reason that several attempts have been made to try to predict epileptic seizures before they occur. This project proposes to make use of the Hierarchical Temporal Memory model, an anomaly detector inspired by the neocortex, for the detection of abnormalities in the EEG signal, specifically, the preictal activity prior to the seizure. The main benefits of this innovative neural network are that it allows online unsupervised learning with streaming data, as well as adaptation to behavioural changes of the input, since it is continuously learning and updating as it sees new records. After understanding the model basis and replicating some available examples, an application programming interface has been created with the HTM model, which returns the anomaly likelihood as output value, a metric that describes the probability of a record of being anomalous. The aim is to obtain an output that allows us stablishing a threshold to differentiate between anomalous and non-anomalous data. The optimal model parameters and their influence on the output have been studied, being resolution and anomaly period the ones with a more direct impact on the model performance. Additionally, it has been discussed how resampling is a crucial step during the pre-processing phase in order to ease the sequential pattern learning of the algorithm. For the study, firstly, the performance of the model has been evaluated with a synthetic dataset constructed from real patient data, and it has been possible to see how the model is capable of detecting epileptic seizures as abnormal, but does not successfully detect anomalies in the data records that precede the seizure. It has also been seen how the model learned seizures as non-anomalous after having seen one before, so tests have been carried out tr, La calidad de vida de las personas con epilepsia se ve considerablemente alterada por el riesgo de sufrir crisis epilépticas y los accidentes que pueden ocasionar durante el desarrollo de sus actividades vitales cotidianas. Es por ello que se han realizado diversos intentos para tratar de predecir las crisis epilépticas antes de que se produzcan. Este proyecto propone hacer uso del modelo Hierarchical Temporal Memory, una red neuronal inspirada en el neocórtex, para la detección de anomalías en la señal EEG, concretamente, la actividad preictal previa a la crisis. Las principales ventajas de esta innovadora red neuronal son que permite el aprendizaje online no supervisado de datos a tiempo real, así como la adaptación a los cambios de comportamiento de los datos de entrada. Tras comprender las bases del modelo y replicar algunos ejemplos disponibles, se ha creado un programa con el modelo HTM, que devuelve como valor de salida la probabilidad de anomalía, una métrica que describe la probabilidad de que un registro sea anómalo. El objetivo es obtener una respuesta que nos permita establecer un umbral para diferenciar entre datos anómalos y no anómalos. Se han estudiado los parámetros óptimos del modelo y su influencia en la salida, siendo la resolución y el periodo de anomalía los que tienen un impacto más directo en el rendimiento del modelo. Además, se ha discutido cómo el remuestreo es un paso crucial durante la fase de preprocesamiento para facilitar el aprendizaje secuencial de patrones del algoritmo. Para el estudio, en primer lugar, se ha evaluado el rendimiento del modelo con señales EEG sintéticas construidas a partir de datos reales de pacientes, y se ha podido comprobar cómo el modelo es capaz de detectar ataques epilépticos como anormales, pero no detecta con éxito anomalías en los registros de datos que preceden a la crisis. También se ha visto como el modelo aprendía las crisis como no anómalas después de haber visto una anteriormente, por lo que se han, La qualitat de vida de les persones amb epilèpsia es veu considerablement alterada pel risc de patir crisis epilèptiques i els accidents que poden ocasionar durant el desenvolupament de les activitats quotidianes. És per això que s'han realitzat diversos intents per predir les crisis epilèptiques abans que es produeixin. Aquest projecte proposa fer ús del model Hierarchical Temporal Memory, una xarxa neuronal inspirada en el neocòrtex, per a la detecció d'anomalies al senyal EEG, concretament, l'activitat preictal prèvia a la crisi. Els principals avantatges d'aquesta innovadora xarxa neuronal són que permet l'aprenentatge en línia no supervisat de dades a temps real, així com l'adaptació als canvis de comportament de les dades d'entrada. Després de comprendre les bases del model i replicar-ne alguns exemples disponibles, s'ha creat un programa amb el model HTM, que torna com a valor de sortida la probabilitat d'anomalia, una mètrica que descriu la probabilitat que un registre sigui anòmal. L'objectiu és obtenir una resposta que ens permeti establir un llindar per diferenciar entre dades anòmales i no anòmales. S'han estudiat els paràmetres òptims del model i la seva influència a la sortida, sent la resolució i el període d'anomalia els que tenen un impacte més directe en el rendiment del model. A més, s'ha discutit com el remostreig és un pas crucial durant la fase de preprocessament per facilitar l'aprenentatge seqüencial de patrons de l'algorisme. Per a l'estudi, en primer lloc, s'ha avaluat el rendiment del model amb senyals EEG sintètics construïts a partir de dades reals de pacients, i s'ha pogut comprovar com el model és capaç de detectar la senyal durant la crisis epilèptica com a anormal, però no detecta amb èxit anomalies als registres de dades que precedeixen la crisi. També s'ha vist com el model aprenia les crisis com no anòmales després d'haver-ne vist una anteriorment, per la qual cosa s'han realitzat proves entrenant-se amb dades interictals, per pos

Technological and medical advances in recent decades have promoted a lengthening of life expectancy, leading to an increase in age-associated cognitive diseases. As a result, there is a growing interest in efficient and cost-effective technological alternatives for the early detection of cognitive problems. Recent studies show growing evidence of a relationship between electrocardiogram (ECG) parameters and cognitive decline. For this reason, this study aims to assess the validity of ECG markers to detect mild cognitive impairment in elderly subjects. The 'Lemon' database, that contains the cognitive and ECG results of 227 healthy adults, has been analysed. Initially, the electrocardiographic signals have been filtered and adapted to extract multiple relevant ECG markers. To assess the reliability of these markers, several tests were conducted. A statistical analysis between cognitive categories, a machine learning classification problem, and multiple regressions with the additional tests included in the database. The analysis focused on elderly patients, who are classified in three cognitive groups according to their impairment (normal, moderate, and severe). Given the statistical significance between cognitive categories and the favourable results obtained in the regression analysis, two markers should be emphasised: the traditional temporal ratios of heart rate variability (HRV), such as the average beat, a measure of the average between QRS peaks, and the fragmentation ratios (HRF), an estimate of cardiac neuroautonomic dysfunction measured by variations in the QRS interval. Among the different classifiers, the artificial neural network (ANN) stands out, providing the best and most stable classification ratios (55.00 % accuracy, 47.60 % sensitivity, 50.00 % precision, in a three class, five-cross-fold problem). The reported tendency to correctly differentiate normal subjects must be emphasized. This is observed both in the statistical tests, where no significanc

L’objectiu principal d’aquest treball és explorar els camps de la Intel∙ligència Artificial explicable (XAI per les seves sigles en anglès) i de la Intel∙ligència Artificial multimodal, arribant a desenvolupar un mètode d’explicabilitat per a Intel∙ligència Artificial multimodal en l’àmbit de la salut. S’ha concretat una metodologia per obtenir explicacions dels models que combinen la informació extreta de més d’una modalitat de dades. L’estratègia es basa en extreure característiques de les imatges que es puguin presentar en format tabular per posteriorment ser annexades a les dades clíniques tabulars i aplicant mètodes d’explicabilitat a un model entrenat amb totes les dades tabulars. El mètode desenvolupat està acotat a casos d’ús que combinin imatge mèdica i dades clíniques tabulars, és agnòstic al model, proporciona explicabilitat global i local i és de possible aplicació en múltiples casos d’ús. Per provar i millorar el mètode desenvolupat, s’ha utilitzat un cas d’ús de diagnòstic de la Malaltia d’Alzheimer (MA), incorporant imatges de ressonància magnètica (MRI, per les seves sigles en anglès) i dades clíniques tabulars per a cada pacient. El resultat d’aquest projecte el conformen aquesta Memòria i Annexos, així com tres documents en format notebook amb tot el codi desenvolupat en llenguatge Python. Es conclou que el treball té moltes possibilitats d’ampliació i optimització futures., El principal objetivo de este trabajo es explorar los campos de la Inteligencia Artificial explicable (XAI por sus siglas en inglés) y de la Inteligencia Artificial multimodal, llegando a desarrollar un método de explicabilidad para Inteligencia Artificial multimodal en el ámbito de la salud. Se ha concretado una metodología para obtener explicaciones de los modelos que combinan la información extraída de más de una modalidad de datos. La estrategia se basa en extraer características de las imágenes que se puedan presentar en formato tabular para posteriormente ser anexados a los datos clínicos tabulares y aplicando métodos de explicabilidad a un modelo entrenado con todos los datos tabulares. El método desarrollado está acotado a casos de uso que combinen imagen médica y datos clínicos tabulares, es agnóstico al modelo, proporciona explicabilidad global y local y es de posible aplicación en múltiples casos de uso. Para probar y mejorar el método desarrollado, se ha utilizado un caso de uso de diagnóstico de la Enfermedad de Alzheimer, incorporando imágenes de resonancia magnética (MRI, por sus siglas en inglés) y datos clínicos tabulares para cada paciente. El resultado de este proyecto lo conforman esta Memoria y Anexos, así como tres documentos en formato notebook con todo el código desarrollado en lenguaje Python. Se concluye que el trabajo tiene muchas posibilidades de ampliación y optimización futuros., The main goal of this work is to explore the fields of eXplainable Artificial Intelligence (XAI) and multimodal Artificial Intelligence, developing an explainability method for multimodal Artificial Intelligence in the field of health. This work specifies a methodology to obtain explanations of the models that combine the information extracted from more than one data modality. The strategy is based on extracting characteristics from the images that can be presented in tabular format, attaching them afterwards to the tabular clinical data and applying explainability methods to a model trained with all the tabular data. The developed method is limited to the use cases that combine medical imaging and tabular clinical data, it is agnostic to the model, provides global and local explainability and it can be applied in multiple use cases. To test and improve the developed method, a diagnostic use case of Alzheimer’s Disease (AD) has been used, incorporating magnetic resonance images (MRI) and tabular clinical data for each patient. The result of this project consists on this Report and Annexes, as well as three documents in notebook format with all the code developed in Python. It is concluded that this work has many opportunities of improvement and optimization.

La pandèmia viscuda arreu del món a inicis del món a causa del SARS-CoV-2, agent causant de la malaltia coneguda com a coronavirus, ha vist reflectida la necessitat de models matemàtics que poguessin ajudar a explicar a la població com es trobava la pandèmia usant indicadors, paràmetres i gràfics que, de forma senzilla, donessin un estat el qual s’anava actualitzant diàriament i així poder prendre decisions pel que fa a mesures sanitàries i de control i aïllament social. En aquest treball es vol realitzar una comparativa a partir de les dades reals de la pandèmia al territori català, el Baix Llobregat i a l’Alt Penedès treballades mitjançant els model de Gompertz i ARIMA. Per a tots dos models, amb el programari Matlab, s’han validat les dades de partida, s’han realitzat modelitzacions i s’ha comprovat que, efectivament, són capaces de realitzar pronòstics en quant a casos de coronavirus i en quant a la mortalitat de la malaltia. Pel model de Gompertz, model ja conegut i utilitzat en dinàmiques de poblacions en ser un model amb paràmetres físics, s’obtenen resultats prou satisfactoris a partir d’aquests paràmetres, ajustats a partir de l’optimització no lineal per mitjà de mínims quadrats. Pel que fa al model ARIMA, en ser aquest un model autoregressiu, necessita de l’estudi de la sèrie temporal, el tractament d’aquesta i el tenir un algoritme propi per a poder modelitzar els seus paràmetres, els quals no són físics si no matemàtics. A més, es corre el risc de cometre overfitting, o sobreentrenar el model, si s’utilitza tota la sèrie temporal. Així, s’ha decidit usar mètodes de train/test amb les dades inicials per a dur a terme el model, obtenint uns resultats molt satisfactoris, tot i ser més complicats de tractar. Així doncs, durant l’estudi es trobaran explicacions de caire teòric de les sèries temporals i els models estudiats, com s’han validat i a quins territoris, avaluant els errors relatius comesos respecte als territoris que serveixen de referència, i per

Sentinel lymph node status is a crucial prognosis factor for melanomas; nonetheless, the invasive surgery required to obtain it always puts the patient at risk. In this study, we develop a Deep Learning-based approach to predict lymph node metastasis from Whole Slide Images of primary tumours. Albeit very informative, these images come with complexities that hamper their use in machine learning applications, namely their large size and limited datasets. We propose a pre-training strategy based on self-supervised contrastive learning to extract better image feature representations and an attention-based Multiple Instance Learning approach to enhance the model’s performance. With this work, we quantitatively demonstrate that combining both methods improves various classification metrics and qualitatively show that contrastive learning encourages the network to output higher attention scores to tumour tissue and lower scores to image artifacts., Work supported by the Spanish Research Agency (AEI) under project PID2020-116907RB-I00 of the call MCIN/AEI/10.13039/501100011033 and the project 718/C/ 2019 funded by Fundació la Marato de TV3., Peer Reviewed, Postprint (author's final draft)

On the one hand, clinical trials are of great importance in discovering new treatments for diseases. They teach research things that cannot be learned in the laboratory, that is, what does and does not work in humans. What’s more, they are a really helpful tool for deciding whether the side effects of a new drug or treatment are acceptable compared to the potential benefits. Since results are not known at the beginning, this process is quite uncertain and effective management of doses is required. On the other hand, Reinforcement Learning is a Machine Learning paradigm different from Supervised Learning and Unsupervised Learning. Unlike these two methods, Reinforcement Learning is used when we want a system to accomplish a task by understanding the task by itself and the system must learn based on the “trial and error” rule. In recent years, several Reinforcement Learning applications have brought great advances in different fields. However, this new paradigm has not been used for optimizing the inventory management of clinical trials, so that’s why this master thesis addresses this line of investigation. The contributions of this master thesis are: (1) The definition of the Markov Decision Process formulation for the current problem, (2) The application of Tabular Methods to solve the problem, and (3) The improvement of the used Tabular Methods by modifying their respective Q-Tables. Results show a considerable improvement after the Q-Table’s modification. However, the system does not achieve a great performance mainly due to the high dimensionality of the problem, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar

The management of sick leaves is a critical task that public and private health systems carry out. This enables the good care of sick workers and guarantees a safe return to their jobs. Most health systems enforce regulations that establish the duration of sick leave according to general rules for groups of diagnoses. However, these regulations do not account for the particularities of workers. On the one hand, an early return to work is sometimes possible, but this does not happen unless the worker pro-actively requests it. On the other hand, the worker’s health condition could demand for one or more leave extensions, but the system requires mandatory and sometimes unnecessary follow-ups, adding nuisance to patients and overhead to health systems. In both cases, the lack and excess of action by the health system represents extra costs for society. This paper proposes the analysis of a voluminous historical dataset of sick leaves (including medical and personal data) to predict the duration of future sick leaves for patients. The data mining process is performed for a large number of diagnoses to assess the possibility of using data driven models for broad decision-making. The nature and characteristics of the data makes it difficult to obtain models using classical methods, which is why the analysis focuses on non-linear machine learning-based survival analysis methods. In sight of the models performance, we move forward to its practical implementation, proposing a tool to manage the decision of what patients should be contacted at a given date using the predictions of the trained models. This tool will manage the whole cycle, continuously training on new data, performing daily predictions, and presenting the results to the health-care decision-maker for their assessment., This work has been funded by a collaboration between Asepeyo and BSC. We want to thank the following people from Asepeyo for their help and support that made this project possible. Xavier Calatrava Petisme, Alex Nogué Martinez, Enric Lleal Serra, Francisco Manuel Ventura Nofuentes, Oscar González Cherta, Francisco Sánchez Algarra, Eulàlia Borén and Vanessa Vegazo. We also want to thank to Nadia Tonello (BSC Data Manager) and Ulises Cortés (UPC/BSC) for their insightful comments., Peer Reviewed, Postprint (author's final draft)

Objectius de Desenvolupament Sostenible::3 - Salut i Benestar

The current research focus in Robot-Assisted Minimally Invasive Surgery (RAMIS) is directed towards increasing the level of robot autonomy, to place surgeons in a supervisory position. Although Learning from Demonstrations (LfD) approaches are among the preferred ways for an autonomous surgical system to learn expert gestures, they require a high number of demonstrations and show poor generalization to the variable conditions of the surgical environment. In this work, we propose an LfD methodology based on Generative Adversarial Imitation Learning (GAIL) that is built on a Deep Reinforcement Learning (DRL) setting. GAIL combines generative adversarial networks to learn the distribution of expert trajectories with a DRL setting to ensure generalisation of trajectories providing human-like behaviour. We consider automation of tissue retraction, a common RAMIS task that involves soft tissues manipulation to expose a region of interest. In our proposed methodology, a small set of expert trajectories can be acquired through the da Vinci Research Kit (dVRK) and used to train the proposed LfD method inside a simulated environment. Results indicate that our methodology can accomplish the tissue retraction task with human-like behaviour while being more sample-efficient than the baseline DRL method. Towards the end, we show that the learnt policies can be successfully transferred to the real robotic platform and deployed for soft tissue retraction on a synthetic phantom., Peer Reviewed, Postprint (author's final draft)

Corona Virus Disease 2019 (COVID-19) is a new disease that is based on the SARSCoV- 2 virus. The virus has caused a worldwide pandemic due to its high infection rate and severity of symptoms. Several methods for detecting the virus exist among which different medical imaging modalities, in particular X-Ray imaging. In this thesis, we propose a three-phase machine learning approach to detect, from X-Ray images, whether a person is infected with the virus or not. The approach relies on an ensemble of customized convolutional neural networks to extract essential features from input images. The extracted features undergo fusion and are then passed on to a classifier for final results. We validated the approach on a set of 3,886 X-Ray images of patients carrying the virus, patients suffering from viral pneumonia, and healthy persons. When benchmarked against several models published in the literature, our proposed model outperformed them all.

Skin cancer is a major public health issue with millions of cases diagnosed around the world. Melanoma is the most mortal form of skin cancer and causes the highest percentage of deaths. Although the mortality rate for melanoma is significant, when an early diagnosis is made more than the 95% of people survive. Therefore, a neural network image classification would be significantly helpful during diagnosis. Artificial neural networks have become a popular machine learning model due to the ability to make nonlinear and complex relationships between thousands of variables. In fact, on occasion convolutional neural networks pattern detection abilities surpass their human counterparts. The main objective of this thesis is to design a convolutional neural network which is able to distinguish melanoma from other skin lesions with a high rate of accuracy. Neural networks were trained and tested using images from HAM10000 dataset. Using a replicated factorial fractional design of experiments, we have realized the importance of balance in classification. Using different oversampling methods we have obtained a F1-score of 84% in the test data. As a result, we have demonstrated that it is possible to classify melanoma with greater precision. In fact, these results appear to be better than the usual results achieved through multi-class classification. Furthermore, we believe that with more computational capabilities better results could be reached, El càncer de pell és un problema important de salut pública, amb milions de casos diagnosticat sarreu del món. El melanoma és la forma més mortal de càncer de pell, responsable de la immensa majoria de les morts per càncer de pell. Tot i que la mortalitat és significativa, quan es detecta precoçment, la supervivència del melanoma supera el 95%. És per aquest motiu que la classificació d'imatges mitjançant xarxes neuronals pot ser de gran ajuda per als diagnòstics.Les xarxes neuronals són un model d'aprenentatge automàtic molt utilitzat actualment per la seva capacitat d'establir relacions complexes i no lineals entre milers de variables, i arriben a superar-les capacitats humanes en detecció de patrons. L'objectiu principal d'aquest projecte és crear una xarxa neuronal convolucional capaç de distingir els melanomes entre diferents lesions cutànies amb gran precisió.Les xarxes neuronals han sigut entrenades i provades fent servir les imatges de la basede dades HAM10000. A partir d'un disseny d'experiments factorial fraccionat de 26-2 amb rèpliques s'ha obtingut el coneixement necessari per centrar-se en el balanceig de les classes en la classificació binària. S'ha obtingut una F1-score de 84% en el seu test. Aquests resultats demostren que és possible fer aquesta classificació amb gran precisió d'aquestes imatges dels melanomes. De fet, sembla que aquests resultats són millors que els que s'acostumen a obtenir mitjançant una classificació de múltiples classes i es creu que, amb més capacitats computacionals, es podria obtenir encara millors resultats, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar

Unas décadas atrás, nació Deep Learning, una técnica que revolucionó el mundo de la Inteligencia Artificial tal y como se conocía. Esta imita el funcionamiento neuronal de un cerebro humano para clasificar conjuntos de datos y encontrar patrones entre ellos. Gracias a este sistema computacional, en este trabajo se ha podido diseñar un modelo clasificatorio de imágenes que detecte la neumonía. Para ello, se ha hecho uso de la metodología Transfer Learning. Esta se basa en utilizar modelos entrenados previamente para crear el nuevo modelo. Además se ha utilizado las redes neuronales convolucionales como extractoras de patrones. Se ha decidido identificar esta patología porque la neumonía es una infección respiratoria que, si se complica, puede llegar a ser letal, sobre todo en niños menores de cinco años. Del mismo modo, se ha creado este modelo con el objetivo de que se pueda utilizar en estudios clínicos para así poder encontrar nuevos tratamientos o controlar la enfermedad. Para crear el modelo, se ha utilizado la librería Fast.ai. debido a que tiene componentes de alto nivel que permiten proporcionar resultados de forma más sencilla y rápida. El conjunto de datos utilizados para crear el modelo se ha extraído de la página web Kaggle. Como se quería obtener el mejor rendimiento posible, se han realizado cuatro modelos distintos a partir de cuatro modelos pre entrenados; ResNet 18, ResNet 34, ResNet 50 y AlexNet. Al final, se han acabado obteniendo resultados muy buenos a partir de todos los modelos, incluso en tres de ellos se ha alcanzado una precisión mayor del 99%. Aun así, ha sido a partir de ResNet 50 que se ha obtenido el mejor rendimiento y con el que se ha creado el programa que consigue detectar la neumonía, A few decades ago, Deep Learning appeared revolutionizing the world of Artificial Intelligence as it was known. This technique mimics the neural functioning of a human brain to classify data sets and to find patterns among them. Thanks to this computational system, it has been possible to design through this project a classifying model of images that detects pneumonia. Transfer Learning has been the methodology used to achieve so. This method is based on using previously trained models to create the new model. Furthermore, convolutional neural networks have been used as pattern extractors. It was decided to identify this pathology because pneumonia is a respiratory infection that, if it gets bad, can be lethal, especially in children under five years old. Likewise, this model has been created with the aim of being used in clinical studies in order to find new treatments and to control the disease. To create the model, the Fast.ai. library has been used because it has high-level components that can quickly and easily provide results. The dataset used to create the model was extracted from the Kaggle website. As it was wanted to obtain the best possible performance, four different models have been made from four pre-trained models; ResNet 18, ResNet 34, ResNet 50 and AlexNet. In the end, very good results have been obtained from all the models, even in three of them an accuracy of more than 99% has been achieved. However, the best performance was obtained from ResNet 50. It was with this model that the program that detects pneumonia was created, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar::3.4 - Per a 2030, reduir en un terç la mortalitat prematura per malalties no transmissibles, mitjançant la prevenció i el tractament, i promoure la salut mental i el benestar

La Inteligencia Artificial se ha vuelto una disciplina que trata cualquier ámbito, en este trabajo se ha realizado una aplicación en el ámbito de la salud. Se ha creado un modelo de aprendizaje automático, que clasifica imágenes de rayos-X del tórax, en positivas o negativas frente al virus COVID-19, previamente clasificados. El objetivo de este trabajo es encontrar un modelo que realice dicha clasificación correctamente, mediante redes neuronales. Los datos utilizados son proporcionados por la página web kaggle[12] y se trata de datos desequilibrados, se han estudiado los parámetros, métodos y métricas a tener en cuenta a la hora de clasificar datos desequilibrados. Se han entrenado varios modelos, un primer modelo con los datos desequilibrados, un segundo modelo añadiendo un ajuste al modelo anterior y finalmente, se ha realizado un modelo a partir de un subconjunto de las muestras para poder tratar con datos equilibrados y mejorar la clasificación. Los resultados obtenidos no han sido los esperados, debido a la similitud entre las imágenes y la complicación que conlleva tratar con datos desequilibrados, sin embargo, se han obtenido resultados significativos. El modelo que mejor ha realizado la clasificación ha conseguido detectar un 45,5 % de las muestras con COVID-19, Artificial Intelligence has become a discipline that deals with any field, in this work an application has been made in the field of health. A deep learning model has been created, which classifies X-ray images of the chest, as positive or negative against the COVID-19 virus, previously classified. The objective of this work is to find a model that performs this classification correctly, using neural networks. The data used are provided by the kaggle [12] website and it is about unbalanced data. The parameters, methods and metrics to take into account when classifying unbalanced data have been studied. Several models have been trained, a first model with unbalanced data, a second model adding an adjustment to the previous model and finally, a model has been made from a subset of the samples to be able to deal with balanced data and improve the classification. The results obtained have not been as expected, due to the similarity between the images and the complication involved in dealing with unbalanced data, however, significant results have been obtained. The model that performed the best classification detected 45.5 % of the samples with COVID-19, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar

In personalized healthcare, an ecosystem for the manipulation of reliable and safe private data should be orchestrated. This paper describes an approach for the generation of synthetic electrocardiograms (ECGs) based on Generative Adversarial Networks (GANs) with the objective of anonymizing users’ information for privacy issues. This is intended to create valuable data that can be used both in educational and research areas, while avoiding the risk of a sensitive data leakage. As GANs are mainly exploited on images and video frames, we are proposing general raw data processing after transformation into an image, so it can be managed through a GAN, then decoded back to the original data domain. The feasibility of our transformation and processing hypothesis is primarily demonstrated. Next, from the proposed procedure, main drawbacks for each step in the procedure are addressed for the particular case of ECGs. Hence, a novel research pathway on health data anonymization using GANs is opened and further straightforward developments are expected., Peer Reviewed, Postprint (published version)

With people living longer than ever, the number of cases with dementia such as Alzheimer's disease increases steadily. It affects more than 46 million people worldwide, and it is estimated that in 2050 more than 100 million will be affected. While there are no effective treatments for these terminal diseases, therapies such as reminiscence, that stimulate memories from the past are recommended. Currently, reminiscence therapy takes place in care homes and is guided by a therapist or a carer. In this work, we present an AI-based solution to automate the reminiscence therapy. This consists of a dialogue system that uses photos of the users as input to generate questions about their life. Overall, this paper presents how reminiscence therapy can be automated by using deep learning, and deployed to smartphones and laptops, making the therapy more accessible to every person affected by dementia., Peer Reviewed, Postprint (published version)

EDITH is a project aiming to orchestrate an ecosystem of manipulation of reliable and safe data, applied to the field of health, proposing the creation of digital twins for personalised healthcare. This paper elaborates on a first approach about using Generative Adversarial Networks (GANs) for the generation of fake data, with the objective of anonymizing users information in the health sector. This is intended to create valuable data that can be used both, in educational and research areas, while avoiding the risk of a sensitive data leakage. Meanwhile GANs are mainly exploited on images and video frames, we are proposing to process raw data in the form of an image, so it can be managed through a GAN, then decoded back to the original data domain. The performance of this prototype has been demonstrated. Moreover, a novel research pathway has been opened so further developments are expected., Peer Reviewed, Postprint (author's final draft)

In recent years, the demand for alternative medical diagnostics of the human kidney or renal is growing, and some of the reasons behind this relate to its non-invasive, early, real-time, and pain-free mechanism. The chronic kidney problem is one of the major kidney problems, which require an early-stage diagnosis. Therefore, in this work, we have proposed and developed an Intelligent Iris-based Chronic Kidney Identification System (ICKIS). The ICKIS takes an image of human iris as input and on the basis of iridology a deep neural network model on a GPU-based supercomputing machine is applied. The deep neural network models are trained while using 2000 subjects that have healthy and chronic kidney problems. While testing the proposed ICKIS on 2000 separate subjects (1000 healthy and 1000 chronic kidney problems), the system achieves iris-based chronic kidney assessment with an accuracy of 96.8%. In the future, we will work to improve our AI algorithm and try data-set cleaning, so that accuracy can be increased by more efficiently learning the features., This work is supported by the Higher Education Commission (HEC) of Pakistan under the Technology Development Fund with project Number TDF03-097 and National Research Program for Universities (NRPU) with project grant no. 8153/Federal/NRPU/R&D/HEC/2017., Peer Reviewed, Postprint (published version)

This master thesis is a continuation of the investigation line opened in with the Generative Adversarial Network based Machine for Fake Data Generation thesis. The objective is using Generative Adversarial Networks (GANs) for the generation of fake data for anonymizing patients information in the health sector. This way, new samples can be generated without putting personal data at risk and, if the quality is good enough, can be used in educational and research areas. A systematic revision of the previous works has been made, and a line of work has been developed in the area of electrocardiograms, using the techniques that have given better results in other papers. Several GAN models have been made, each of them trying different features, and satisfactory results have been obtained in some of them. Moreover, quantitative measuring techniques have been included and tested.

More than 2.7 million people died in the United States in 2016, each leaving behind an estimated 1–5 close friends or relatives who are highly affected by the death. This means there are about 10 million newly bereaved persons each year."( Iglewicz et al., 2020) If this estimation method is carried out worldwide, there will be much more. Although various research has made great progress in the field of grief, especially for complicated grief, researchers have designed an evidence-based structured treatment of complicated grief. However, in an environment where psychology clinicians are far in short supply, the low penetration rate of knowledge in this field, and the limitations of clinicians' abilities have caused the difficulty of managing grief. Here, I explored the possibility of combining AI technology to provide support to people in grief and completed the design of one possible application. It is based on the analysis of clinical empirical research on managing grief, inspired by the collaboration of people from different fields to successfully transform the experience of managing grief into a more accessible way for users.

Aquest treball consisteix en el disseny i desenvolupament d’un prototip per al reconeixement de cèl·lules sanguínies, per a realitzar un diagnòstic temprà, i l’estudi de tots els conceptes teòrics necessaris per a la comprensió total del treball. Aquest procés comença en l’estudi del camp de la intel·ligència artificial dedicat a les xarxes neuronals i el món del machine learning, camp que en els darrers anys ha guanyat importància. Analitzant els diferents tipus de problemes possibles i la manera més adient d’atacar-los, entendre que són les xarxes neuronals i les metodologies que utilitzen. Un cop entesa la base teòrica, s’analitza un model de classificació de cèl·lules ja existent: que fa, com ho fa i els resultats obtinguts, així com el model preentrenat Xception utilitzat en aquest. Familiaritzats amb el model, es desenvolupa una aplicació web de caràcter local, en l’entorn de treball Dash, per a ordinadors o similars, capaç d’interactuar amb el model, presentant així una eina de treball per a personal mèdic per poder aprofitar tot el potencial del model d’una manera ràpida i eficaç. Finalment, l’aplicació s’integra dins d’una placa de desenvolupament prou potent per a operar models de xarxes neuronals amb una mida molt reduïda, esdevenint el prototip de dispositiu mèdic portàtil per a la classificació de cèl·lules.

Medicine is becoming an increasingly data-centred discipline and, beyond classical statistical approaches, artificial intelligence (AI) and, in particular, machine learning (ML) are attracting much interest for the analysis of medical data. It has been argued that AI is experiencing a fast process of commodification. This characterization correctly reflects the current process of industrialization of AI and its reach into society. Therefore, societal issues related to the use of AI and ML should not be ignored any longer and certainly not in the medical domain. These societal issues may take many forms, but they all entail the design of models from a human-centred perspective, incorporating human-relevant requirements and constraints. In this brief paper, we discuss a number of specific issues affecting the use of AI and ML in medicine, such as fairness, privacy and anonymity, explainability and interpretability, but also some broader societal issues, such as ethics and legislation. We reckon that all of these are relevant aspects to consider in order to achieve the objective of fostering acceptance of AI- and ML-based technologies, as well as to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. Our specific goal here is to reflect on how all these topics affect medical applications of AI and ML. This paper includes some of the contents of the “2nd Meeting of Science and Dialysis: Artificial Intelligence,” organized in the Bellvitge University Hospital, Barcelona, Spain., Peer Reviewed, Postprint (author's final draft)

Modern clinical environments are laden with technology devices continuously gathering physiological data from patients. This is especially true in critical care environments, where life-saving decisions may have to be made on the basis of signals from monitoring devices. Hemodynamic monitoring is essential in dialysis, surgery, and in critically ill patients. For the most severe patients, blood pressure is normally assessed through a catheter, which is an invasive procedure that may result in adverse effects. Blood pressure can also be monitored noninvasively through different methods and these data can be used for the continuous assessment of pressure using machine learning methods. Previous studies have found pulse transit time to be related to blood pressure. In this short paper, we propose to study the feasibility of implementing a data-driven model based on restricted Boltzmann machine artificial neural networks, delivering a first proof of concept for the validity and viability of a method for blood pressure prediction based on these models., Peer Reviewed, Postprint (author's final draft)

Treball desenvolupat en el marc del programa "European Project Semester"., The growing population around the world and increase of seniors, as well as a demand for high quality services create new problems and challenges, especially in a healthcare sector. Patient treatment is very often a difficult and time consuming process, however, in today’s society people lack time in every aspect of their lives. Shortage of medical staff is only deepening the problem of long waiting time needed to acquire medical assistance. To fulfil the requirements of patients, governments must invest into finding innovative, efficient and yet affordable solutions that will increase efficiency of healthcare systems. The aim of this paper is to describe how smart solutions can be implemented in order to cope with challenges of the healthcare sector. The research was focused on organisational and technological problems that are present in this sector. Though there are various existing solutions to these problems, which will be presented in this report, the main part of it will be devoted to description of the proprietary system that was developed by the team named Salutem, throughout the course of European Project Semester. The solution is a distributed system consisting of two main components, a Web Application and a Mobile Application that communicate with each other. The Web Application is aimed to provide a management tool for health centre employees, as well as an online reservation system for patients. It copes with a problem of long waiting time in queues to doctor’s office by finding an optimal time of a visit for each patient registered for a given doctor. This is done with use of self-learning Artificial Intelligence (AI) algorithm that is embedded in the system. The Mobile Application is using Near Field Communication(NFC) technology to monitor patients that come for a visit, which includes gathering time data that will be used for the process of AI learning. NFC is also used to instantly provide patient data to doctors once a patient is detected in a do, Outgoing

In this paper, we present a Cognitive Assistive Social Pet Robot design and an early field study with it to facilitate learning with children with Autism Spectrum Disorder. The robotic platform is a low-cost robotic turtle based on a RaspberryPI and Arduino., Postprint (published version)

Summary: Intracavitary high dose rate (HDR) brachytherapy is a form of radiation therapy generally in which a post-surgical tissue margin is treated. The dose gradient of HDR brachytherapy is very steep, and thus small displacements of the applicator, even as small as 1 mm, could potentially cause significant variations of dose which could result in undesired side effects such as overdose of a critical organ. In this retrospective dosimetric study, the variation of dose due to various small range motions of gynecological applicators is investigated. The results show that the implementation of additional immobilization and localization devices along with other safety measures needs to be further investigated., 2015, Includes bibliography., Degree granted: Thesis (M.S.)--Florida Atlantic University, 2015, Collection: FAU Electronic Theses and Dissertations Collection

REMPARK project objective is to develop a personal health system with closed loop detection, response and action capabilities for the assessment and possible management of Parkinson's Disease (PD) patients. The project is developing a wearable monitoring system able to identify in real time the motor status of the PD patients and evaluating ON/OFF/Dyskinesia status with a very high sensitivity and specificity degree (>80%) in operation during ambulatory conditions. Identification of the motor status is based on the knowledge included in a large database obtained with the collaboration of a number of volunteer PD patients, according a specific defined protocol in ambulatory conditions. Artificial Intelligence (AI) methods are applied to the database information for the automatic detection of motor symptoms., Peer Reviewed, Postprint (published version)

Analysis of human movement is an important research area, specially for health applications. In order to assess the quality of life of people with mobility problems like Parkinson’s disease (PD) or stroke patients, it is crucial to monitor their daily life activities. The main goal of this work is to characterize basic activities and their transitions using a single sensor located at the waist. This paper presents a novel postural detection algorithm which is able to detect and identify 6 different postural transitions, sit to stand, stand to sit, bending up/down and lying to sit and sit to lying transitions with a sensitivity of 86.5% and specificity of 95%. The algorithm has been tested on 31 healthy volunteers and 8 PD patients who performed a total of 545 and 176 transitions respectively. The proposed algorithm is suitable to be implemented in real-time systems for on-line monitoring applications., Peer Reviewed, Postprint (published version)

Endocrinologists treating diabetes mellitus find it overwhelming to keep track of the enormous amount of data gathered from the multiple measurements retrieved daily by their patients, throughout the years. This makes it hard for them to find a certain pattern in the data that could help them assign, to each patient, the optimal insulin dosage. This forces them to seek trial and error until they find the individualized insulin doses, required by each patient, to reach their optimal glucose levels. Hence, there is a great read to automate the process of estimating the glucose level. For this, we propose two machine learning techniques and one heuristic. In particular, we present C4.5, Case-Based Reasoning and genetic algorithms. We validate our approach on a data set obtained from the UCMI online machine learning repository. Obtained results are promising. Case-Based Reasoning outperformed both C4.5 and Genetic Algorithms.

The AIDS epidemic, caused by Human Immunodeficiency Virus (HIV), is a global crisis which threatens development gains, economies, and societies. The eradication of HIV/AIDS represents one of humanity’s greatest challenges, which requires co-operation, and comprehensive collaboration between science, governments, social institutions, the media, the professions, and the general public. In this endeavour strategic information plays a major role. The Free State Department of Health introduced Antiretroviral Therapy (ART) to meet the needs of the rising number of people living with HIV and also dying due to AIDS related diseases. A patient information system was deployed by the Province to supplement the ART programme rollout process by gathering data and providing all the basic patient antiretroviral information. The patient information system was a traditional online clinical system and concentrated on the bread-and-butter issues of accumulating data on a patient. Very little functionality was provided to deal with the complexities of managing the clinical outcomes of the ART programme. To add to the problem, other online operational systems had to be interrogated to gain an understanding of the impact the rollout of ARV had. These operational systems ranged from standalone Human Resource systems to information systems accumulating data on tuberculosis which is closely related to HIV/AIDS. No mechanism or platform existed to provide management with integrated strategic information to manage the business process intelligently. This study focussed on the challenges and solutions to overcome this shortfall. The main objective of this study was to construct a framework for providing strategic information for the management of the ART programme in the Free State Department of Health. This objective was reached with a two phase action research methodology. The author of this study fulfilled simultaneously the roles of the researcher and the practitioner. During phase one a c

Postprint (author's final draft)

Summary: A detailed dosimetric comparison between Inverse Planning by Simulated Annealing (IPSA) and Dose Points (DP) optimized treatment plans has been performed for High Dose Rate (HDR) brachytherapy of skin lesions using Freiburg Flap applicator in order to find out whether or not IPSA offers better clinical dosimetric outcomes for lesions categorized into four different curvatures. Without compromising target coverage, IPSA reduced the volume of Planning Target Volume (lesion) that received at least 125% of the prescription dose on average by 41%. It also reduced the volume of the healthy skin surrounding the lesion that receives at least 100% of the prescription dose on average by 42%. IPSA did not show any advantage over DP in sparing normal structures underlying the lesions treated. Although DP optimization algorithm has been regularly used at Lynn Cancer Institute for HDR brachytherapy of skin lesions, recent upgrades in IPSA software have made IPSA more amenable to rapid treatment planning and therefore IPSA can be used either in place of DP or as its alternative., 2014, Includes bibliography., Thesis (M.S.)--Florida Atlantic University, 2014.