Introduction: External support behaviours, which include leaning (supporting with the non-task hand) or bracing (supporting with the body), are frequently employed by workers in manufacturing settings. However, current ergonomic assessment tools are limited by our limited understanding of these behaviours. Recent studies have investigated these behaviours, however, the designs of these studies are limited in their applicability to real-world scenarios. The purpose of this study was to assess how different task parameters affect the prediction of external support behaviours, as well as the effect of support on task hand, and body, kinematics and kinetics, in a minimally constrained experimental design. Methods: Female participants (n = 18) performed a series of one-handed maximal exertions (in the six orthogonal directions), and one precision task, in four hand Locations. Trials either featured support (as chosen by the participant), or no support. Results & Discussion: Three logistic regression models were developed, with inputs from individual and task characteristics, and they correctly predicted the occurrence of leaning, bracing, or simultaneous leaning and bracing, 74-86% of the time. Leaning and/or bracing were found to provide: 1) oppositional forces to increase task hand force generation, 2) balance, by countering destabilizing moments about the feet, and 3) a reduction in moment arm of the task hand force, with respect to the upper body joints, by bringing the shoulder closer to the task hand. Participants were able to exert 64.8% more force at the task hand as a result of support. Leaning hand placement depended on the task force direction and location. However, the positioning of the leaning hand varied very little. Finally, the precision condition showed that fine motor demands may also affect external support choice. / Thesis / Master of Science in Kinesiology

Purpose Robotic-assisted minimally invasive esophagectomy (RAMIE) has become one standard approach for the operative treatment of esophageal tumors at specialized centers. Here, we report the results of a prospective multicenter registry for standardized RAMIE. Methods The German da Vinci Xi registry trial included all consecutive patients who underwent RAMIE at five tertiary university centers between Oct 17, 2017, and Jun 5, 2020. RAMIE was performed according to a standard technique using an intrathoracic circular stapled esophagogastrostomy. Results A total of 220 patients were included. The median age was 64 years. Total minimally invasive RAMIE was accomplished in 85.9%; hybrid resection with robotic-assisted thoracic approach was accomplished in an additional 11.4%. A circular stapler size of ≥28 mm was used in 84%, and the median blood loss and operative time were 200 (IQR: 80–400) ml and 425 (IQR: 335–527) min, respectively. The rate of anastomotic leakage was 13.2% (n=29), whereas the two centers with >70 cases each had rates of 7.0% and 12.0%. Pneumonia occurred in 19.5% of patients, and the 90-day mortality was 3.6%. Cumulative sum analysis of the operative time indicated the end of the learning curve after 22 cases. Conclusions High-quality multicenter registry data confirm that RAMIE is a safe procedure and can be reproduced with acceptable leak rates in a multicenter setting. The learning curve is comparably low for experienced robotic surgeons.

The treatment of owner-occupied housing (OOH) is probably the most important unresolved issue in inflation measurement. How -- and whether -- it is included in the Consumer Price Index (CPI) affects inflation expectations, the measured level of real interest rates, and the behavior of governments, central banks and market participants. We show that none of the existing treatments of OOH are fit for purpose. Hence we propose a new simplified user cost method with better properties. Using a micro-level dataset, we then compare the empirical behavior of eight different treatments of OOH. Our preferred user cost approach pushes up the CPI during housing booms (by 2 percentage points or more). Our findings relate to the following important debates in macroeconomics: the behavior of the Phillips curve in the US during the global financial crisis, and the response of monetary policy to housing booms, secular stagnation, and globalization. / Series: Department of Economics Working Paper Series

Made available in DSpace on 2016-06-02T19:44:02Z (GMT). No. of bitstreams: 1 TeseMGMT.pdf: 865770 bytes, checksum: 64a8e6f13853515e8e6f52c8db887e35 (MD5) Previous issue date: 2007-09-20 / People with mental retardation usually present motor development delays. Nevertheless, these delays seem to be more often related to cognitive factors such as attention and comprehension than to motor or mental deficits. Strategies have been developed to teach motor skills to this population. One of the existing strategies is mental training, which is based on imagining the movement to be executed without the presence of the physical movement. The general objective of this doctoral dissertation was to apply a procedure based on physical and mental training to the teaching of rolling forward, a basic skill for artistic gymnastics practitioners, and to verify its effects in mentally retarded students. In experiment 1 there were two subjects (P1 and P2) aged 15 and 20 respectively, enrolled in a school for the mentally retarded. A single-subject experimental design with alternating treatments was applied. The rolling forward skill was divided in four phases. The results showed that P1 learned all the phases of forward rolling, whereas P2 learned partially phases I and II of the skill taught. We believe that the difficulty found by this participant was due to his motor difficulties, once he also presented an associated physical handicap. The purpose of experiment 2 was to apply the mental training procedure and verifying their effects in the forward rolling learning process in three students aged 12, 12 and 16, respectively, all of them with mental retardation. The experimental design applied was of the single subject in a multiple baseline design. The participants of this study learned all phases of forward rolling, and even though they presented different performance levels, all of them benefited from the strategy used. We realized that the mental training elicited other behaviors from the participants like: following rules, self-conversation, attention, concentration and relaxation. To understand the aspects that affect the use of mental training and to establish experimental designs to investigate this strategy were some of the contributions of this work. / Pessoas com deficiência mental apresentam atrasos no desenvolvimento motor. No entanto, esses atrasos parecem estar mais relacionados a fatores cognitivos de atenção e compreensão de instruções do que a déficits motores ou mentais. Estratégias têm sido utilizadas com o objetivo de auxiliar o ensino de habilidades motoras para essa população. Uma das estratégias existentes é o treino mental, ou seja, imaginar o movimento a ser executado sem a presença do movimento físico. Partindo da abordagem comportamental, utilizando diferentes delineamentos experimentais, o objetivo geral deste trabalho foi de aplicar os procedimentos de treino físico e treino mental e verificar seus efeitos na aprendizagem em alunos com deficiência mental. O experimento 1 teve como objetivo aplicar os procedimentos de treino físico e mental e verificar os seus efeitos na aprendizagem do rolamento para frente, elemento da Ginástica Artística, em alunos com deficiência mental. Participaram desse estudo dois jovens (P1 e P2), com idade de 15 e 20 anos respectivamente, estudantes de uma escola especializada. O delineamento experimental utilizado foi o de sujeito único, com tratamentos alternados. Para fins de análise, a habilidade de rolamento para a frente foi dividida em quatro fases. Os resultados encontrados mostraram que P1 aprendeu todas as fases e P2 aprendeu parcialmente as fases I e II da habilidade ensinada. Acreditamos que a dificuldade encontrada por esse participante foi decorrente de sua dificuldade motora, pois ele possuía também uma deficiência física associada. O experimento 2 teve como objetivo aplicar o procedimento de treino mental e verificar os seus efeitos na aprendizagem do rolamento para a frente, em três alunos, com idades de 12, 12 e 16 anos respectivamente, com deficiência mental. O delineamento experimental utilizado foi o de sujeito único de linha de base múltipla. Os participantes desse estudo aprenderam todas as fases do rolamento para frente e, apesar de apresentarem níveis de desempenho diferentes, os três se beneficiaram da estratégia utilizada. Percebemos que o treino mental evocou também outros comportamentos dos participantes como: seguir regras, autoconversação, atenção, concentração e relaxamento. Desenvolver um programa de ensino de habilidades motoras a jovens com deficiência mental e investigar, através de delineamentos experimentais específicos, o papel do treino mental no desenvolvimento dessas habilidades foram algumas das contribuições desse trabalho.

Studiens syfte är att påvisa hur barn tillämpar enkel teknik i förskolan genom de fem enkla maskinerna. Observationer och”Intervju i farten” är de metodval som besvarar studiens syfte och frågeställningar. Observationer och intervjuer har genomförts i förskolans utemiljö under en förmiddag och utgår från barnens fria lek där målet är att utgå ifrån barnens perspektiv och reflektioner. Situationerna som blivit valda till studien baseras av barnens nyfikenhet och påvisade intressen. Resultatet i studien visar att två av de fem enkla maskinerna tillämpas av barnen i förskolans utemiljö och fria lek. Detta synliggörs genom deras användning av lutande planet och hjulet ur de fem enkla maskinerna. Det sker genom användning av redskap, som utforskande, del av leken och genom begrepp. Detta sker genom ett sociokulturellt perspektiv där olika faktorer påverkar barnens lärande. / The purpose of the study is to demonstrate how children apply simple technology in preschool through “The Big Five”. Observations and "Interview on the move" are the method choices that answer the purpose and questions of the study. Observations and interviews have been conducted in the preschool outdoor environment during a morning and are based on the children's free play where the aim is to start from the children's perspective and reflections. The situations that have been chosen for the study are based on the children's curiosity and demonstrated interests. The result of the study shows that two of “The Big Five” are applied by the children in the preschool outdoor environment and free play. This is demonstrated by their use of the leaning plane and the wheel from “The Big Five”. It shows by their use of tools such as exploration, part of the game and through concepts. This is done through a sociocultural perspective where different factors influence children's learning.

Nous visons à mieux comprendre, à travers la notion composite de rapport(s) au(x) savoir(s), la façon dont le sujet apprenant haïtien se construit dans l'espace scolaire comme membre de la société et s'y intègre. L’approche se base sur des données construites sur des singularités d’« histoires » scolaires et des statistiques issues d’études sociologiques. Elles sont analysées et interprétées dans un cadre théorique inspiré de travaux développés par l’équipe ESCOL (Charlot, Bautier, Rochex) ou par Beillerot dans une perspective clinique, ou culturelle comme Hayder. Les situations sociopolitiques et économiques rendent complexes les rapports à l’école et à ses objets : ainsi dans la société haïtienne, les enseignants éprouvent des difficultés à susciter l’intérêt pour les savoirs scolaires et les apprenants expriment des sentiments d’abandon à leur sort. La réussite à l’école ne leur suffit pas pour se projeter dans un avenir plus assuré qu’il ne l’est actuellement. Malgré tout, des familles se sacrifient pour que leurs enfants continuent à fréquenter l’école. Ici s’origine une idée de mieux comprendre ce que signifie, pour un jeune haïtien le fait d’aller à l'école, d'y travailler ou non, d'y apprendre et comprendre les savoirs proposés. Notre question centrale : de quel ordre sont les facteurs qui influencent la(es) rapport(s) au(x) savoir(s) des sujets apprenant dans l’espace scolaire haïtien ? Notre hypothèse principale : La mobilisation du sujet apprenant pour investir la(es) savoir(s) dépend de ses rapports à lui-même, à l'institution (à travers les interactions avec les enseignant(e)s et personnels de direction) et de ce que ces savoirs mobilisent en lui.Ces questions sont abordées à partir de l’organisation de l’enseignement dans différentes institutions scolaires prenant en compte entre autres : qualité d’enseignement, rapports à la culture scolaire, question du sens de l’école et des savoirs, etc.. Nous tentons de formuler un problème éducatif en Haïti à partir d’une lecture «en positif » des situations des sujets apprenant. Un des constats : les savoirs étant présentés en vrac, ceux qui n’ont pas une stratégie de « survie » se perdent dans l’indifférence de la société. / We predict to better understanding the Haitian learning experience through the notions of its relationships with knowledge and how these relationships are built within the school system environment as a member of society leading up to the integration. This approach is based on individual students’ stories and statistical facts issued from sociological studies. On one hand, these stories and facts are been analyzed and interpreted within theoretical and academic frameworks developed by ESCOL (Charlot, Bautier, Rochex). On the other hand, they have been analyzed by Beillerot from a clinical perspective, and analyzed by Haydwe from a cultural standpoint. The socio-politic and economic situations have contributed to the complexity of the relationships between the learners and school environments. Consequently, teachers have endured difficulties to motivate students to learn meanwhile students have expressed desire to drop out from school given that academic success has not been sufficient to ensure a sustainable future to them. Nevertheless, Haitian parents, in spite of limited resources continue to invest in the education of their children. Herein, begin the idea of understanding what it means for young Haitians to attend school, to work or not, to learn and understand what they are being taught in school.Our central question: What are the influential factors within the relationships between the learners and Haitian school system? Our hypothesis: The motivation of a student to learn depends on intrinsic motivation; and the interaction between him or her and the school institutions trough interaction with teachers and administrative personnel.These issues are raised from the organization of the educative system through several institutions in assessment of the quality of instruction, relation with the school culture, questions on the importance of education, etc. We try to formulate the problem of the Haitian school system from a “positive model” of the learners’ circumstance. One of the findings, since knowledge is presented in bulk, those who do not have a "survival" strategy, are lost in the society frightening indifference.

【第一篇論文中文摘要】 本文使用路透社央行干預匯市的新聞報導，探討哪些因素可以提高亞洲央行成功干預匯市的機率，研究期間為2005年1月至2011年4月。此研究期間涵蓋全球金融風暴和美國採行量化寬鬆政策，因此，亞洲貨幣在逐步對美元升值後發生大幅度的貶值。研究結果顯示印尼、馬來西亞、菲律賓、新加坡、台灣及泰國的央行採取逆風而行的策略是有效的干預方式，而且多個國家在同日干預匯市及第一日的干預會有較高成功的機率。 【第二篇論文中文摘要】 本文透過不同的研究方法針對亞洲國家央行干預匯率市場的有效性再次驗證，研究期間為2005年1月至2011年4月，實證結果顯示亞洲國家在次貸風暴期間面臨美元升值的壓力，央行會採取賣美元的方式來干預匯市，但是這種干預匯市的方式卻僅能減緩美元升值的趨勢，其中以印尼盾、新加坡元、新台幣紛紛對美元貶值較為明顯，而在次貸風暴發生之後，美國實施量化寬鬆政策造成亞洲國家卻面臨美元貶值的壓力，各國央行改採買美元的方式來干預匯市，但是此種干預匯市的方式也只造成美元緩慢貶值的趨勢，其中印尼盾、馬來西亞令吉、新加坡元、韓圜、泰銖分別對美元升值的趨勢較為明顯，此現象反應亞洲央行干預匯市是採取逆風而行的策略，雖然能降低匯率的波動，但無法改變匯率的升貶值趨勢。 【第三篇論文中文摘要】 本研究是在探討印度、印尼、南韓、馬來西亞、新加坡、泰國及台灣央行透過干預匯率市場，對其國家的公司在美國發行存託憑證折溢價的影響，研究期間為2005年1月至2011年4月。研究結果顯示央行對匯市干預造成的變動，確實會影響到該國公司在美國發行的存託憑證產生折價的情形。另外，亞洲央行使用買美元干預匯市的作法會對該國公司在美國發行的存託憑證產生溢價，而央行透過賣美元干預匯市的作法會對該國公司在美國發行的存託憑證產生折價的影響，但是由於樣本資料的限制，其效果在統計上並不顯著。由公司層面的分析可以看出央行透過賣美元來干預匯市對其國家的公司在美國發行的存託憑證會有明顯產生折價的影響。 / 【第一篇論文英文摘要】 Using Reuters’ news reports on central bank interventions, we investigate the factors that increase the odds of intervention success by Asian central banks in the foreign exchange market from January 2005 to April 2011. This period coincides with the global credit crisis and quantitative easing policy, which have engendered a sharp depreciation followed by a gradual appreciation of Asian currencies. The results show that leaning-against-the-wind intervention strategies are effective in Indonesia, Malaysia, Philippines, Singapore, Taiwan, and Thailand. We also find that joint and first day interventions are associated with higher odds of effective intervention. 【第二篇論文英文摘要】 This paper examines the effectiveness of central bank interventions in the foreign exchange market from January 2005 to April 2011 in Asia. The results show that the central banks in Asia intervene in the foreign exchange markets by selling U.S. dollars to prevent severe depreciation of local currencies during the global credit crisis. However, central bankers can only slow down the trend of depreciation of local currencies against U.S. dollar. The currencies apparently depreciate against U.S. dollar in Indonesia, Singapore, and Taiwan. After the global credit crisis, Asian countries confront appreciations of local currencies due to the US quantitative easing policy. The central banks in Asia intervene by purchasing U.S. dollars in the foreign exchange market. Nevertheless, intervention strategies slowly reduce U.S. dollar depreciations. The foreign exchange rate apparently appreciate against U.S. dollar in India, Malaysia, Singapore, South Korea, and Thailand. Results show that Asian central banks adopt leaning-against-the-wind intervention strategies during the sample period. Their interventions in the foreign exchange market can only reduce fluctuations in the foreign exchange rate, but fail to reverse the trend of Asian exchange rates. 【第三篇論文英文摘要】 This paper examines whether Asian central bank interventions in the foreign exchange market affect the discount or premium of American Depositary Receipt (ADR) of Asian companies from January 2005 to April 2011. The sample consists of companies from Indian, Indonesia, South Korea, Malaysia, Singapore. Empirical results show that central bank interventions increase ADR discounts of companies in Asian countries. In addition, interventions by purchasing U.S. dollars result in higher ADR premiums, and the strategies of selling U.S. dollars affect ADR discounts. Though some of the empirical results are not statistically significant due to limited sample size, results based on individual firms show that selling USD interventions by Asian central banks have a significant impact on their ADR discounts.

STAT1是一個轉錄因子，在細胞生理功能中是非常重要的訊息傳遞者，在免疫系統具有抗病毒的角色，但是目前為止對於STAT1在中樞神經系統所扮演的角色仍不清楚。爲證實STAT1的表現與空間記憶的形成有關聯，我們將大白鼠分成兩組，一組為有訓練的組別，另一組則為無訓練的組別分別進行水迷津試驗，試驗完畢後取出大鼠的海馬迴CA1區域組織進行即時定量聚合酶連鎖反應與西方墨點法分析。結果顯示，經過水迷津訓練的刺激下，STAT1 mRNA與蛋白質分別減少約34 %及40 %，而STAT2 mRNA及蛋白質的表現則不受空間學習的影響。爲了進ㄧ步探討STAT1在空間學習記憶過程中所扮演的角色，實驗利用STAT1 siRNA轉染至海馬迴CA1區域抑制STAT1的表現，發現降低STAT1表現會促進大白鼠在水迷津試驗的學習能力，實驗同時也轉染STAT2 siRNA至CA1區域，結果顯示STAT2不參與大白鼠空間記憶的形成。本實驗室先前發現降低laminin β1表現量會促進大白鼠的空間學習記憶 (unpublished observation, 附錄二)，此外laminin β1基因啟動子上具有STAT1結合序列：interferon-γ activated site (GAS)。因此，實驗利用PC12細胞進行laminin β1報導基因分析，結果顯示STAT1會促進 laminin β1啟動子的轉錄活性。而爲了進一步探討在STAT1影響空間學習與記憶歷程中與laminin β1的關聯性，實驗利用STAT1 siRNA抑制大白鼠海馬迴CA1區STAT1的表現並促進空間學習與記憶的同時，發現laminin β1 mRNA及蛋白質表現量都受到STAT siRNA的抑制，而轉染野生型STAT1-Flag質體則會增加laminin β1 mRNA及蛋白質的表現量，顯示STAT1正向調控laminin β1的表現。本篇論文提出海馬迴CA1區域的STAT1參與動物空間學習與記憶的形成，其中可能與STAT1正向調控laminin β1的表現有關。 / STAT1 is a signal transducer and transcription factor in the cell. Several reports have indicated that STAT1 plays a critical role in immune response against virus infection in animals. However, the role of STAT1 in the central nervous system is still unclear. In the present study, we aimed to examine the role of STAT1 involved in spatial memory formation in rat and the possible downstream gene that STAT1 regulates. Rats were randomly divided into the trained group and the non-trained group. Animals were subjected to water maze learning according to the previous behavioral paradigm. Their hippocampus CA1 tissues were dissected out for STAT1 mRNA level and protein level determination. Results indicated that spatial training markedly decreased STAT1 mRNA level and protein level in the CA1 area, but this change was not found for STAT2 mRNA and protein expression. To further confirm the role of STAT1 involved in spatial learning and memory, animals were transfected with STAT1 siRNA in the CA1 area. Results showed that STAT1 siRNA transfection significantly facilitated water maze performance, whereas their water maze performance under STAT2 siRNA transfection was not altered. Previous studies from our laboratory have demonstrated that laminin β1 impairs spatial memory formation in rat (unpublished observation). In addition, promoter analysis indicates that the laminin β1 promoter region contains two GAS elements, which is the STAT1/STAT1 and STAT1/STAT3 binding site. Results from luciferase reporter assay revealed that transfection of STAT1 siRNA decreased laminin β1 promoter activity, whereas transfection of STAT1 wild-type plasmid increased laminin β1 promoter activity. To further study the relationship between STAT1 and laminin β1 in spatial memory formation, we used STAT1 siRNA to knockdown STAT1 expression and these animals were subjected to spatial training. We then determined their laminin β1 expression. Results showed that the laminin β1 mRNA level and protein level were both significantly decreased by STAT1 siRNA transfection. Besides, STAT1 wild-type plasmid transfection increased laminin β1 mRNA level and protein level in the CA1 area associated with spatial memory impairment. These results together suggest that STAT1 negatively regulates spatial memory formation. Further, STAT1 may impair spatial memory formation through increased laminin β1 expression.

This thesis is aimed at the Military Museum in Kraliky. This construction made on the basis of the initial design of the designer. For this reason, it was necessary to deal with during the processing work some technical problems, transport of materials to the construction site or purely site layout itself. The whole area of the museum consists of several buildings. The largest and main building of the exposition hall with steel supporting structures, then there is the Administration building, which in turn is a brick workshop that has as Exp hall steel structure. There is also a replica of the First Republic Military cottage, which has a wooden frame and demonstration area, where there will be live demonstrations of military equipment.

[ES] Los Cuidados Paliativos (PC) son cuidados médicos especializados cuyo objetivo esmejorar la calidad de vida de los pacientes con enfermedades graves. Históricamente,se han aplicado a los pacientes en fase terminal, especialmente a los que tienen undiagnóstico oncológico. Sin embargo, los resultados de las investigaciones actualessugieren que la PC afecta positivamente a la calidad de vida de los pacientes condiferentes enfermedades. La tendencia actual sobre la PC es incluir a pacientes nooncológicos con afecciones como la EPOC, la insuficiencia de funciones orgánicas ola demencia. Sin embargo, la identificación de los pacientes con esas necesidades escompleja, por lo que se requieren herramientas alternativas basadas en datos clínicos. La creciente demanda de PC puede beneficiarse de una herramienta de cribadopara identificar a los pacientes con necesidades de PC durante el ingreso hospitalario.Se han propuesto varias herramientas, como la Pregunta Sorpresa (SQ) o la creaciónde diferentes índices y puntuaciones, con distintos grados de éxito. Recientemente,el uso de algoritmos de inteligencia artificial, en concreto de Machine Learning (ML), ha surgido como una solución potencial dada su capacidad de aprendizaje a partirde las Historias Clínicas Electrónicas (EHR) y con la expectativa de proporcionarpredicciones precisas para el ingreso en programas de PC. Esta tesis se centra en la creación de herramientas digitales basadas en ML para la identificación de pacientes con necesidades de cuidados paliativos en el momento del ingreso hospitalario. Hemos utilizado la mortalidad y la fragilidad como los dos criterios clínicos para la toma de decisiones, siendo la corta supervivencia y el aumento de la fragilidad, nuestros objetivos para hacer predicciones. También nos hemos centrado en la implementación de estas herramientas en entornos clínicos y en el estudio de su usabilidad y aceptación en los flujos de trabajo clínicos. Para lograr estos objetivos, en primer lugar, estudiamos y comparamos algoritmos de ML para la supervivencia a un año en pacientes adultos durante el ingreso hospitalario. Para ello, definimos una variable binaria a predecir, equivalente a la SQ y definimos el conjunto de variables predictivas basadas en la literatura. Comparamos modelos basados en Support Vector Machine (SVM), k-Nearest Neighbours (kNN), Random Forest (RF), Gradient Boosting Machine (GBM) y Multilayer Perceptron (MLP), atendiendo a su rendimiento, especialmente al Área bajo la curva ROC (AUC ROC). Además, obtuvimos información sobre la importancia de las variables para los modelos basados en árboles utilizando el criterio GINI. En segundo lugar, estudiamos la medición de la fragilidad de la calidad de vida(QoL) en los candidatos a la intervención en PC. Para este segundo estudio, redujimosla franja de edad de la población a pacientes ancianos (≥ 65 años) como grupo objetivo. A continuación, creamos tres modelos diferentes: 1) la adaptación del modelo demortalidad a un año para pacientes ancianos, 2) un modelo de regresión para estimarel número de días desde el ingreso hasta la muerte para complementar los resultadosdel primer modelo, y finalmente, 3) un modelo predictivo del estado de fragilidad aun año. Estos modelos se compartieron con la comunidad académica a través de unaaplicación web b que permite la entrada de datos y muestra la predicción de los tresmodelos y unos gráficos con la importancia de las variables. En tercer lugar, propusimos una versión del modelo de mortalidad a un año enforma de calculadora online. Esta versión se diseñó para maximizar el acceso de losprofesionales minimizando los requisitos de datos y haciendo que el software respondiera a las plataformas tecnológicas actuales. Así pues, se eliminaron las variablesadministrativas específicas de la fuente de datos y se trabajó en un proceso para minimizar las variables de entrada requeridas, manteniendo al mismo tiempo un ROCAUC elevado del modelo. Como resultado, e / [CA] Les Cures Pal·liatives (PC) són cures mèdiques especialitzades l'objectiu de les qualsés millorar la qualitat de vida dels pacients amb malalties greus. Històricament, s'hanaplicat als pacients en fase terminal, especialment als quals tenen un diagnòstic oncològic. No obstant això, els resultats de les investigacions actuals suggereixen que lesPC afecten positivament a la qualitat de vida dels pacients amb diferents malalties. Latendència actual sobre les PC és incloure a pacients no oncològics amb afeccions comla malaltia pulmonar obstructiva crònica, la insuficiència de funcions orgàniques o lademència. No obstant això, la identificació dels pacients amb aqueixes necessitats éscomplexa, per la qual cosa es requereixen eines alternatives basades en dades clíniques. La creixent demanda de PC pot beneficiar-se d'una eina de garbellat per a identificar als pacients amb necessitats de PC durant l'ingrés hospitalari. S'han proposatdiverses eines, com la Pregunta Sorpresa (SQ) o la creació de diferents índexs i puntuacions, amb diferents graus d'èxit. Recentment, l'ús d'algorismes d'intel·ligènciaartificial, en concret de Machine Learning (ML), ha sorgit com una potencial soluciódonada la seua capacitat d'aprenentatge a partir de les Històries Clíniques Electròniques (EHR) i amb l'expectativa de proporcionar prediccions precises per a l'ingrés enprogrames de PC. Aquesta tesi se centra en la creació d'eines digitals basades en MLper a la identificació de pacients amb necessitats de cures pal·liatives durant l'ingréshospitalari. Hem utilitzat mortalitat i fragilitat com els dos criteris clínics per a lapresa de decisions, sent la curta supervivència i la major fragilitat els nostres objectiusa predir. Després, ens hem centrat en la seua implementació en entorns clínics i hemestudiat la seua usabilitat i acceptació en els fluxos de treball clínics.Aquesta tesi se centra en la creació d'eines digitals basades en ML per a la identificació de pacients amb necessitats de cures pal·liatives en el moment de l'ingrés hospitalari. Hem utilitzat la mortalitat i la fragilitat com els dos criteris clínics per ala presa de decisions, sent la curta supervivència i l'augment de la fragilitat, els nostresobjectius per a fer prediccions. També ens hem centrat en la implementació d'aquesteseines en entorns clínics i en l'estudi de la seua usabilitat i acceptació en els fluxos detreball clínics. Per a aconseguir aquests objectius, en primer lloc, estudiem i comparem algorismesde ML per a la supervivència a un any en pacients adults durant l'ingrés hospitalari.Per a això, definim una variable binària a predir, equivalent a la SQ i definim el conjuntde variables predictives basades en la literatura. Comparem models basats en Support Vector Machine (SVM), k-Nearest Neighbours (kNN), Random Forest (RF), Gradient Boosting Machine (GBM) i Multilayer Perceptron (MLP), atenent el seu rendiment,especialment a l'Àrea sota la corba ROC (AUC ROC). A més, vam obtindre informaciósobre la importància de les variables per als models basats en arbres utilitzant el criteri GINI. En segon lloc, estudiem el mesurament de la fragilitat de la qualitat de vida (QoL)en els candidats a la intervenció en PC. Per a aquest segon estudi, vam reduir lafranja d'edat de la població a pacients ancians (≥ 65 anys) com a grup objectiu. Acontinuació, creem tres models diferents: 1) l'adaptació del model de mortalitat a unany per a pacients ancians, 2) un model de regressió per a estimar el nombre de dies desde l'ingrés fins a la mort per a complementar els resultats del primer model, i finalment,3) un model predictiu de l'estat de fragilitat a un any. Aquests models es van compartiramb la comunitat acadèmica a través d'una aplicació web c que permet l'entrada dedades i mostra la predicció dels tres models i uns gràfics amb la importància de lesvariables. En tercer lloc, vam proposar una versió del model de mortalitat a un any en formade calculadora en línia. Aquesta versió es va di / [EN] Palliative Care (PC) is specialized medical care that aims to improve patients' quality of life with serious illnesses. Historically, it has been applied to terminally ill patients, especially those with oncologic diagnoses. However, current research results suggest that PC positively affects the quality of life of patients with different conditions. The current trend on PC is to include non-oncological patients with conditions such as Chronic Obstructive Pulmonary Disease (COPD), organ function failure or dementia. However, the identification of patients with those needs is complex, and therefore alternative tools based on clinical data are required. The growing demand for PC may benefit from a screening tool to identify patients with PC needs during hospital admission. Several tools, such as the Surprise Question (SQ) or the creation of different indexes and scores, have been proposed with varying degrees of success. Recently, the use of artificial intelligence algorithms, specifically Machine Learning (ML), has arisen as a potential solution given their capacity to learn from the Electronic Health Records (EHRs) and with the expectation to provide accurate predictions for admission to PC programs. This thesis focuses on creating ML-based digital tools for identifying patients with palliative care needs at hospital admission. We have used mortality and frailty as the two clinical criteria for decision-making, being short survival and increased frailty, as our targets to make predictions. We also have focused on implementing these tools in clinical settings and studying their usability and acceptance in clinical workflows. To accomplish these objectives, first, we studied and compared ML algorithms for one-year survival in adult patients during hospital admission. To do so, we defined a binary variable to predict, equivalent to the SQ and defined the set of predictive variables based on literature. We compared models based on Support Vector Machine (SVM), k-Nearest Neighbours (kNN), Random Forest (RF), Gradient Boosting Machine (GBM) and Multilayer Perceptron (MLP), attending to their performance, especially to the Area under the ROC curve (AUC ROC). Additionally, we obtained information on the importance of variables for tree-based models using the GINI criterion. Second, we studied frailty measurement of Quality of Life (QoL) in candidates for PC intervention. For this second study, we narrowed the age of the population to elderly patients (≥ 65 years) as the target group. Then we created three different models: 1) for the adaptation of the one-year mortality model for elderly patients, 2) a regression model to estimate the number of days from admission to death to complement the results of the first model, and finally, 3) a predictive model for frailty status at one year. These models were shared with the academic community through a web application a that allows data input and shows the prediction from the three models and some graphs with the importance of the variables. Third, we proposed a version of the 1-year mortality model in the form of an online calculator. This version was designed to maximize access from professionals by minimizing data requirements and making the software responsive to the current technological platforms. So we eliminated the administrative variables specific to the dataset source and worked on a process to minimize the required input variables while maintaining high the model's AUC ROC. As a result, this model retained most of the predictive power and required only seven bed-side inputs. Finally, we evaluated the Clinical Decision Support System (CDSS) web tool on PC with an actual set of users. This evaluation comprised three domains: evaluation of participant's predictions against the ML baseline, the usability of the graphical interface, and user experience measurement. A first evaluation was performed, followed by a period of implementation of improvements and corrections to the pla / Blanes Selva, V. (2022). Clinical Decision Support Systems for Palliative Care Referral: Design and Evaluation of Frailty and Mortality Predictive Models [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/190993