RESUMO

Topic-based search systems retrieve items by contextualizing the information seeking process on a topic of interest to the user. A key issue in topic-based search of text resources is how to automatically generate multiple queries that reflect the topic of interest in such a way that precision, recall, and diversity are achieved. The problem of generating topic-based queries can be effectively addressed by Multi-Objective Evolutionary Algorithms, which have shown promising results. However, two common problems with such an approach are loss of diversity and low global recall when combining results from multiple queries. This work proposes a family of Multi-Objective Genetic Programming strategies based on objective functions that attempt to maximize precision and recall while minimizing the similarity among the retrieved results. To this end, we define three novel objective functions based on result set similarity and on the information theoretic notion of entropy. Extensive experiments allow us to conclude that while the proposed strategies significantly improve precision after a few generations, only some of them are able to maintain or improve global recall. A comparative analysis against previous strategies based on Multi-Objective Evolutionary Algorithms, indicates that the proposed approach is superior in terms of precision and global recall. Furthermore, when compared to query-term-selection methods based on existing state-of-the-art term-weighting schemes, the presented Multi-Objective Genetic Programming strategies demonstrate significantly higher levels of precision, recall, and F1-score, while maintaining competitive global recall. Finally, we identify the strengths and limitations of the strategies and conclude that the choice of objectives to be maximized or minimized should be guided by the application at hand.

RESUMO

Medical imaging is essential nowadays throughout medical education, research, and care. Accordingly, international efforts have been made to set large-scale image repositories for these purposes. Yet, to date, browsing of large-scale medical image repositories has been troublesome, time-consuming, and generally limited by text search engines. A paradigm shift, by means of a query-by-example search engine, would alleviate these constraints and beneficially impact several practical demands throughout the medical field. The current project aims to address this gap in medical imaging consumption by developing a content-based image retrieval (CBIR) system, which combines two image processing architectures based on deep learning. Furthermore, a first-of-its-kind intelligent visual browser was designed that interactively displays a set of imaging examinations with similar visual content on a similarity map, making it possible to search for and efficiently navigate through a large-scale medical imaging repository, even if it has been set with incomplete and curated metadata. Users may, likewise, provide text keywords, in which case the system performs a content- and metadata-based search. The system was fashioned with an anonymizer service and designed to be fully interoperable according to international standards, to stimulate its integration within electronic healthcare systems and its adoption for medical education, research and care. Professionals of the healthcare sector, by means of a self-administered questionnaire, underscored that this CBIR system and intelligent interactive visual browser would be highly useful for these purposes. Further studies are warranted to complete a comprehensive assessment of the performance of the system through case description and protocolized evaluations by medical imaging specialists.

RESUMO

The applicability of the path planning strategy to robotic manipulators has been an exciting topic for researchers in the last few decades due to the large demand in the industrial sector and its enormous potential development for space, surgical, and pharmaceutical applications. The automation of high-degree-of-freedom (DOF) manipulator robots is a challenging task due to the high redundancy in the end-effector position. Additionally, in the presence of obstacles in the workspace, the task becomes even more complicated. Therefore, for decades, the most common method of integrating a manipulator in an industrial automated process has been the demonstration technique through human operator intervention. Although it is a simple strategy, some drawbacks must be considered: first, the path's success, length, and execution time depend on operator experience; second, for a structured environment with few objects, the planning task is easy. However, for most typical industrial applications, the environments contain many obstacles, which poses challenges for planning a collision-free trajectory. In this paper, a multiple-query method capable of obtaining collision-free paths for high DOF manipulators with multiple surrounding obstacles is presented. The proposed method is inspired by the resistive grid-based planner method (RGBPM). Furthermore, several improvements are implemented to solve complex planning problems that cannot be handled by the original formulation. The most important features of the proposed planner are as follows: (1) the easy implementation of robotic manipulators with multiple degrees of freedom, (2) the ability to handle dozens of obstacles in the environment, (3) compatibility with various obstacle representations using mathematical models, (4) a new recycling of a previous simulation strategy to convert the RGBPM into a multiple-query planner, and (5) the capacity to handle large sparse matrices representing the configuration space. A numerical simulation was carried out to validate the proposed planning method's effectiveness for manipulators with three, five, and six DOFs on environments with dozens of surrounding obstacles. The case study results show the applicability of the proposed novel strategy in quickly computing new collision-free paths using the first execution data. Each new query requires less than 0.2 s for a 3 DOF manipulator in a configuration space free-modeled by a 7291 × 7291 sparse matrix and less than 30 s for five and six DOF manipulators in a configuration space free-modeled by 313,958 × 313,958 and 204,087 × 204,087 sparse matrices, respectively. Finally, a simulation was conducted to validate the proposed multiple-query RGBPM planner's efficacy in finding feasible paths without collision using a six-DOF manipulator (KUKA LBR iiwa 14R820) in a complex environment with dozens of surrounding obstacles.

RESUMO

Resumen: Introducción: los cuidados paliativos (CP) son un marcador de calidad de asistencia en terapia intensiva; sin embargo, han sido poco evaluados en Uruguay. La detección proactiva de pacientes mediante disparadores de consultas es una estrategia que podría optimizar el acceso a los CP. Objetivos: determinar la prevalencia y las características de los disparadores de consulta de CP en pacientes críticos. Analizar la utilización de recursos en estos pacientes. Material y método: estudio de cohorte, retrospectivo, que incluyó pacientes ingresados a unidad de cuidados intensivos (UCI) entre marzo de 2016 y febrero de 2019. Los disparadores analizados fueron: a) presencia de tumor con metástasis; b) estadía en UCI 50% por encima de la media (14 días); c) >75 años con disfunción orgánica múltiple, y d) >80 años con dos o más comorbilidades graves. Resultados: se analizaron 2.850 pacientes. El 26% (734) presentó al menos un disparador de consulta con CP. El más prevalente: estadía en UCI 50% por encima de la media (18%). Estos pacientes presentaron mayor edad: 61 (43-75) vs 54 (36-65) años (p < 0,001) y mayor gravedad, SAPSIII de 60 (48-74) vs 47 (35-61) puntos (p<0,001). Requirieron más asistencia respiratoria mecánica (ARM) 87% vs 55% (p <0,001), vasopresores 48% vs 24% (p< 0,001) y hemodiálisis 8% vs 4% (p<0,001). Presentaron mayor estadía 18 (9-27) vs 4 (2-8) días, (p<0,001) y tiempo en ARM 14 (7-23) vs 3 (1- 6) días (p<0,001). Conclusiones: la cuarta parte de los pacientes en UCI activaron al menos un criterio de CP, presentaron mayor gravedad y utilizaron más sostén de soporte vital.

Summary: Introduction: palliative care (PC) constitutes a marker of the quality of intensive care assistance. However, it has not been thoroughly assessed in Uruguay. Proactive detection of patients by means of "consultation triggers" should be considered a strategy to optimize access to PC. Objetives: to determine the prevalence and characteristics of Palliative Care consultation triggers in critical patients. To analyse the use of resources in these patients. Method: retrospective cohort study of patients admitted in the ICU between March 2016 and February 2019. The following triggers were identified: a) a tumor with metastasis; length of stay at the ICU 50% over the average (14 days), c) >75 years old with multiple organic dysfunction and d) >80 years old with 2 or more severe comorbidities Results: 2.850 patients were analysed. 26% (734) presented at least one consultation trigger with PC. Length of stay at the ICU 50% over average (18%). These patients presented higher average age 61 (43-75) versus 54 (36-65) years old (p < 0.001), and increased severity, SAPSIII of 60 (48-74) compared to 47 (35-61) points (p<0.001); 87% required mechanical ventilation compared to 55% (p <0.001), vasopressors 48% compared to 24% (p< 0.001) and hemodialysis 8% compared to 4% (p<0.001). 18 presented a longer stay (9-27) compared to 4 (2-8) days, (p<0.001) and time on mechanical ventilation 14 (7-23) compared to 3 (1- 6) days (p<0.001). Conclusions: 25 percent of patients in the ICU activated at least one criterion for PC, they were in a more severe condition and used more mechanical ventilation.

Resumo: Introdução: os cuidados paliativos (CP) são um marcador de qualidade da atenção em Terapia Intensiva, porém, pouco avaliados no Uruguai. A detecção proativa de pacientes usando "gatilhos de consulta" é uma estratégia que pode otimizar o acesso aos CP. Metas: determinar a prevalência e as características dos critérios de elegibilidade de CP em pacientes críticos. Analisar o uso de recursos nesses pacientes. Materiais e métodos: estudo de coorte retrospectivo, incluindo pacientes internados na UTI entre março de 2016 e fevereiro de 2019. Os critérios analisados foram: a) presença de tumor com metástase, b) permanência na UTI 50% acima da média (14 dias), c ) >75 anos com disfunção de múltiplos órgãos e d) >80 anos com 2 ou mais comorbidades graves. Resultados: 2.850 pacientes foram analisados. 26% (734) apresentaram pelo menos 1 critério de elegibilidade para CP. O mais prevalente foi a permanecia na UTI 50% superior à média (18%). Esses pacientes tinham mais de 61 anos (43-75) vs 54 (36-65) anos (p <0,001) e condições mais graves, SAPSIII de 60 (48-74) vs 47 (35-61) pontos (p <0,001). Necessitaram mais ventilação mecânica assistida (AVM) 87% vs 55% (p <0,001), vasopressores 48% vs 24% (p <0,001) e hemodiálise 8% vs 4% (p <0,001). Tiveram uma permanência mais prolongada 18 (9-27) vs 4 (2-8) dias, (p <0,001) e tempo em AVM 14 (7-23) vs 3 (1-6) dias (p <0,001). Conclusões: um quarto dos pacientes internados na UTI ativou pelo menos um critério de elegibilidade para CP, apresentou maior gravidade e utilizou mais suporte vital.

Assuntos

RESUMO

Objetivo: describir las aplicaciones de la teleodontología para la atención de pacientes durante y posterior a la pandemia de la COVID-19. Método: la búsqueda de artículos sobre teleodontología se realizó en las bases de datos PubMed, EMBASE, EBSCO, SCOPUS, ClinicalKey y LILACS, para identificar estudios publicados en inglés, español y portugués; se incluyeron estudios que contenían las palabras claves teleodontología y COVID-19, publicados desde enero a diciembre de 2020 y que estuvieran completos. La calidad de los artículos se evaluó según las directrices PRISMA-P. Resultados: se identificaron 49 artículos y se incluyeron 14 para la evaluación. De estos estudios, dos eran descriptivos (test de diagnóstico), seis eran estudios descriptivos de corte transversal, cinco eran pruebas pilotos; se identificó, además, un estudio de diseño retrospectivo. Se presenta la teleodontología como alternativa para diagnósticos y tratamientos de enfermedades bucales en tiempos de pandemia, mediante uso de dispositivos móviles, teleorientación y fotografías. La mayoría de los estudios presentaron un riesgo de sesgo de moderado a alto. Conclusión: la teleodontología es una herramienta tecnológica remota para apoyar la orientación, educación y tratamiento, que permite consolidar información de manera sincrónica y asincrónica sin la necesidad del contacto directo entre odontólogo y paciente.

Objective: to describe the applications of teleodontology for patient care during and after the COVID-19 pandemic. Method: the search for articles on teleodontology was carried out in the PubMed, EMBASE, EBSCO, SCOPUS, ClinicalKey and LILACS databases to identify studies published in English, Spanish and Portuguese; Studies that contained the keywords teleodontology and COVID-19, published from January to December 2020 and that were complete, were included. The quality of the articles was evaluated according to the PRISMA-P guidelines. Results: 49 articles were identified and 14 were included for evaluation. Of these studies, two were descriptive (diagnostic tests), six were descriptive cross-sectional studies, five were pilot tests; In addition, a retrospective design study was identified. Teleodontology is presented as an alternative for diagnosing and treating oral diseases in times of pandemic, through the use of mobile devices, remote orientation and photographs. Most of the studies were at moderate to high risk of bias. Conclusion: teleodontology is the remote tool to support remote guidance, education and treatment through technology, allowing the consolidation of information synchronously and asynchronously without the need for direct contact between dentist and patient

Assuntos

RESUMO

Data citation is an interesting computational challenge, whose solution draws on several well-studied problems in database theory: query answering using views, and provenance. We describe the problem, suggest an approach to its solution, and highlight several open research problems, both practical and theoretical.