RESUMO
Given the rapid spread of COVID-19, having tools to screen patients and reduce the risk of death is crucial. This study focuses on the outcomes (cures and deaths) of confirmed COVID-19 cases in Rio de Janeiro State for both vaccinated and unvaccinated patients. Machine Learning (ML) algorithms were used to classify outcomes based on symptom, comorbidity, and age data obtained from the State Health Secretariat of Rio de Janeiro. After cleaning the dataset and selecting relevant attributes, the final model achieved an accuracy of 87,3% and a precision of 86,6% in predicting outcomes for unvaccinated patients. Similarly, the final model for vaccinated patients achieved an accuracy of 86,3% and a precision of 83,1% in predicting outcomes. In addition, the attributes of patients that stand out with and without the vaccine were evaluated. Overall, these results demonstrate the potential benefits of using machine learning methods to improve patient screening and reduce the risk of COVID-19-related deaths. (AU)
RESUMO
While several statistical machine learning methods have been developed and studied for assessing the genomic prediction (GP) accuracy of unobserved phenotypes in plant breeding research, few methods have linked genomics and phenomics (imaging). Deep learning (DL) neural networks have been developed to increase the GP accuracy of unobserved phenotypes while simultaneously accounting for the complexity of genotype-environment interaction (GE); however, unlike conventional GP models, DL has not been investigated for when genomics is linked with phenomics. In this study we used 2 wheat data sets (DS1 and DS2) to compare a novel DL method with conventional GP models. Models fitted for DS1 were GBLUP, gradient boosting machine (GBM), support vector regression (SVR) and the DL method. Results indicated that for 1 year, DL provided better GP accuracy than results obtained by the other models. However, GP accuracy obtained for other years indicated that the GBLUP model was slightly superior to the DL. DS2 is comprised only of genomic data from wheat lines tested for 3 years, 2 environments (drought and irrigated) and 2-4 traits. DS2 results showed that when predicting the irrigated environment with the drought environment, DL had higher accuracy than the GBLUP model in all analyzed traits and years. When predicting drought environment with information on the irrigated environment, the DL model and GBLUP model had similar accuracy. The DL method used in this study is novel and presents a strong degree of generalization as several modules can potentially be incorporated and concatenated to produce an output for a multi-input data structure.
Assuntos
Aprendizado Profundo , Triticum , Triticum/genética , Melhoramento Vegetal/métodos , Modelos Genéticos , Fenótipo , Genômica/métodos , GenótipoRESUMO
Este artículo propone un método de aprendizaje profesional basado en proyectos para la formación inicial o continua de los trabajadores, el cual expresa como novedad científica el establecimiento de una dinámica que sistematiza la regularidad de un método de trabajo tecnológico con un método de enseñanza aprendizaje profesional e integra en periodos alternos por ciclos formativos profesionales a la docencia con la práctica laboral y el trabajo de investigación científica mediante el tratamiento de las relaciones entre lo instructivo con lo educativo y el crecimiento profesional. La investigación se orientó en un enfoque cuantitativo de tipo preexperimental. La muestra objeto de estudio, estuvo constituida por 60 estudiantes del Instituto Tecnológico de Holguin. Se emplearon como métodos el análisis documental, el enfoque sistémico, la observación, el preexperimento pedagógico y el estadígrafo Chi-Cuadrado (X2). Luego de analizar los datos, se encontró la existencia de transformaciones significativas en el aprendizaje de dichos estudiantes que generaron impactos favorables en los procesos productivos y de servicios en las cuales se insertaron laboralmente, concluyendo que este método desde su aspecto externo y estructura interna contribuye a elevar la calidad de la formación profesional del trabajador desde un enfoque más integral flexible y contextualizado.
This article proposes a project-based professional learning method for the initial or continuous training of workers. As a scientific novelty, it establishes a dynamic that systematizes the regularity of the technological work method -professional teaching-learning method- and integrates teaching with work practice and scientific research in alternate periods by professional training cycles by treating the relationships between instruction and educational and profesional growth. The research adopted a quantitative approach of a pre-experimental type. The sample under study consisted of 60 students from the Instituto Tecnológico de Holguin. Documentary analysis, systemic approach, observation, pedagogical pre-experiment, and the Chi-Square statistician (X2) were used as methods. After analyzing the data, significant transformations in these students' learning were found that produced favorable impacts on the productive processes and services in which they were inserted in the workplace. In conclusion, from its external aspect and internal structure, this method contributes to raising the worker's professional training quality from a more comprehensive, flexible, and contextualized approach.
RESUMO
ABSTRACT Learning is a complex construct that involves several factors, mainly the interaction between teachers and students in the process of teaching and learning. Understanding how students learn and which factors influence academic performance is essential information for lesson planning and evaluation, in addition to allowing a better use of students' learning potential and outcomes. The ability to constructively modify one's behavior depends on how well we combine our experiences, reflections, conceptualizations, and planning to make improvements. This seems particularly relevant in medical education, where students are expected to retain, recall, and apply vast amounts of information assimilated throughout their training period. Over the years, there has being a gradual shift in medical education from a passive learning approach to an active learning approach. To support the learning environment, educators need to be aware of the different learning styles of their students to effectively tailor instructional strategies and methods to cater to students' learning needs. However, the space for reflection on the process of teaching is still incipient in higher-education institutions in Brazil. The present article proposes a critical review of the importance of identifying students' learning styles in undergraduate medical education. Different models exist for assessing learning styles. Different styles can coexist in equilibrium (multimodal style) or predominate (unimodal style) in the same individual. Assessing students' learning styles can be a useful tool in education, once it is possible to analyze with what kind of learning students can better develop themselves, improving their knowledge and influencing positively in the process of learning. Over the last century, medical education experienced challenges to improve the learning process and curricular reform. Also, this has resulted in crucial changes in the field of medical education, with a shift from a teacher centered and subject based teaching to the use of interactive, problem based, student centered learning.
RESUMO A aprendizagem é uma construção complexa que envolve diversos fatores, principalmente a interação entre professores e alunos no processo de ensino/ aprendizagem. Entender como os alunos aprendem e quais fatores influenciam o desempenho acadêmico são informações essenciais para o planejamento das aulas, além de permitir um melhor aproveitamento do potencial de aprendizado e desempenho dos alunos. A capacidade de modificar construtivamente o comportamento de uma pessoa depende de quão bem combinamos nossas experiências, reflexões, conceituações e estratégias para desenvolver o processo de mudança. Isso parece particularmente relevante na educação médica, na qual se espera que os alunos retenham, processem e apliquem grandes quantidades de informação durante todo o período de treinamento. Ao longo dos anos tem havido uma mudança gradual na educação médica de uma abordagem de aprendizagem passiva para uma abordagem de aprendizagem ativa. Para fortalecer o ambiente de aprendizado, os educadores precisam estar cientes dos diferentes estilos de aprendizado de seus alunos e, desta forma, adaptar estratégias e metodologias pedagógicas que aprimoram o processo de aprendizagem. No entanto, o espaço de reflexão sobre o processo de ensino ainda é incipiente nas instituições de ensino superior no Brasil. O presente artigo propõe uma revisão crítica sobre a importância da identificação dos estilos de aprendizagem dos alunos no ensino médico de graduação. Existem diferentes ferramentas para avaliar estilos de aprendizagem. Diferentes estilos podem coexistir em equilíbrio (estilo multimodal) ou predominar (estilo unimodal) no mesmo indivíduo. Avaliar os estilos de aprendizagem dos alunos pode ser uma ferramenta útil na educação, uma vez que é possível analisar as vias sensoriais mais favoráveis para assimilar e processar os conhecimentos, influenciando positivamente o processo de aprendizagem. No último século, a educação médica vem postulando novos desafios para melhorar o processo de aprendizagem através da reforma curricular. Além disso, impulsionou mudanças cruciais no campo da educação médica, transformando um modelo de ensino passivo, previsível e centrado na figura do professor em um modelo de aprendizagem ativo, centrado no aluno, interativo e baseado em problemas.