ABSTRACT
Resumen La analítica del aprendizaje es una disciplina novedosa que tiene un enorme potencial para mejorar la calidad de la educación médica y la evaluación del aprendizaje. Se define como: la medición, recopilación, análisis y reporte de datos sobre los alumnos y sus contextos, con el propósito de entender y optimizar el aprendizaje y los entornos en que ocurre. En las últimas décadas, la aparición de grandes volúmenes de datos (big data), acompañada de una rápida evolución en la minería de datos educativos, la aparición de tecnologías sofisticadas para analizar y visualizar datos de cualquier tipo, así como la disponibilidad de dispositivos móviles con conectividad permanente, mayor velocidad de procesamiento y capacidad de recuperación de información, han generado un contexto que favorece el uso de la analítica del aprendizaje en la medicina clínica y la educación médica. En este artículo se describe la historia reciente del concepto de analítica del aprendizaje, sus ventajas y desventajas en educación superior, así como sus aplicaciones en la enseñanza de las ciencias de la salud y la evaluación educativa. Es necesario que la comunidad de educadores médicos conozca la analítica del aprendizaje, para ser capaces de integrarla en su contexto eficaz y oportunamente.
Abstract Learning analytics is an innovative discipline that has an enormous potential to improve the quality of medical education and learning assessment. It is defined as: the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs. In recent decades, the appearance of large volumes of data (big data), accompanied by a quick evolution of educational data mining techniques, the emergence of sophisticated technologies to analyze and visualize any type of data, as well as the availability of permanently-connected mobile electronic devices, higher processing speed and capacity of information retrieval, have generated a context that favors the use of learning analytics in clinical medicine and medical education. In this paper, the recent history of the concept of learning analytics is described, as well as its advantages and disadvantages in higher education, and its applications in the teaching of health sciences and educational assessment. It is necessary for the community of medical educators to be acquainted with learning analytics, in order to be able to integrate it to our context in an efficacious and timely manner.
Subject(s)
Humans , Educational Technology , Education, Medical/methods , Learning , Data Collection/methods , Data Mining/methods , Big DataABSTRACT
Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of human health and disease. Developed from artificial neural networks, deep learning-based algorithms show great promise in extracting features and learning patterns from complex data. The aim of this paper is to provide an overview of deep learning techniques and some of the state-of-the-art applications in the biomedical field. We first introduce the development of artificial neural network and deep learning. We then describe two main components of deep learning, i.e., deep learning architectures and model optimization. Subsequently, some examples are demonstrated for deep learning applications, including medical image classification, genomic sequence analysis, as well as protein structure classification and prediction. Finally, we offer our perspectives for the future directions in the field of deep learning.
Subject(s)
Humans , Algorithms , Computational Biology , Methods , Diagnostic Imaging , Genomics , Methods , Image Interpretation, Computer-Assisted , Methods , Machine Learning , Neural Networks, Computer , Protein Structure, Secondary , Proteins , MetabolismABSTRACT
Adverse drug reactions (ADRs) induced by drug-drug interactions have posed a serious threat to patients′health and caused immense economic losses. With the increase in the number of combined drugs, the occurrence rate of side effects has surged. Since traditional methods for discovering drug interactions are infficient and costly, the biomedical informatics based methods are able to acquire valuable information about ADR by analyzing and mining from biomedical big data at a low cost and with high throughput. Methods of discovering potential drug interactions through literature mining, data mining and physiologically based pharmacokinetic models are systematically reviewed in this paper. Also, the prospect of potential research fields of drug conbination is outlined.
ABSTRACT
Bioinformatics is a rapidly emerging field of biomedical research. A flood of large-scale genomic, proteomic and postgenomic data means that many of the challenges in biomedical research are now challenges in informatics. Clinical informatics has long developed technologies to improve biomedical research and clinical care by integrating experimental and clinical information systems. Biomedical informatics, powered by high throughput technologies, genomic-scale databases, and advanced clinical information system, is likely to transform our biomedical understanding forever much the same way that biochemistry did to biology a generation ago. The emergence of health and biomedical informatics revolutionizing both bioinformatics and clinical informatics will eventually change the current practice of medicine, including diagnostics, therapeutics, and prognostics.