Extracción y procesamiento de datos a partir de historiales clínicos de pacientes

Abstract

Con el paso de los años, el aumento exponencial de los datos no estructurados ha hecho que su administración y la extracción de información sea un gran desafío, ya que los datos deben convertirse en formatos legibles para una máquina, con el fin de que esta pueda procesar los datos recogidos, analizarlos, y dar una solución esperada. En colaboración con el Centro Neurológico Antonio Alayón, el TFG se centrará en el diseño y desarrollo de una herramienta de extracción, tratamiento y visualización de datos a partir de historiales clínicos de los pacientes del centro (en formato ODT/DOC), así como estructurar los datos en una base de datos para su posterior visualización. Principalmente, el trabajo se centra en la extracción y procesamiento de los datos recogidos de los historiales clínicos e introducirlos de forma estructurada en una base de datos, pero, además del cometido principal, se ha desarrollado una aplicación web de gestión de datos para añadir, editar o borrar nuevos historiales clínicos, además, de poder visualizar de forma gráfica los datos recogidos del proceso de extracción, sirviendo así como una herramienta útil para el personal del centro. Las principales tecnologías utilizadas en el proyecto van desde el IDE (PyCharm 2019.2), lenguajes de programación, principalmente, Python y JavaScript, así como de frameworks de programación, tanto de backend (Flask) como frontend (BootStrap, DataTables, Plotly)

Over the years, the exponential increase in unstructured data has supposed that its administration and information extraction represent a great challenge, since the data must be converted into readable formats for a machine, so that it can process the collected data, analyze it, and give an expected solution. In collaboration with Centro Neurológico Antonio Alayón, TFG will focus on the design and development of a data extraction, treatment and visualization tool from the center's patients records (ODT / DOC format), as well as structuring the data in a database for later visualization. The project was focused on the extraction and processing of the data collected from the clinical records and stored in a structured way into a database, but, in addition to the main proposal, a web application for data management has been developed to add, edit or delete new clinical records. In addition, this application allows the users to visualize the data obtained from the extraction process, serving as a useful tool for the center's staff. The main technologies used in the project are the IDE (PyCharm 2019.2), programming languages, mainly Python and JavaScript, as well as programming frameworks, both backend (Flask) and frontend (BootStrap, DataTables, Plotly)

Over the years, the exponential increase in unstructured data has supposed that its administration and information extraction represent a great challenge, since the data must be converted into readable formats for a machine, so that it can process the collected data, analyze it, and give an expected solution. In collaboration with Centro Neurológico Antonio Alayón, TFG will focus on the design and development of a data extraction, treatment and visualization tool from the center's patients records (ODT / DOC format), as well as structuring the data in a database for later visualization. The project was focused on the extraction and processing of the data collected from the clinical records and stored in a structured way into a database, but, in addition to the main proposal, a web application for data management has been developed to add, edit or delete new clinical records. In addition, this application allows the users to visualize the data obtained from the extraction process, serving as a useful tool for the center's staff. The main technologies used in the project are the IDE (PyCharm 2019.2), programming languages, mainly Python and JavaScript, as well as programming frameworks, both backend (Flask) and frontend (BootStrap, DataTables, Plotly)