{"id":11863,"date":"2021-01-08T09:24:02","date_gmt":"2021-01-08T15:24:02","guid":{"rendered":"https:\/\/saluddigital.com\/?p=11863"},"modified":"2025-10-21T13:55:52","modified_gmt":"2025-10-21T19:55:52","slug":"nuevo-estudio-sobre-la-prediccion-de-covid-19-a-traves-de-aprendizaje-profundo","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/avance-de-la-ciencia\/nuevo-estudio-sobre-la-prediccion-de-covid-19-a-traves-de-aprendizaje-profundo\/","title":{"rendered":"New study on COVID-19 prediction through deep learning"},"content":{"rendered":"<div data-elementor-type=\"wp-post\" data-elementor-id=\"11863\" class=\"elementor elementor-11863\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-12e7b5af elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no wpr-equal-height-no\" data-id=\"12e7b5af\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-69e87950\" data-id=\"69e87950\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-74ba8640 elementor-widget elementor-widget-heading\" data-id=\"74ba8640\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Nature published a new research based on Artificial Intelligence that, according to more than 50 thousand tests studied, would be able to predict COVID-19 by asking some basic questions.<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-3db6f53d elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no wpr-equal-height-no\" data-id=\"3db6f53d\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-34ef17c7\" data-id=\"34ef17c7\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-4164dfbc elementor-widget elementor-widget-text-editor\" data-id=\"4164dfbc\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>The application of tests, the rapid isolation of infected patients, as well as the tracking of contacts are important measures to stop the transmission of the virus and thus reduce mortality by COVID-19. Equally important for health systems is rapid and efficient diagnosis, for which predictive models have been developed that can estimate the risk of infection. These are intended to facilitate the classification of patients in order to make better use of available resources.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5fe6c7c9 elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no wpr-equal-height-no\" data-id=\"5fe6c7c9\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-124d66b5\" data-id=\"124d66b5\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-74089b56 elementor-widget elementor-widget-image\" data-id=\"74089b56\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"1200\" height=\"630\" src=\"https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo.jpg\" class=\"attachment-full size-full wp-image-11864\" alt=\"\" srcset=\"https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo.jpg 1200w, https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo-660x347.jpg 660w, https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo-768x403.jpg 768w, https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo-840x441.jpg 840w, https:\/\/saluddigital.com\/wp-content\/uploads\/2021\/01\/Nuevo-estudio-sobre-la-predicci\u00f3n-de-COVID-19-a-trav\u00e9s-de-aprendizaje-profundo-16x8.jpg 16w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-3c65a19e\" data-id=\"3c65a19e\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-33ed6d05 elementor-widget elementor-widget-text-editor\" data-id=\"33ed6d05\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>In the research published by Nature and its journal npj Digital Medicine entitled: \u201cMachine learning-based prediction of COVID-19 diagnosis based on symptoms\u201d, researchers planned an approach based on automatic learning with records of 51,831 people tested, of which 4,769 were positive. The data were obtained from the Ministry of Health of Israel, the researchers' place of origin.<\/p><p>The model predicted test results using eight characteristics: sex, age &gt;60 years, contact with infected people, and the appearance of five symptoms.  In this way, priority can be given to testing for COVID-19 when resources are limited.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-500fb0a5 elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no wpr-equal-height-no\" data-id=\"500fb0a5\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-738e6df2\" data-id=\"738e6df2\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-c990668 elementor-widget elementor-widget-text-editor\" data-id=\"c990668\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>The following is a list of the characteristics on which the prediction model was developed, with their category and response options:<\/p><ul><li><strong>Basic information<\/strong>: Sex (male \/ female) and Age \u226560 years (true \/ false).<\/li><li><strong>Symptoms <\/strong>: Cough (true\/false), Fever (true\/false), Sore throat (true\/false), Shortness of breath (true\/false), Headache (true\/false).<\/li><li><strong>Other Information: <\/strong>Known contact with an individual confirmed to have COVID-19 (true\/false).<\/li><\/ul><p>The researchers accepted some limitations of the model, due to available data on self-reported symptoms and contact of individuals with confirmed patients: \u201cWe showed that training and testing a model while filtering out symptoms of high bias in advance still achieved very high accuracy. We also note that all the symptoms were self-reported, and a negative value for a symptom might mean that the symptom was not reported. It is therefore important to assess the model\u2019s performance in the circumstance that more values are unreported or missing rather than with negative values,\u201d they explain in the discussion section.<\/p><p>However, in the research they explain that they carried out random tests to test the model and obtained important results, so they are confident about the model's effectiveness:  To simulate a less biased condition, in our prospective test set, we randomly selected negative reports of all five symptoms at a time, and removed the negative values. When applied to these simulated test sets, the model still showed promising results, thus reinforcing our confidence in the model\u201d.<\/p><p>To read the full article, click on the following link: <a href=\"https:\/\/www.nature.com\/articles\/s41746-020-00372-6#Abs1\">https:\/\/www.nature.com\/articles\/s41746-020-00372-6#Abs1<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5e9060cf elementor-section-boxed elementor-section-height-default elementor-section-height-default wpr-particle-no wpr-jarallax-no wpr-parallax-no wpr-sticky-section-no wpr-equal-height-no\" data-id=\"5e9060cf\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-6069c2da\" data-id=\"6069c2da\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-45dfd96e elementor-widget elementor-widget-toggle\" data-id=\"45dfd96e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"toggle.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<div class=\"elementor-toggle\">\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<div id=\"elementor-tab-title-1171\" class=\"elementor-tab-title\" data-tab=\"1\" role=\"button\" aria-controls=\"elementor-tab-content-1171\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\"> BIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1171\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"1\" role=\"region\" aria-labelledby=\"elementor-tab-title-1171\"><p><strong>ANDEAN <\/strong><\/p><p><a href=\"https:\/\/www.nature.com\/articles\/s41746-020-00372-6\">https:\/\/www.nature.com\/articles\/s41746-020-00372-6<\/a><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"<p>Nature public\u00f3 una nueva investigaci\u00f3n basada en Inteligencia Artificial que, gracias a m\u00e1s de 50 mil pruebas estudiadas, ser\u00eda capaz de predecir COVID-19 al realizar algunas preguntas b\u00e1sicas. La aplicaci\u00f3n de pruebas, el aislamiento r\u00e1pido de pacientes contagiados, as\u00ed como el rastreo de contactos son medidas importantes para frenar la transmisi\u00f3n del virus y as\u00ed reducir la mortalidad por COVID-19. De igual importancia para los sistemas de salud es el diagn\u00f3stico r\u00e1pido y eficiente, para ello se han desarrollado modelos de predicci\u00f3n que pueden estimar el riesgo de infecci\u00f3n. Estos tienen como objetivo facilitar la clasificaci\u00f3n de pacientes para aprovechar mejor los recursos disponibles. En la investigaci\u00f3n publicada por Nature y su revista npj Digital Medicine titulada: \u201cPredicci\u00f3n basada en el aprendizaje autom\u00e1tico del diagn\u00f3stico de COVID-19 basado en los s\u00edntomas\u201d, los investigadores planearon un enfoque basado en aprendizaje autom\u00e1tico con registros de 51 mil 831 personas probadas, de las cuales 4 mil 769 resultaron positivas. Los datos fueron obtenidos del Ministerios de Salud de Israel, lugar de origen de los investigadores. El modelo predijo los resultados de pruebas al utilizar ocho caracter\u00edsticas: sexo, edad &gt;60 a\u00f1os, contacto con infectados, y la aparici\u00f3n de cinco s\u00edntomas. &nbsp;De esta manera se pueden priorizar las pruebas de COVID-19 cuando los recursos son limitados. A continuaci\u00f3n, la lista de las caracter\u00edsticas sobre las que fue desarrollado el modelo de predicci\u00f3n, con su categor\u00eda y sus opciones de respuesta: Informaci\u00f3n b\u00e1sica: Sexo (hombre \/ mujer) y Edad \u226560 a\u00f1os (verdadero \/ falso). S\u00edntomas: Tos (verdadero \/ falso), Fiebre (verdadero \/ falso), Dolor de garganta (verdadero \/ falso), Dificultad para respirar (verdadero \/ falso), Dolor de cabeza (verdadero \/ falso). Otra informaci\u00f3n: Contacto conocido con un individuo con caso confirmado de COVID-19 (verdadero \/ falso). Los investigadores aceptaron algunas limitantes del modelo, debido a los datos disponibles sobre s\u00edntomas autoinformados y el contacto de personas con pacientes confirmados: \u201cDemostramos que entrenar y probar un modelo mientras se filtraban los s\u00edntomas de alto sesgo por adelantado a\u00fan lograba una precisi\u00f3n muy alta.&nbsp;Tambi\u00e9n observamos que todos los s\u00edntomas fueron autoinformados y un valor negativo para un s\u00edntoma podr\u00eda significar que no se inform\u00f3 el s\u00edntoma.&nbsp;Por lo tanto, es importante evaluar el desempe\u00f1o del modelo en la circunstancia de que falten o no se informen m\u00e1s valores que con valores negativos\u201d, explican en el apartado de discusi\u00f3n. Sin embargo, en la investigaci\u00f3n explican que realizaron pruebas aleatorias para probar el modelo y obtuvieron resultados importantes, por lo que conf\u00edan por la eficacia del modelo: \u201cPara simular una condici\u00f3n menos sesgada, en nuestro conjunto de pruebas prospectivas, seleccionamos al azar informes negativos de los cinco s\u00edntomas a la vez y eliminamos los valores negativos. Cuando se aplic\u00f3 a estos conjuntos de prueba simulados, el modelo a\u00fan mostr\u00f3 resultados prometedores, lo que refuerza nuestra confianza en el modelo\u201d, concluyen. Para leer el art\u00edculo completo consulta el siguiente enlace: https:\/\/www.nature.com\/articles\/s41746-020-00372-6#Abs1 BIBLIOGRAF\u00cdA ANDINA https:\/\/www.nature.com\/articles\/s41746-020-00372-6<\/p>","protected":false},"author":1,"featured_media":11864,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3399,152,156,1418],"tags":[145],"class_list":["post-11863","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-analitica","category-avance-de-la-ciencia","category-big-data","category-resena-de-publicaciones-cientificas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11863","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/comments?post=11863"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11863\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/11864"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=11863"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=11863"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=11863"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}