{"id":10613,"date":"2020-10-29T09:21:43","date_gmt":"2020-10-29T15:21:43","guid":{"rendered":"https:\/\/saluddigital.com\/?p=10613"},"modified":"2025-10-21T14:20:48","modified_gmt":"2025-10-21T20:20:48","slug":"para-calcular-el-numero-de-casos-de-covid-19-no-reportados-investigadores-promueven-la-aplicacion-de-aprendizaje-automatico-e-inteligencia-artificial","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/avance-de-la-ciencia\/para-calcular-el-numero-de-casos-de-covid-19-no-reportados-investigadores-promueven-la-aplicacion-de-aprendizaje-automatico-e-inteligencia-artificial\/","title":{"rendered":"To calculate the number of unreported COVID-19 cases, researchers promote the application of machine learning and artificial intelligence"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Researchers at Chan Zuckerberg Biohub, a joint initiative of UC Berkeley, UC San Francisco and Stanford University, are working on a machine learning and cloud technology technique that can more accurately understand the number of uninsured COVID-19 cases.<\/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
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Artificial Intelligence has played an increasingly relevant role for the medical sciences in recent years. In 2020, during the pandemic, various strategies have emerged from health research centers and health authorities in various countries to measure trends and developments in the epidemiological landscape.\u00a0<\/p>

This Chan Zuckerberg Biohub project is intended to be a tool to reduce the spread of COVID-19. \u201cIt is now well-known that asymptomatic infections are a common phenomenon in the spread of coronavirus. And it's very important to understand that phenomenon because, depending on how many asymptomatic infections there are, public health interventions might be different\u201d said Dr. Lucy Li, data scientist at Chan Zuckerberg Biohub in an interview with HealthITAnalytics.<\/p>

The same Li, in conjunction with researcher Patrick Ayscue also of the Chan Zuckerberg Biohub, published in June an article on the use of viral genomes to estimate undetected COVID-19 infections. \u201cFor disease outbreaks where you can detect every single infection, rapid testing and just a small amount of contact tracing is enough to get the epidemic under control. But for coronavirus, because there are so many asymptomatic infections out there, testing alone won't help control the pandemic\u201d, she said.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\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
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Through the exchange and increased availability of innovative data and tools, such as AI, through machine learning it will be possible to more accurately detect the behavior of contagions \u201cThe data I'm using are the viral genomes \u2013 the viral DNA. As the viral genomes spread through the population, they accumulate mutations. Generally, these mutations are not good or bad, they're just changes in the genome. Every time the virus is spread to a new person, it could accumulate new mutations. So, if we know how quickly the virus mutates, we can infer how many missing transmission links there were in between the observed genomes\u201d, Li explained in an interview with the specialized website.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Through that type of data, it is how the model is trained as it can \"simulate\" different scenarios to know what is known about these viral genomes, in addition machine learning optimizes and streamlines these processes that previously required more time. \u201cBefore cloud computing became more common and these big computational resources became available, some of these analyses could take months to run. I've seen papers that were based on months of running a very complex model\u201d explains the researcher, who at the same time recognizes the importance of applying new technologies to achieve better results. \u201cBut by having access to more computational resources in the cloud, we can shorten that time from months to days, because we're able to leverage much more memory and better parallelize our analysis.\u201d<\/p>

Scientists hope that this model can be adopted by health authorities in various countries. They also explained that in each place different results can be obtained, if an increase in under-registered cases is detected it may be necessary to increase the number of tests in the population, in addition also this type of research on a massive scale could help to know how close we are to the end of the pandemic. \u201cBy tracking how many people in the population have been infected by the virus or the number of undetected cases, we could get a sense of how far are we from eliminating this disease,\u201d Li concluded.<\/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

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/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\tBIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

HEALTH IT ANALYTICS <\/strong><\/p>

https:\/\/healthitanalytics.com\/news\/using-machine-learning-to-calculate-unreported-covid-19-cases<\/a><\/p>

\u00a0<\/strong><\/p>

MEDRXIV<\/strong><\/p>

https:\/\/www.medrxiv.org\/content\/10.1101\/2020.05.05.20092098v3<\/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":"

Investigadores del Chan Zuckerberg Biohub, una iniciativa conjunta de UC Berkeley, UC San Francisco y la Universidad de Stanford, se encuentran trabajando en una t\u00e9cnica de aprendizaje autom\u00e1tico y tecnolog\u00eda en la nube que pueda conocer con mayor precisi\u00f3n la cantidad de casos de COVID-19 no reportados. La Inteligencia Artificial ha desempe\u00f1ado un rol cada vez m\u00e1s relevante para las ciencias m\u00e9dicas durante los \u00faltimos a\u00f1os. En 2020, durante la pandemia, han surgido diversas estrategias por parte de centros de investigaci\u00f3n en salud y autoridades de salud en diversos pa\u00edses, para medir las tendencias y la evoluci\u00f3n del panorama epidemiol\u00f3gico.\u00a0 Este proyecto de Chan Zuckerberg Biohub, pretende ser una herramienta para reducir la propagaci\u00f3n de COVID-19. \u201cAhora es bien sabido que las infecciones asintom\u00e1ticas son un fen\u00f3meno com\u00fan en la propagaci\u00f3n del coronavirus. Y es muy importante entender ese fen\u00f3meno porque, dependiendo de cu\u00e1ntas infecciones asintom\u00e1ticas haya, las intervenciones de salud p\u00fablica pueden ser diferentes\u201d, dijo la Dra. Lucy Li, cient\u00edfica de datos en Chan Zuckerberg Biohub en entrevista con HealthITAnalytics. La misma Li en conjunto con el investigador Patrick Ayscue tambi\u00e9n de la Chan Zuckerberg Biohub, publicaron en junio un art\u00edculo sobre la utilizaci\u00f3n de genomas virales para estimar contagios de COVID-19 no detectados. \u201cPara los brotes de enfermedades en los que se pueden detectar todas y cada una de las infecciones, las pruebas r\u00e1pidas y una peque\u00f1a cantidad de rastreo de contactos son suficientes para controlar la epidemia.\u00a0Pero para el coronavirus, debido a que hay tantas infecciones asintom\u00e1ticas, las pruebas por s\u00ed solas no ayudar\u00e1n a controlar la pandemia\u201d, mencion\u00f3 la investigadora. A trav\u00e9s del intercambio y la mayor disponibilidad de datos y herramientas innovadoras, como la IA, a trav\u00e9s del aprendizaje autom\u00e1tico ser\u00e1 posible detectar con mayor precisi\u00f3n el comportamiento de los contagios \u201cLos datos que estoy usando son los genomas virales, el ADN viral. A medida que los genomas virales se propagan por la poblaci\u00f3n, acumulan mutaciones. Generalmente, estas mutaciones no son buenas ni malas, son solo cambios en el genoma. Cada vez que el virus se transmite a una nueva persona, podr\u00eda acumular nuevas mutaciones. Entonces, si sabemos qu\u00e9 tan r\u00e1pido muta el virus, podemos inferir cu\u00e1ntos enlaces de transmisi\u00f3n faltantes hab\u00eda entre los genomas observados\u201d, explic\u00f3 Li en entrevista con el medio especializado. A trav\u00e9s de ese tipo de datos, es como el modelo es entrenado ya que puede hacer “simulaciones” de diferentes escenarios para saber qu\u00e9 es lo que se conoce de estos genomas virales, adem\u00e1s el aprendizaje autom\u00e1tico optimiza y agilizan estos procesos que antes requer\u00edan mayor tiempo. \u201cAntes de que la computaci\u00f3n en la nube fuera m\u00e1s com\u00fan y estos grandes recursos computacionales estuvieran disponibles, algunos de estos an\u00e1lisis pod\u00edan tardar meses en ejecutarse.\u00a0He visto art\u00edculos basados \u200b\u200ben meses de ejecuci\u00f3n de un modelo muy complejo\u201d, explica la investigadora, que a la vez reconoce la importancia de aplicar las nuevas tecnolog\u00edas para lograr mejores resultados. \u201cPero al tener acceso a m\u00e1s recursos computacionales en la nube, podemos acortar ese tiempo de meses a d\u00edas, porque podemos aprovechar mucha m\u00e1s memoria y paralelizar mejor nuestro an\u00e1lisis\u201d. Los cient\u00edficos esperan que este modelo pueda ser adoptado por autoridades sanitarias en diversos pa\u00edses. Adem\u00e1s explicaron que en cada lugar se pueden obtener diferentes resultados, si se detecta un aumento de casos subregistrados es posible que sea necesario incrementar el n\u00famero de pruebas en la poblaci\u00f3n, adem\u00e1s tambi\u00e9n este tipo de investigaciones en una escala masiva podr\u00edan ayudar a conocer que tan cerca estamos del final de la pandemia. \u201cAl rastrear cu\u00e1ntas personas de la poblaci\u00f3n han sido infectadas por el virus o el n\u00famero de casos no detectados, podr\u00edamos tener una idea de qu\u00e9 tan lejos estamos de eliminar esta enfermedad\u201d, concluy\u00f3 Li. BIBLIOGRAF\u00cdA HEALTH IT ANALYTICS https:\/\/healthitanalytics.com\/news\/using-machine-learning-to-calculate-unreported-covid-19-cases \u00a0 MEDRXIV https:\/\/www.medrxiv.org\/content\/10.1101\/2020.05.05.20092098v3<\/p>","protected":false},"author":1,"featured_media":10614,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[152,156],"tags":[145],"class_list":["post-10613","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-avance-de-la-ciencia","category-big-data","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/10613","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=10613"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/10613\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/10614"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=10613"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=10613"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=10613"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}