{"id":10914,"date":"2020-11-11T09:29:33","date_gmt":"2020-11-11T15:29:33","guid":{"rendered":"https:\/\/saluddigital.com\/?p=10914"},"modified":"2025-10-21T14:15:08","modified_gmt":"2025-10-21T20:15:08","slug":"mit-presento-herramienta-basada-en-ia","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/comunidades-conectadas\/mit-presento-herramienta-basada-en-ia\/","title":{"rendered":"MIT unveiled artificial intelligence-based tool and cough recordings for COVID-19 detection in people without symptoms"},"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

Through the sound of the cough recorded by a mobile phone, the algorithm is able to detect asymptomatic cases of COVID-19<\/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

Since April, the Massachusetts Institute of Technology (MIT) has developed an artificial intelligence-based algorithm for COVID-19 detection through coughing. After months of training the algorithm through 70 thousand recordings of forced cough that sent volunteers through mobile devices or web platforms the process was completed. For data collection, MIT's partnerships with universities and study centers around the world, such as Tose con causa<\/em> (https:\/\/www.toseconcausa.udg.mx<\/a>) campaign, launched by the University of Guadalajara in June, were important.<\/p>

MIT researchers found that people with an asymptomatic SARS-CoV-2 infection can cause changes in people's coughs, so a person's cough with asymptomatic infection is different from that of an infection-free person. However, the differences between the two coughs are not noticeable to the human ear, in the face of this, Artificial Intelligence was key, to develop a reliable algorithm that could verify the assertion.<\/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

The algorithm was fed tens of thousands of cough samples as well as spoken words. The algorithm accurately identified 98.5% cough of people with confirmed COVID-19 case, and 100% cough of asymptomatic people.<\/p>

MIT's plan with this innovation is to incorporate this AI model into an easy-to-use application and seek FDA (Food and Drug Administration) approval to make it available to the population for free and easily identify asymptomatic people, and reduce contagion.<\/p>

\u201cThe effective implementation of this group diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, or a restaurant,\u201d said Brian Subirana, a Catalan research scientist who is a member of MIT's Auto-ID Laboratory and developer of this project.<\/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

Prior to the pandemic, researchers had worked on training algorithms that could diagnose pneumonia or asthma through mobile cough recordings. On the same line MIT had developed AI models for cough analysis for Signs of Alzheimer's. \u201cThe sounds of talking and coughing are both influenced by the vocal cords and surrounding organs. This means that when you talk, part of your talking is like coughing, and vice versa. It also means that things we easily derive from fluent speech, AI can pick up simply from coughs, including things like the person\u2019s gender, mother tongue, or even emotional state. There\u2019s in fact sentiment embedded in how you cough,\u201d Subirana explained.<\/p>

Thanks to previous studies, they began testing this type of biomarkers in COVID-19. It was in April that they began collecting voice recordings from both confirmed COVID-19 patients and healthy people.<\/p>

The 70.000 recordings contain various types of cough, which equates to about 200 thousand cough samples. Nearly 2.500 recordings were for people who confirmed coVID-19, including asymptomatic ones.<\/p>

Researchers Jordi Laguarta and Ferran Hueto accompanying Subirana agreed that there are similarities between Alzheimer's discrimination and COVID-19. Since they didn't have to make many adjustments to the AI model that was originally built for Alzheimer's. This model detects patterns in four biomarkers: vocal cord strength, feeling, lung and respiratory performance and muscle degradation.<\/p>

Advances in his research were published in IEEE Journal of Engineering in Medicine and Biology. Finally, the authors mention that \u201cpandemics could be a thing of the past if pre-screening tools are always on in the background and constantly improved.\u201d<\/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

MIT <\/strong><\/p>

https:\/\/news.mit.edu\/2020\/covid-19-cough-cellphone-detection-1029<\/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":"

A trav\u00e9s del sonido de la tos grabado por un tel\u00e9fono m\u00f3vil, el algoritmo es capaz de detectar casos asintom\u00e1ticos de COVID-19 El Massachusetts Institute of Technology (MIT), ha desarrollado desde abril un algoritmo basado en inteligencia artificial para la detecci\u00f3n de COVID-19 a trav\u00e9s de la tos. Tras meses de entrenamiento al algoritmo a trav\u00e9s de 70 mil grabaciones de tos forzada que enviaron voluntarios a trav\u00e9s de dispositivos m\u00f3viles o plataformas web se complet\u00f3 el proceso. Para la recopilaci\u00f3n de datos, fueron importantes las alianzas del MIT con universidades y centros de estudio de todo el mundo, como fue la campa\u00f1a Tose con causa (https:\/\/www.toseconcausa.udg.mx), lanzada por la Universidad de Guadalajara en junio. Los investigadores del MIT descubrieron que las personas con una infecci\u00f3n asintom\u00e1tica por SARS-CoV-2 puede provocar cambios en la tos de las personas, por lo que la tos de una persona con infecci\u00f3n asintom\u00e1tica es diferente a la de una persona libre de infecci\u00f3n. Sin embargo, las diferencias entre ambas toses no son percibibles para el o\u00eddo humano, ante ello, la Inteligencia Artificial fue clave, para desarrollar un algoritmo confiable que pudiera comprobar la aseveraci\u00f3n. El algoritmo fue alimentado con decenas de miles de muestras de toses y tambi\u00e9n de palabras habladas. El algoritmo identific\u00f3 con una precisi\u00f3n del 98,5% las toses de las personas con caso confirmado de COVID-19, y 100% las toses de las personas asintom\u00e1ticas. El plan del MIT con esta innovaci\u00f3n es incorporar este modelo de IA, a una aplicaci\u00f3n f\u00e1cil de utilizar y buscar la aprobaci\u00f3n de la FDA (Food and Drug Administration), para ponerla a disposici\u00f3n de la poblaci\u00f3n de manera gratuita e identificar f\u00e1cilmente a personas asintom\u00e1ticas, y reducir los contagios. “La implementaci\u00f3n efectiva de esta herramienta de diagn\u00f3stico grupal podr\u00eda disminuir la propagaci\u00f3n de la pandemia si todos la usan antes de ir a un sal\u00f3n de clases, una f\u00e1brica o un restaurante”, mencion\u00f3 Brian Subirana, cient\u00edfico investigador catal\u00e1n miembro de Auto-ID Laboratory del MIT y desarrollador de este proyecto. Previo a la pandemia, los investigadores hab\u00edan trabajado en el entrenamiento de algoritmos que pudieran diagnosticar neumon\u00eda o asma a trav\u00e9s de grabaciones de tos mediante tel\u00e9fonos m\u00f3viles. Sobre la misma l\u00ednea el MIT, hab\u00eda desarrollado modelos de IA para el an\u00e1lisis de tos en b\u00fasqueda de signos de Alzheimer. \u201cLos sonidos de hablar y toser est\u00e1n influenciados por las cuerdas vocales y los \u00f3rganos circundantes. Esto significa que cuando habla, parte de su conversaci\u00f3n es como toser y viceversa. Tambi\u00e9n significa que las cosas que obtenemos f\u00e1cilmente del habla fluida, la IA puede captar simplemente de la tos, incluidas cosas como el g\u00e9nero de la persona, la lengua materna o incluso el estado emocional. De hecho, hay un sentimiento incrustado en la forma en que tose”, explic\u00f3 Subirana. Gracias a los estudios previos, comenzaron a probar este tipo de biomarcadores en COVID-19. Fue en abril cuando comenzaron a recopilar las grabaciones de voz, tanto de pacientes con COVID-19 confirmado, como de personas sanas. Las 70 mil grabaciones contienen varios tipos de tos, lo que equivale a cerca de 200 mil muestras de tos. Cerca de 2 mil 500 grabaciones correspondieron a personas que confirmaron tener COVID-19, incluidas las asintom\u00e1ticas. Los investigadores Jordi Laguarta y Ferran Hueto que acompa\u00f1an a Subirana, coincidieron en que existen similitudes entre la discriminaci\u00f3n de Alzheimer y COVID-19. Ya que no tuvieron que realizar muchos ajustes al modelo de IA que originalmente estaba construido para Alzheimer. Este modelo detecta patrones en cuatro biomarcadores: fuerza de las cuerdas vocales, sentimiento, rendimiento pulmonar y respiratorio y degradaci\u00f3n muscular. Los avances de su investigaci\u00f3n fueron publicados en IEEE Journal of Engineering in Medicine and Biology. Finalmente, los autores mencionan que “las pandemias podr\u00edan ser cosa del pasado si las herramientas de preselecci\u00f3n est\u00e1n siempre en segundo plano y se mejoran constantemente”. BIBLIOGRAF\u00cdA MIT https:\/\/news.mit.edu\/2020\/covid-19-cough-cellphone-detection-1029<\/p>","protected":false},"author":1,"featured_media":10915,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,154],"tags":[145],"class_list":["post-10914","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-comunidades-conectadas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/10914","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=10914"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/10914\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/10915"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=10914"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=10914"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=10914"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}