{"id":24787,"date":"2022-04-12T09:55:06","date_gmt":"2022-04-12T14:55:06","guid":{"rendered":"https:\/\/saluddigital.com\/?p=24787"},"modified":"2025-10-21T09:54:48","modified_gmt":"2025-10-21T15:54:48","slug":"universidad-de-florida-participa-en-el-desarrollo-del-generador-de-lenguaje-clinico-mas-grande-del-mundo","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/universidad-de-florida-participa-en-el-desarrollo-del-generador-de-lenguaje-clinico-mas-grande-del-mundo\/","title":{"rendered":"University of Florida participates in the development of the largest clinical language generator in the world"},"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

The University of Florida Academic Health Center (UF Health) is collaborating with NVIDIA to create the world's largest natural network of synthetic clinical data.<\/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

In a partnership with NVIDIA, UF Health is developing a neural network for the generation of synthetic clinical data, an important advance for training AI models in health. This language model, called SynGatorTron, is capable of creating synthetic patient profiles using health record data.<\/p>

This model has been entered with data that represents information from more than 2 million patients, thus it has more than 5 billion parameters, which makes it the largest clinical language generator in the world.<\/p>

\u201cThe synthetic data is not actually linked to a real human being, but has characteristics similar to those of real patients. SynGatorTron can, for example, create digital diabetes patient health records that have characteristics like a real population,\u201d explained Duane Mitchell, assistant vice president for research and director of the UF Institute for Clinical and Translational Sciences.<\/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

This model will facilitate the creation of AI models (machine and deep learning), algorithms, and other tools, since the use of synthetic data eliminates privacy problems with patients. Likewise, it facilitates collaboration between research and health institutions and promotes the use of this type of data to address specific health problems, such as unconventional diseases.<\/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

\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\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

\u201cThe synthesis of different types of clinical records will democratize the ability to build all kinds of applications that rely on such data by addressing data scarcity and privacy,\u201d said Mona Flores, global director of medical AI at NVIDIA.<\/p>

Similarly, SynGatorTron also solves certain problems of underrepresentation, by generating specific data on population groups, disease characteristics and more. "When you have the ability to mimic population characteristics without being tied to real patients, it opens the imagination to see if we can generate realistic data sets that allow us to answer questions that we might not otherwise be able to, due to restrictions on access." to data or limited access, information about patients of interest,\u201d Mitchell said.<\/p>

Other applications of this solution include clinical trials, development of deep learning models to discover the effects of a drug and its effects on population groups.<\/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\t BIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

AI MEAS<\/strong><\/p>

https:\/\/ai-med.io\/more-news\/uf-health-and-nvidia-build-worlds-largest-clinical-language-generator\/<\/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":"

El Centro Acad\u00e9mico de Salud de la Universidad de Florida (UF Health), se encuentra colaborando con NVIDIA para la creaci\u00f3n de la red natural de datos cl\u00ednicos sint\u00e9ticos m\u00e1s grande del mundo. En una asociaci\u00f3n con NVIDIA, UF Health, se encuentra desarrollando una red neuronal para la generaci\u00f3n de datos cl\u00ednicos sint\u00e9ticos, un avance importante para el entrenamiento de modelos de IA en salud. Este modelo de lenguaje llamado SynGatorTron, es capaz de crear perfiles de pacientes sint\u00e9ticos a trav\u00e9s de datos de registros de salud. Este modelo ha sido entrado con datos que representan informaci\u00f3n de m\u00e1s de 2 millones de pacientes, de esta forma cuenta con m\u00e1s de 5 mil millones de par\u00e1metros, lo que lo convierte en el generador de lenguaje cl\u00ednico m\u00e1s grande del mundo. \u201cLos datos sint\u00e9ticos en realidad no est\u00e1n vinculados a un ser humano real, pero tienen caracter\u00edsticas similares a las de los pacientes reales. SynGatorTron puede, por ejemplo, crear registros de salud de pacientes con diabetes digitales que tienen caracter\u00edsticas como una poblaci\u00f3n real\u201d, explic\u00f3 Duane Mitchell, vicepresidenta asistente de investigaci\u00f3n y directora del Instituto de Ciencias Cl\u00ednicas y Traslacionales de la UF. Este modelo facilitar\u00e1 la creaci\u00f3n de modelos de IA (aprendizaje autom\u00e1tico y profundo), algoritmos, y otras herramientas, ya que la utilizaci\u00f3n de datos sint\u00e9ticos elimina los problemas de privacidad con los pacientes. Asimismo, facilita la colaboraci\u00f3n entre instituciones de investigaci\u00f3n y de salud y promueve la utilizaci\u00f3n de este tipo de datos para atender problemas espec\u00edficos de salud, como enfermedades no convencionales. \u201cLa s\u00edntesis de diferentes tipos de registros cl\u00ednicos democratizar\u00e1 la capacidad de crear todo tipo de aplicaciones que dependan de dichos datos al abordar la escasez de datos y la privacidad\u201d, explic\u00f3 Mona Flores, directora global de IA m\u00e9dica de NVIDIA. De igual forma, SynGatorTron, tambi\u00e9n resuelve ciertos problemas de subrepresentaci\u00f3n, al generar datos espec\u00edficos sobre grupos de poblaci\u00f3n, caracter\u00edsticas de enfermedades y m\u00e1s. \u201cCuando tienes la capacidad de imitar las caracter\u00edsticas de la poblaci\u00f3n sin estar atado a pacientes reales, se abre la imaginaci\u00f3n para ver si podemos generar conjuntos de datos realistas que nos permitan responder preguntas que de otro modo no podr\u00edamos, debido a restricciones en el acceso a los datos o acceso limitado, informaci\u00f3n sobre pacientes de inter\u00e9s\u201d, dijo Mitchell. Otras aplicaciones de esta soluci\u00f3n incluyen ensayos cl\u00ednicos, desarrollo de modelos de aprendizaje profundo para conocer efectos de un medicamento y sus efectos en grupos de poblaci\u00f3n. BIBLIOGRAF\u00cdA AI MED https:\/\/ai-med.io\/more-news\/uf-health-and-nvidia-build-worlds-largest-clinical-language-generator\/<\/p>","protected":false},"author":1,"featured_media":24789,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3393,160],"tags":[145],"class_list":["post-24787","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-inteligencia-artificial-y-ciencia","category-noticias","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/24787","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=24787"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/24787\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/24789"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=24787"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=24787"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=24787"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}