{"id":28107,"date":"2022-06-27T09:50:32","date_gmt":"2022-06-27T14:50:32","guid":{"rendered":"https:\/\/saluddigital.com\/?p=28107"},"modified":"2025-10-20T11:44:13","modified_gmt":"2025-10-20T17:44:13","slug":"cientificos-desarrollan-modelo-para-entrenar-inteligencia-artificial-a-traves-de-conversaciones-medicas","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/cientificos-desarrollan-modelo-para-entrenar-inteligencia-artificial-a-traves-de-conversaciones-medicas\/","title":{"rendered":"Scientists develop model to train Artificial Intelligence through medical conversations"},"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

Artificial Intelligence (AI), requires training for its application, especially in the medical field, conducting simulated interviews and natural language processing (NLP), is useful for this task.<\/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

Researchers published an article in Scientific Data<\/em> of Nature<\/em>, detailing the creation of datasets<\/em> for AI training through medical conversations with an Objective Structured Clinical Examinations (OSCE) format. The investigation focused on respiratory cases and its objective was to provide a complete set of data o data set<\/em> on medical talks to the medical research community.<\/p>

There are generally limitations in the research and application of AI using data from medical conversations, as these require training that can interfere with patient privacy and data sharing regulations.<\/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

In this way, the authors of the article mentioned above developed a method for simulating medical conversations that is used to train AI applied to health. For this, a team of residents in internal medicine, physical medicine, anatomical pathology, and family medicine, as well as medical students, created this data set simulating medical interviews using the OSCE format.<\/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

The interviews were recorded and transcribed. More than 272 simulated conversations between doctors and patients were recorded and categorized into categories, however, most of them were simulated cases of respiratory cases.<\/p>

Interview transcripts are useful for training various NLP models, for measuring the accuracy of transcription tools, among other uses. In this sense, the dataset presented by this research was able to correct common errors in the transcription of medical conversations, in the audio recording, making it useful and applicable to train any PLN model.<\/p>

\u201cMore importantly, access to data of this caliber is a significant challenge for many researchers due to the sensitive nature of the data, government regulations that limit data sharing in research, and the question of monetization. of the data. Therefore, the presented dataset of complete medical conversations in audio and text format is a valuable asset for academia and the medical industry,\u201d the authors explain.<\/p>

However, one of the main limitations of this dataset is the small number of simulated cases of non-respiratory diseases. In fact, of the 272 simulated conversations, 214 corresponded to respiratory cases and the rest to cardiac, dermatological, gastrointestinal and musculoskeletal cases.<\/p>

You can read the study in detail at the following link: https:\/\/www.nature.com\/articles\/s41597-022-01423-1<\/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

\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

NATURE<\/strong><\/p>

https:\/\/www.nature.com\/articles\/s41597-022-01423-1<\/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":"

La Inteligencia Artificial (IA), requiere entrenamiento para su aplicaci\u00f3n, especialmente en el campo m\u00e9dico, la realizaci\u00f3n de entrevistas simuladas y el procesamiento de lenguaje natural (PLN), es \u00fatil para esta tarea. Investigadores publicaron un art\u00edculo en Scientific Data de Nature, que detalla la creaci\u00f3n de datasets para el entrenamiento de IA a trav\u00e9s de conversaciones m\u00e9dicas con un formato de Ex\u00e1menes Cl\u00ednico Estructurados Objetivos (OSCE, en ingl\u00e9s). La investigaci\u00f3n se enfoc\u00f3 en casos respiratorios y su objetivo fue proporcionar un conjunto completo de datos o dataset sobre conversaciones m\u00e9dicas a la comunidad de la investigaci\u00f3n m\u00e9dica. Generalmente existen limitaciones en la investigaci\u00f3n y aplicaci\u00f3n de IA utilizando datos de conversaciones m\u00e9dicas, ya que estas requieren entrenamiento que puede interferir con la privacidad del paciente y regulaciones sobre el intercambio de datos. De esta forma, los autores del art\u00edculo mencionado anteriormente, desarrollaron un m\u00e9todo para la simulaci\u00f3n de conversaciones m\u00e9dicas que sirve para entrenar IA aplicada en salud. Para ello un equipo de residentes en medicina interna, medicina f\u00edsica, patolog\u00eda anat\u00f3mica, y medicina familiar, as\u00ed como estudiantes de medicina, crearon este conjunto de datos simulando entrevistas m\u00e9dicas utilizando el formato OSCE. Las entrevistas fueron grabadas y transcritas. M\u00e1s de 272 conversaciones simuladas entre m\u00e9dicos y pacientes fueron registradas y categorizadas en categor\u00edas, sin embargo, la mayor parte de ellas fueron casos simulados de casos respiratorios. Las transcripciones de las entrevistas son \u00fatiles para entrenar diversos modelos de PLN, para medir la precisi\u00f3n de las herramientas de transcripci\u00f3n, entre otros usos. En este sentido, el dataset presentado por esta investigaci\u00f3n pudo corregir errores usuales en la transcripci\u00f3n de conversaciones m\u00e9dicas, en la grabaci\u00f3n de audio, volvi\u00e9ndolo \u00fatil y aplicable para entrenar cualquier modelo de PLN. \u201cY lo que es m\u00e1s importante, el acceso a datos de este calibre es un reto importante para muchos investigadores debido a la naturaleza confidencial de los datos, a las regulaciones gubernamentales que limitan el intercambio de datos en la investigaci\u00f3n y a la cuesti\u00f3n de la monetizaci\u00f3n de los datos. Por lo tanto, el conjunto de datos presentado de conversaciones m\u00e9dicas completas en formato de audio y texto es un activo valioso para el mundo acad\u00e9mico y la industria m\u00e9dica\u201d, explican los autores. Sin embargo, una de las principales limitaciones de este dataset es la reducida cantidad de casos simulados de enfermedades no respiratorias. De hecho, de las 272 conversaciones simuladas, 214 correspondieron a casos respiratorios y el resto a casos cardiacos, dermatol\u00f3gicos, gastrointestinales y musculoesquel\u00e9ticos. Puedes leer el estudio a detalle en el siguiente enlace: https:\/\/www.nature.com\/articles\/s41597-022-01423-1 BIBLIOGRAF\u00cdA NATURE https:\/\/www.nature.com\/articles\/s41597-022-01423-1<\/p>","protected":false},"author":1,"featured_media":28108,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3399,156,160],"tags":[145],"class_list":["post-28107","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-analitica","category-big-data","category-noticias","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/28107","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=28107"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/28107\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/28108"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=28107"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=28107"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=28107"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}