{"id":29016,"date":"2022-07-20T08:47:30","date_gmt":"2022-07-20T13:47:30","guid":{"rendered":"https:\/\/saluddigital.com\/?p=29016"},"modified":"2025-10-20T11:31:51","modified_gmt":"2025-10-20T17:31:51","slug":"investigadores-utilizan-aprendizaje-automatico-para-optimizar-el-flujo-de-trabajo-en-admisiones-al-hospital-por-covid-19","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/investigadores-utilizan-aprendizaje-automatico-para-optimizar-el-flujo-de-trabajo-en-admisiones-al-hospital-por-covid-19\/","title":{"rendered":"Researchers use machine learning to optimize workflow in hospital admissions by. COVID-19."},"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 the Johns Hopkins University School of Medicine implemented a machine learning system to optimize hospital admission decisions for 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

The high demand for medical care during the pandemic affected emergency departments in the United States, which continued their work of distinguishing patients who need hospital care and those who can be discharged safely. In this way they had to incorporate new variables to identify patients with COVID-19. To this end, Johns Hopkins researchers presented a study<\/a>, where they show the development, implementation and evaluation of an integrated clinical decision support system through electronic health records (EHR, in English).<\/p>

This system uses data from EHR and machine learning to estimate the short-term risk of clinical deterioration in patients with confirmed or suspected cases of COVID-19. In this way, the system can determine the risk and need for critical care within 24 hours, as well as the specific care needs of hospitalized patients within 72 hours.<\/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

\u201cModel performance and numerous patient-oriented outcomes, including in-hospital mortality, were measured across the study periods. The incidence of critical care needs within 24 h and hospital care needs within 72 h were 10.7 % and 22.5 %, respectively, and were similar in all study periods\u201d, explains the study.<\/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

For its part, the machine learning model had a remarkable performance in all conditions since it obtained an AUC range from 0.85 to 0.91 in the prediction of critical care needs and from 0.80 to 0.90 for critical care needs. of hospital care.<\/p>

However, total mortality remained unchanged during the study period, but achieved a reduction among high-risk patients after implementing the clinical decision support model.<\/p>

The models were trained with 39 different predictor variables, such as shortness of breath, lactate levels, history of kidney disease, hypotension, among others.<\/p>

\u201cOur models also provide information that may inform clinical practice and the interpretation of similar models in the future. Diabetes, chronic lung disease, cardiovascular disease, and hypertension have been identified as important risk factors for severe illness and mortality from COVID-19, although these comorbidities were not among the most important predictors for any of our models." explains the study.<\/p>

In these variables and other demographic variables, age and sex, had little weight in the models. However, despite seeming contradictory, in acute care settings the physiological variables and manifestations of the disease were more important in the clinical course than epidemiological risk factors.<\/p>

Learn more about this study and its results at the following link:<\/p>

https:\/\/www.nature.com\/articles\/s41746-022-00646-1<\/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\/s41746-022-00646-1<\/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":"

Investigadores de la Facultad de Medicina de la Universidad Johns Hopkins implementaron un sistema de aprendizaje autom\u00e1tico para optimizar las decisiones de admisi\u00f3n hospitalaria por COVID-19. La gran demanda de atenci\u00f3n m\u00e9dica durante la pandemia, afect\u00f3 a los departamentos de emergencia en Estados Unidos, que continuaron su labor de distinguir pacientes que necesitan atenci\u00f3n hospitalaria y aquellos que pueden recibir el alta m\u00e9dica de manera segura. De esta forma tuvieron que incorporar nuevas variables para identificar pacientes con COVID-19. Para ello investigadores de Johns Hopkins presentaron un estudio, donde muestran el desarrollo, implementaci\u00f3n y evaluaci\u00f3n de un sistema integrado de soporte de decisiones cl\u00ednica por medio de registros de salud electr\u00f3nicos (EHR, en ingl\u00e9s). Este sistema utiliza los datos de EHR y aprendizaje autom\u00e1tico, para estimar el riesgo a corto plazo del deterioro cl\u00ednico en pacientes con casos de COVID-19 confirmados o sospechosos. De esta forma el sistema puede determinar el riesgo y necesidad de atenci\u00f3n cr\u00edtica en las 24 horas posteriores, as\u00ed como las necesidades de atenci\u00f3n especificas en pacientes hospitalizados dentro de 72 horas. \u201cEl rendimiento del modelo y numerosos resultados orientados al paciente, incluida la mortalidad hospitalaria, se midieron a lo largo de los per\u00edodos de estudio. La incidencia de necesidades de atenci\u00f3n cr\u00edtica dentro de las 24 h y las necesidades de atenci\u00f3n hospitalaria dentro de las 72 h fueron del 10,7 % y el 22,5 %, respectivamente, y fueron similares en todos los per\u00edodos de estudio\u201d, explica el estudio. Por su parte el modelo de aprendizaje autom\u00e1tico tuvo un rendimiento destacable en todas las condiciones ya que obtuvo un rango de AUC de 0,85 a 0,91 en la predicci\u00f3n de necesidades de atenci\u00f3n cr\u00edtica y de 0,80 a 0,90 para necesidades de atenci\u00f3n hospitalaria. Sin embargo, la mortalidad total se mantuvo sin cambios durante el periodo de estudio, pero logr\u00f3 una reducci\u00f3n entre pacientes de alto riesgo luego de implementar el modelo de soporte de decisiones cl\u00ednicas. Los modelos fueron entrenados con 39 variables de predicci\u00f3n distintas, como a la dificultad para respirar, niveles de lactato, antecedentes de enfermedad renal, hipotensi\u00f3n, entre otras. \u201cNuestros modelos tambi\u00e9n brindan informaci\u00f3n que puede informar la pr\u00e1ctica cl\u00ednica y la interpretaci\u00f3n de modelos similares en el futuro. La diabetes, la enfermedad pulmonar cr\u00f3nica, la enfermedad cardiovascular y la hipertensi\u00f3n se han identificado como factores de riesgo importantes de enfermedad grave y mortalidad por COVID-19, aunque estas comorbilidades no se encontraban entre los predictores m\u00e1s importantes para ninguno de nuestros modelos\u201d, explica el estudio. En estas variables y otras variables demogr\u00e1ficas, edad y sexo, tuvieron poco peso en los modelos. No obstante, a pesar de parecer contradictorio, en entornos de atenci\u00f3n aguda las variables y manifestaciones fisiol\u00f3gicas de la enfermedad fueron m\u00e1s importantes en la trayectoria cl\u00ednica que factores de riesgo epidemiol\u00f3gicos. Conoce m\u00e1s sobre este estudio y sus resultados en el siguiente enlace: https:\/\/www.nature.com\/articles\/s41746-022-00646-1 BIBLIOGRAF\u00cdA NATURE https:\/\/www.nature.com\/articles\/s41746-022-00646-1<\/p>","protected":false},"author":1,"featured_media":29018,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3400,160,1418],"tags":[145],"class_list":["post-29016","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-diagnostico","category-noticias","category-resena-de-publicaciones-cientificas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/29016","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=29016"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/29016\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/29018"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=29016"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=29016"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=29016"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}