{"id":28332,"date":"2022-07-06T09:32:30","date_gmt":"2022-07-06T14:32:30","guid":{"rendered":"https:\/\/saluddigital.com\/?p=28332"},"modified":"2025-10-20T11:35:34","modified_gmt":"2025-10-20T17:35:34","slug":"estudio-muestra-nuevo-sistema-de-aprendizaje-automatico-que-genera-puntajes-de-riesgo-clinico","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/estudio-muestra-nuevo-sistema-de-aprendizaje-automatico-que-genera-puntajes-de-riesgo-clinico\/","title":{"rendered":"Study shows new machine learning system that generates clinical risk scores"},"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

Risk scores are used to make more informed clinical decisions, and machine learning implementation is helpful in identifying important predictors for scoring.<\/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

With risk scores, clinicians can make faster assessments of a patient's risk of achieving scores associated with key predictors of risk. On the other hand, machine learning improves these processes, by having tools with greater capacity for the selection of variables. A study published in PLOS Digital Health, made a connection between machine learning tools (AutoScore) and risk scoring tools (ShapleyVIC).<\/p>

For the study, the authors proposed a variable selection mechanism since connecting both tools directly could affect interpretability and predictive performance. The developed model is tailored to risk scores and was integrated into an automated framework for risk score development.<\/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

The study demonstrated how the proposed method can help researchers understand the 41 candidate variables for predicting outcomes. "We have presented a useful tool to support transparent high-risk decision-making," the study explains.<\/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

This investigation focused on premature death or unplanned readmission after hospital discharge. The variable selection method obtained 6 variables from 41 candidates to develop the risk score of an acceptable performance, this had a performance similar to that of a 16-variable model based on machine learning.<\/p>

\u201cOur work contributes to the recent emphasis on the interpretability of prediction models for high-risk decision making, providing a disciplined solution for the detailed assessment of variable importance and the transparent development of parsimonious clinical risk scores,\u201d explains Dr. Article.<\/p>

One of the models used for the study, AutoScore, has been tested in various settings such as to derive risk scores in emergency department triage, as well as to provide scores on survival after out-of-hospital cardiac arrest.<\/p>

See more details about both models and their results by reading the full study at the following link:<\/p>

https:\/\/journals.plos.org\/digitalhealth\/article?id=10.1371\/journal.pdig.0000062<\/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

PLOS DIGITAL HEALTH<\/strong><\/p>

https:\/\/journals.plos.org\/digitalhealth\/article?id=10.1371\/journal.pdig.0000062<\/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":"

Los puntajes de riesgo se utilizan para tomar decisiones cl\u00ednicas con mayor informaci\u00f3n, adem\u00e1s la implementaci\u00f3n de aprendizaje autom\u00e1tico es \u00fatil para la identificaci\u00f3n de predictores importantes para la creaci\u00f3n de puntajes. Gracias a las puntuaciones de riesgo, los m\u00e9dicos pueden realizar evaluaciones m\u00e1s r\u00e1pidas sobre el riesgo de un paciente de alcanzar puntajes asociados con predictores claves de riesgo. Por otro lado, el aprendizaje autom\u00e1tico mejora estos procesos, al contar con herramientas con mayor capacidad para la selecci\u00f3n de variables. Un estudio publicado en PLOS Digital Health, realiz\u00f3 una conexi\u00f3n entre herramientas de aprendizaje autom\u00e1tico (AutoScore) y las herramientas de puntuaci\u00f3n de riesgo (ShapleyVIC). Para el estudio, los autores propusieron un mecanismo de selecci\u00f3n de variables ya que conectar ambas herramientas de manera directa podr\u00eda afectar la interpretabilidad y el rendimiento predictivo. El modelo desarrollado se adapta a puntajes de riesgo y fue integrado a un marco automatizado para el desarrollo del puntaje de riesgo. El estudio demostr\u00f3 como el m\u00e9todo propuesto puede ayudar a que investigadores comprendan las 41 variables candidatas a la predicci\u00f3n de resultados. \u201cHemos presentado una herramienta \u00fatil para apoyar la toma transparente de decisiones de alto riesgo\u201d, explica el estudio. Esta investigaci\u00f3n se enfoc\u00f3 en la muerte prematura o readmisi\u00f3n no planificada despu\u00e9s del alta hospitalaria. El de selecci\u00f3n de variables, obtuvo 6 variables de 41 candidatos para desarrollar la puntuaci\u00f3n de riesgo de un rendimiento aceptable, este tuvo un rendimiento similar al de un modelo de 16 variables basado en aprendizaje autom\u00e1tico. \u201cNuestro trabajo contribuye al \u00e9nfasis reciente en la interpretabilidad de los modelos de predicci\u00f3n para la toma de decisiones de alto riesgo, proporcionando una soluci\u00f3n disciplinada para la evaluaci\u00f3n detallada de la importancia variable y el desarrollo transparente de puntuaciones de riesgo cl\u00ednico parsimoniosas\u201d, explica el art\u00edculo. Uno de los modelos utilizados para el estudio, AutoScore, ha sido probado en diversos entornos como para derivar puntuaciones de riesgo en triaje en servicio de urgencias, as\u00ed como para proporcionar puntuaciones en supervivencia luego de un paro card\u00edaco extrahospitalarios. Consulta m\u00e1s detalles sobre ambos modelos y sus resultados leyendo el estudio completo en el siguiente enlace: https:\/\/journals.plos.org\/digitalhealth\/article?id=10.1371\/journal.pdig.0000062 BIBLIOGRAF\u00cdA PLOS DIGITAL HEALTH https:\/\/journals.plos.org\/digitalhealth\/article?id=10.1371\/journal.pdig.0000062<\/p>","protected":false},"author":1,"featured_media":28333,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3400,160],"tags":[145],"class_list":["post-28332","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-diagnostico","category-noticias","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/28332","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=28332"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/28332\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/28333"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=28332"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=28332"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=28332"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}