Machine learning-based prognostic model to predict criticality in patients - Evidencio
Machine learning-based prognostic model to predict criticality in patients with severe Covid-19 infection
Prediction of criticality in patients with severe Covid-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan
Autores de la investigación: Yan L, Zhang H, Xiao Y, Wang M, Guo Y, Sun C, Tang X, Jing L, Li S, Zhang M, Xiao Y, Cao H, Chen Y, Ren T, Jin J, Wang F, Xiao Y, Huang S, Tan X, Huang N, Jiao B, Zhang Y, Luo A, Cao Z, Xu H, Yuan Y
Versión: 1.10
  • Público
  • Enfermedades infecciosas
  • {{ modelType }}
  • Detalles
  • Validar algoritme
  • Guardar entrada
  • Entrada de carga
Mostrar
Unidades

{{ section.title }}

{{ section.description }}

Calcular el resultado

Establezca más parámetros para realizar el cálculo

Predicted probability of mortality: %

{{ resultSubheader }}
{{ $t('download_result_availability') }}
{{ chart.title }}
Intervalo de resultados {{ additionalResult.min }} a {{ additionalResult.max }}

Información condicional

Yan et al. developed a machine learning-based a decision rule using three key features: LDH, hsCRP, and lymphocyte percentage. 

Context information on risk factors: 
The increase of LDH reflects tissue/cell destruction and is regarded as a common sign of tissue/cell damage. Serum LDH has been identified as an important biomarker for the activity and severity of Idiopathic Pulmonary Fibrosis (IPF). In patients with severe pulmonary interstitial disease, the increase of LDH is significant and is one of the most important prognostic markers of lung injury. For the critically ill patients with COVID-19, the rise of LDH level indicates an increase of the activity and extent of lung injury.

The analysis performed by Yan et al, showed that higher serum hs-CRP could be used to predict the risk of death in severe COVID-19 patients. The increase of hs-CRP, an important marker for poor prognosis in ARDS, reflects the persistent state of inflammation.

Previous results suggest that lymphocytes play vital role in forecasting of progression from mild to critically ill and may serve as a potential therapeutic target. The hypothesis is supported by the results of clinical studies. Moreover, lymphopenia is a common feature in the patients with COVID-19 and might be a critical factor associated with disease severity and mortality.

Study limitations: 
First of all, since the proposed machine learning method is purely data driven, its model may vary given a different set of training and validation dataset. Given the limit number of samples in this study, a balance between model complexity and performance was sought. Yet the whole procedure should follow when more data is available.
Secondly, the performed study was a single-centered, retrospective study, which provides a preliminary assessment of the clinical course and outcome of severe patients.

Source: 
Yan et al. Prediction of criticality in patients with severe Covid-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan. (Preprint). 

{{ file.classification }}
PRO
Nota
Las notas sólo son visibles en la descarga de resultados y no serán guardadas por Evidencio

Este algoritme se proporciona con fines educativos, formativos e informativos. No debe utilizarse para apoyar la toma de decisiones médicas ni para prestar servicios médicos o de diagnóstico. Lea nuestro disclaimer.

Algoritmer subyacentes Parte de
Comentarios
Comentario
Escriba un comentario
Los comentarios son visibles para cualquiera

Comentarios sobre el algoritme

Aún no hay comentarios 1 comentario {{ model.comments.length }} Comentarios
En {{ comment.created_at }} {{ comment.user.username }} un autor ya no registrado escribió:
{{ comment.content }}
logo

Inicia sesión para activar las funciones de impresión de Evidencio

Para poder utilizar las funciones de impresión de Evidencio, debe estar conectado.
Si no tiene una cuenta de la Comunidad Evidencio puede crear su cuenta personal gratuita en:

https://www.evidencio.com/registration

Resultados impresos - Ejemplos {{ new Date().toLocaleString() }}

Beneficios de la Cuenta Comunitaria Evidencio

With an Evidencio Community account you can:

  • Create and publish your own prediction algorithms.
  • Share your prediction algorithms with your colleagues, research group, organization or the world.
  • Review and provide feedback on algorithms that have been shared with you.
  • Validate your algorithms and validate algorithms from other users.
  • Find algorithms based on Title, Keyword, Author, Institute, or MeSH classification.
  • Use and save prediction algorithms and their data.
  • Use patient specific protocols and guidelines based on sequential algorithms and decision trees.
  • Stay up-to-date with new algorithms in your field as they are published.
  • Create your own lists of favorite algorithms and topics.

A personal Evidencio account is free, with no strings attached!
Join us and help create clarity, transparency, and efficiency in the creation, validation, and use of medical prediction algorithms.

Descargo de responsabilidad: Los cálculos por sí solos nunca deben dictar la atención al paciente, y no sustituyen al juicio profesional.
Términos y Condiciones | Política de privacidad | Descargo de responsabilidad | Contacto | Rechazar cookies |
Evidencio v3.38 © 2015 - 2025 Evidencio. Todos los derechos reservados