Étude et rapport

Prediction algorithm for ICU mortality and length of stay using machine learning

GRATUIT

Auteur(s) :

Shinya Iwase, Taka‐aki Nakada, Tadanaga Shimada, Takehiko Oami, Takashi Shimazui, Nozomi Takahashi, Jun Yamabe, Yasuo Yamao & Eiryo Kawakami

Éditeur(s) :

NATURE

Date de publication :28/07/2022

9 pages

EN BREF ...

"Machine learning can predict outcomes and determine variables contributing to precise prediction, and can thus classify patients with different risk factors of outcomes. This study aimed to investigate the predictive accuracy for mortality and length of stay in intensive care unit (ICU) patients using machine learning, and to identify the variables contributing to the precise prediction or classification of patients. Patients (n = 12,747) admitted to the ICU at Chiba University Hospital were randomly assigned to the training and test cohorts. After learning using the variables on admission in the training cohort, the area under the curve (AUC) was analyzed in the test cohort to evaluate the predictive accuracy of the supervised machine learning classifiers, including random forest (RF) for outcomes (primary outcome, mortality; secondary outcome, length of ICU stay)." En bref issu de l'étude.

Rédacteur(s) de la fiche : Beesens TEAM


Introductio

1 - In tincidunt nunc ac velit tristique

  • Pellentesque congue, magna elementum suscipit vestibulum
  • Aenean eleifend sodales ipsum vitae consequat
  • Quisque est leo tempus vel purus eu, placerat tincidunt nisl

2 - Sed lobortis elit vitae mollis consectetur

  • In tincidunt nunc ac velit tristique
  • Donec accumsan elit ac ornare eleifend
  • Sed pellentesque suscipit quam ut finibus
  • Fusce imperdiet neque sit amet ipsum ullamcorper scelerisque

3 - Lorem ipsum dolor sit amet

  • Pellentesque congue, magna elementum suscipit vestibulum
  • Aenean eleifend sodales ipsum vitae consequat
  • Quisque est leo tempus vel purus eu, placerat tincidunt nisl

Conclusio

Abonnements Beesens

Accéder à :

  • L'ensemble de la veille e-santé sélectionnée
    par la communauté Beesens,
  • Des documents de références de la e-santé,
  • Et bien plus encore...
JE M'INSCRIS GRATUITEMENT VOIR TOUS NOS ABONNEMENTS

Déjà inscrit ? Identifiez-vous

Également accessible aux abonnés PREMIUM