Gaussian process classification for prediction of in-hospital mortality among preterm infants

We present a method for predicting preterm infant in-hospital mortality using Bayesian Gaussian process classification. We combined features extracted from sensor measurements, made during the first 72 h of care for 598 Very Low Birth Weight infants of birth weight  

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2018-07, Vol.298, p.134-141
Main Authors: Rinta-Koski, Olli-Pekka, Särkkä, Simo, Hollmén, Jaakko, Leskinen, Markus, Andersson, Sture
Format: Article
Language:English
Subjects:
Gaussian process classification
Neonatal intensive care
Time series prediction
Very low birth weight infants
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a method for predicting preterm infant in-hospital mortality using Bayesian Gaussian process classification. We combined features extracted from sensor measurements, made during the first 72 h of care for 598 Very Low Birth Weight infants of birth weight  
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2017.12.064