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

Research output: Contribution to journalArticleScientificpeer-review

Researchers

Research units

  • University of Helsinki

Abstract

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 < 1500 g, with standard clinical features calculated on arrival at the Neonatal Intensive Care Unit. Time periods of 12, 18, 24, 36, 48, and 72 h were evaluated. We achieved a classification result with area under the receiver operating characteristic curve of 0.948, which is in excess of the results achieved by using the clinical standard SNAP-II and SNAPPE-II scores.

Details

Original languageEnglish
Pages (from-to)134-141
JournalNeurocomputing
Volume298
Publication statusPublished - 2018
MoE publication typeA1 Journal article-refereed

    Research areas

  • Gaussian process classification, Neonatal intensive care, Time series prediction, Very low birth weight infants

ID: 18203394