Hybridized neural networks for non-invasive and continuous mortality risk assessment in neonates

Baker, Stephanie, Xiang, Wei, and Atkinson, Ian (2021) Hybridized neural networks for non-invasive and continuous mortality risk assessment in neonates. Computers in Biology and Medicine, 134. 104521.

PDF (Published Version) - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (3MB) | Preview
View at Publisher Website: https://doi.org/10.1016/j.compbiomed.202...


Premature birth is the primary risk factor in neonatal deaths, with the majority of extremely premature babies cared for in neonatal intensive care units (NICUs). Mortality risk prediction in this setting can greatly improve patient outcomes and resource utilization. However, existing schemes often require laborious medical testing and calculation, and are typically only calculated once at admission. In this work, we propose a shallow hybrid neural network for the prediction of mortality risk in 3-day, 7-day, and 14-day risk windows using only birthweight, gestational age, sex, and heart rate (HR) and respiratory rate (RR) information from a 12-h window. As such, this scheme is capable of continuously updating mortality risk assessment, enabling analysis of health trends and responses to treatment. The highest performing scheme was the network that considered mortality risk within 3 days, with this scheme outperforming state-of-the-art works in the literature and achieving an area under the receiver-operator curve (AUROC) of 0.9336 with standard deviation of 0.0337 across 5 folds of cross-validation. As such, we conclude that our proposed scheme could readily be used for continuously-updating mortality risk prediction in NICU environments.

Item ID: 68570
Item Type: Article (Research - C1)
ISSN: 1879-0534
Keywords: Machine learning; Neural networks; Neonatal mortality; Mortality risk prediction; Prognostics; Intensive care
Related URLs:
Copyright Information: © 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license
Funders: Australian Government Research Training Program Scholarship
Date Deposited: 13 Jul 2021 01:56
FoR Codes: 42 HEALTH SCIENCES > 4203 Health services and systems > 420308 Health informatics and information systems @ 100%
SEO Codes: 20 HEALTH > 2001 Clinical health > 200101 Diagnosis of human diseases and conditions @ 50%
20 HEALTH > 2005 Specific population health (excl. Indigenous health) > 200506 Neonatal and child health @ 50%
Downloads: Total: 870
Last 12 Months: 82
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page