Prediction of short-term health outcomes in preterm neonates from heart-rate variability and blood pressure using boosted decision trees.
Boosted decision tree
HRV
Hypotension
Outcome prediction
Journal
Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513
Informations de publication
Date de publication:
Oct 2019
Oct 2019
Historique:
received:
01
04
2019
revised:
11
07
2019
accepted:
25
07
2019
pubmed:
20
8
2019
medline:
18
3
2020
entrez:
18
8
2019
Statut:
ppublish
Résumé
Efficient management of low blood pressure (BP) in preterm neonates remains challenging with considerable variability in clinical practice. There is currently no clear consensus on what constitutes a limit for low BP that is a risk to the preterm brain. It is argued that a personalised approach rather than a population based threshold is more appropriate. This work aims to assist healthcare professionals in assessing preterm wellbeing during episodes of low BP in order to decide when and whether hypotension treatment should be initiated. In particular, the study investigates the relationship between heart rate variability (HRV) and BP in preterm infants and its relevance to a short-term health outcome. The study is performed on a large clinically collected dataset of 831 h from 23 preterm infants of less than 32 weeks gestational age. The statistical predictive power of common HRV features is first assessed with respect to the outcome. A decision support system, based on boosted decision trees (XGboost), was developed to continuously estimate the probability of neonatal morbidity based on the feature vector of HRV characteristics and the mean arterial blood pressure. It is shown that the predictive power of the extracted features improves when observed during episodes of hypotension. A single best HRV feature achieves an AUC of 0.87. Combining multiple HRV features extracted during hypotensive episodes with the classifier achieves an AUC of 0.97, using a leave-one-patient-out performance assessment. Finally it is shown that good performance can even be achieved using continuous HRV recordings, rather than only focusing on hypotensive events - this had the benefit of not requiring invasive BP monitoring. The work presents a promising step towards the use of multimodal data in providing objective decision support for the prediction of short-term outcome in preterm infants with hypotensive episodes.
Sections du résumé
BACKGROUND AND OBJECTIVE
OBJECTIVE
Efficient management of low blood pressure (BP) in preterm neonates remains challenging with considerable variability in clinical practice. There is currently no clear consensus on what constitutes a limit for low BP that is a risk to the preterm brain. It is argued that a personalised approach rather than a population based threshold is more appropriate. This work aims to assist healthcare professionals in assessing preterm wellbeing during episodes of low BP in order to decide when and whether hypotension treatment should be initiated. In particular, the study investigates the relationship between heart rate variability (HRV) and BP in preterm infants and its relevance to a short-term health outcome.
METHODS
METHODS
The study is performed on a large clinically collected dataset of 831 h from 23 preterm infants of less than 32 weeks gestational age. The statistical predictive power of common HRV features is first assessed with respect to the outcome. A decision support system, based on boosted decision trees (XGboost), was developed to continuously estimate the probability of neonatal morbidity based on the feature vector of HRV characteristics and the mean arterial blood pressure.
RESULTS
RESULTS
It is shown that the predictive power of the extracted features improves when observed during episodes of hypotension. A single best HRV feature achieves an AUC of 0.87. Combining multiple HRV features extracted during hypotensive episodes with the classifier achieves an AUC of 0.97, using a leave-one-patient-out performance assessment. Finally it is shown that good performance can even be achieved using continuous HRV recordings, rather than only focusing on hypotensive events - this had the benefit of not requiring invasive BP monitoring.
CONCLUSIONS
CONCLUSIONS
The work presents a promising step towards the use of multimodal data in providing objective decision support for the prediction of short-term outcome in preterm infants with hypotensive episodes.
Identifiants
pubmed: 31421605
pii: S0169-2607(19)30435-3
doi: 10.1016/j.cmpb.2019.104996
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
104996Informations de copyright
Copyright © 2019. Published by Elsevier B.V.