Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring

Aleksandar Jeremic, Kenneth Tan

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Although heart rate is commonly measured in various clinical settings the advanced algorithms for its prediction are rarely implemented in clinical settings and patient management. In neonatal intensive care timely prediction of dangerous levels of heart rate can lead to improved care, positive long-term effects and reduced morbidity. Successful development and implementation of time series prediction algorithms is often based on selection of adequate signal processing models. In practical applications this issue is addressed almost invariably using statistical hypothesis testing. In this paper we propose preliminary model selection algorithm based on Bayesian approach leading to calculation of posterior odds ratios. We evaluate the applicability of the proposed method using a real data set containing over 180 pre-term infants whose heart rates were recorded over the length of their stay in the Neonatal Intensive Care Unit (NICU).

Original languageEnglish
Title of host publicationProceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011
Pages406-410
Number of pages5
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011 - Innsbruck, Austria
Duration: 14 Feb 201116 Feb 2011

Conference

Conference31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011
CountryAustria
CityInnsbruck
Period14/02/1116/02/11

Keywords

  • Bayesian model selection
  • Neonatal heart rate monitoring

Cite this

Jeremic, A., & Tan, K. (2011). Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring. In Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011 (pp. 406-410) https://doi.org/10.2316/P.2011.718-104
Jeremic, Aleksandar ; Tan, Kenneth. / Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring. Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011. 2011. pp. 406-410
@inproceedings{0f02f59750524565863e7d5910db70aa,
title = "Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring",
abstract = "Although heart rate is commonly measured in various clinical settings the advanced algorithms for its prediction are rarely implemented in clinical settings and patient management. In neonatal intensive care timely prediction of dangerous levels of heart rate can lead to improved care, positive long-term effects and reduced morbidity. Successful development and implementation of time series prediction algorithms is often based on selection of adequate signal processing models. In practical applications this issue is addressed almost invariably using statistical hypothesis testing. In this paper we propose preliminary model selection algorithm based on Bayesian approach leading to calculation of posterior odds ratios. We evaluate the applicability of the proposed method using a real data set containing over 180 pre-term infants whose heart rates were recorded over the length of their stay in the Neonatal Intensive Care Unit (NICU).",
keywords = "Bayesian model selection, Neonatal heart rate monitoring",
author = "Aleksandar Jeremic and Kenneth Tan",
year = "2011",
doi = "10.2316/P.2011.718-104",
language = "English",
isbn = "9780889868632",
pages = "406--410",
booktitle = "Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011",

}

Jeremic, A & Tan, K 2011, Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring. in Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011. pp. 406-410, 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011, Innsbruck, Austria, 14/02/11. https://doi.org/10.2316/P.2011.718-104

Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring. / Jeremic, Aleksandar; Tan, Kenneth.

Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011. 2011. p. 406-410.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring

AU - Jeremic, Aleksandar

AU - Tan, Kenneth

PY - 2011

Y1 - 2011

N2 - Although heart rate is commonly measured in various clinical settings the advanced algorithms for its prediction are rarely implemented in clinical settings and patient management. In neonatal intensive care timely prediction of dangerous levels of heart rate can lead to improved care, positive long-term effects and reduced morbidity. Successful development and implementation of time series prediction algorithms is often based on selection of adequate signal processing models. In practical applications this issue is addressed almost invariably using statistical hypothesis testing. In this paper we propose preliminary model selection algorithm based on Bayesian approach leading to calculation of posterior odds ratios. We evaluate the applicability of the proposed method using a real data set containing over 180 pre-term infants whose heart rates were recorded over the length of their stay in the Neonatal Intensive Care Unit (NICU).

AB - Although heart rate is commonly measured in various clinical settings the advanced algorithms for its prediction are rarely implemented in clinical settings and patient management. In neonatal intensive care timely prediction of dangerous levels of heart rate can lead to improved care, positive long-term effects and reduced morbidity. Successful development and implementation of time series prediction algorithms is often based on selection of adequate signal processing models. In practical applications this issue is addressed almost invariably using statistical hypothesis testing. In this paper we propose preliminary model selection algorithm based on Bayesian approach leading to calculation of posterior odds ratios. We evaluate the applicability of the proposed method using a real data set containing over 180 pre-term infants whose heart rates were recorded over the length of their stay in the Neonatal Intensive Care Unit (NICU).

KW - Bayesian model selection

KW - Neonatal heart rate monitoring

UR - http://www.scopus.com/inward/record.url?scp=79958109659&partnerID=8YFLogxK

U2 - 10.2316/P.2011.718-104

DO - 10.2316/P.2011.718-104

M3 - Conference Paper

AN - SCOPUS:79958109659

SN - 9780889868632

SP - 406

EP - 410

BT - Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011

ER -

Jeremic A, Tan K. Predicting the length of stay using Bayesian model selection for Neonatal heart rate monitoring. In Proceedings of the 31st IASTED International Conference on Modelling, Identification, and Control, MIC 2011. 2011. p. 406-410 https://doi.org/10.2316/P.2011.718-104