Predicting the length of stay for neonates using heart-rate Markov models

Aleksandar Jeremic, Kenneth Tan

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

1 Citation (Scopus)

Abstract

Recently, there has been an increase in preterm newborn's survival and as a result longer length of stay (LOS) in neonatal intensive care units (NICU) have been observed. Conseqyently, there has been an increased interest in accurate prediction of the LOS. Most of the existing techniques are based on physiological parameters i.e., scores such as (SNAP-II or SNAPPE-II). In this paper we propose to predict the length of stay using heart-rate measurements combined with physiological scores. We propose to model the heart-rate using Markov chain model and estimate transition probabilities using maximum likelihood estimator and the patient population from Neonatal Intensive Care Unit at McMaster Hospital. We then derive the maximum likelihood estimators of LOS using physiological measurements and transition probabilities. Training and test data sets were used to verify the proposed linear and nonlinear estimators.

Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Pages2912-2915
Number of pages4
Publication statusPublished - 2008
EventInternational Conference of the IEEE Engineering in Medicine and Biology Society 2008 - Vancouver Convention and Exhibition Centre, Vancouver, Canada
Duration: 20 Aug 200825 Aug 2008
Conference number: 30

Conference

ConferenceInternational Conference of the IEEE Engineering in Medicine and Biology Society 2008
Abbreviated titleEMBC 2008
CountryCanada
CityVancouver
Period20/08/0825/08/08

Keywords

  • Lengthof-stay prediction
  • Markov chains
  • Neonatal intensive care

Cite this

Jeremic, A., & Tan, K. (2008). Predicting the length of stay for neonates using heart-rate Markov models. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 (pp. 2912-2915). [4649812]
Jeremic, Aleksandar ; Tan, Kenneth. / Predicting the length of stay for neonates using heart-rate Markov models. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. pp. 2912-2915
@inproceedings{9a7836ab7dec43c38256b70be94eff9b,
title = "Predicting the length of stay for neonates using heart-rate Markov models",
abstract = "Recently, there has been an increase in preterm newborn's survival and as a result longer length of stay (LOS) in neonatal intensive care units (NICU) have been observed. Conseqyently, there has been an increased interest in accurate prediction of the LOS. Most of the existing techniques are based on physiological parameters i.e., scores such as (SNAP-II or SNAPPE-II). In this paper we propose to predict the length of stay using heart-rate measurements combined with physiological scores. We propose to model the heart-rate using Markov chain model and estimate transition probabilities using maximum likelihood estimator and the patient population from Neonatal Intensive Care Unit at McMaster Hospital. We then derive the maximum likelihood estimators of LOS using physiological measurements and transition probabilities. Training and test data sets were used to verify the proposed linear and nonlinear estimators.",
keywords = "Lengthof-stay prediction, Markov chains, Neonatal intensive care",
author = "Aleksandar Jeremic and Kenneth Tan",
year = "2008",
language = "English",
isbn = "9781424418152",
pages = "2912--2915",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08",

}

Jeremic, A & Tan, K 2008, Predicting the length of stay for neonates using heart-rate Markov models. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08., 4649812, pp. 2912-2915, International Conference of the IEEE Engineering in Medicine and Biology Society 2008, Vancouver, Canada, 20/08/08.

Predicting the length of stay for neonates using heart-rate Markov models. / Jeremic, Aleksandar; Tan, Kenneth.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 2912-2915 4649812.

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

TY - GEN

T1 - Predicting the length of stay for neonates using heart-rate Markov models

AU - Jeremic, Aleksandar

AU - Tan, Kenneth

PY - 2008

Y1 - 2008

N2 - Recently, there has been an increase in preterm newborn's survival and as a result longer length of stay (LOS) in neonatal intensive care units (NICU) have been observed. Conseqyently, there has been an increased interest in accurate prediction of the LOS. Most of the existing techniques are based on physiological parameters i.e., scores such as (SNAP-II or SNAPPE-II). In this paper we propose to predict the length of stay using heart-rate measurements combined with physiological scores. We propose to model the heart-rate using Markov chain model and estimate transition probabilities using maximum likelihood estimator and the patient population from Neonatal Intensive Care Unit at McMaster Hospital. We then derive the maximum likelihood estimators of LOS using physiological measurements and transition probabilities. Training and test data sets were used to verify the proposed linear and nonlinear estimators.

AB - Recently, there has been an increase in preterm newborn's survival and as a result longer length of stay (LOS) in neonatal intensive care units (NICU) have been observed. Conseqyently, there has been an increased interest in accurate prediction of the LOS. Most of the existing techniques are based on physiological parameters i.e., scores such as (SNAP-II or SNAPPE-II). In this paper we propose to predict the length of stay using heart-rate measurements combined with physiological scores. We propose to model the heart-rate using Markov chain model and estimate transition probabilities using maximum likelihood estimator and the patient population from Neonatal Intensive Care Unit at McMaster Hospital. We then derive the maximum likelihood estimators of LOS using physiological measurements and transition probabilities. Training and test data sets were used to verify the proposed linear and nonlinear estimators.

KW - Lengthof-stay prediction

KW - Markov chains

KW - Neonatal intensive care

UR - http://www.scopus.com/inward/record.url?scp=61849085867&partnerID=8YFLogxK

M3 - Conference Paper

SN - 9781424418152

SP - 2912

EP - 2915

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

ER -

Jeremic A, Tan K. Predicting the length of stay for neonates using heart-rate Markov models. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 2912-2915. 4649812