Heart rate monitoring in neonatal intensive care using Markov models

Aleksandar Jeremić; Kenneth Tan

doi:10.1109/ICASSP.2008.4517652

Heart rate monitoring in neonatal intensive care using Markov models

Aleksandar Jeremić, Kenneth Tan

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-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, long-term effects and reduced morbidity. In this paper 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. The probabilities of reaching high-risk states in predetermined time intervals are computed and the results are evaluated using the real data set.

Original language	English
Title of host publication	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages	485-488
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2008.4517652
Publication status	Published - 2008
Externally published	Yes
Event	IEEE International Conference on Acoustics, Speech and Signal Processing 2008 - Las Vegas, United States of America Duration: 31 Mar 2008 → 4 Apr 2008 https://ieeexplore.ieee.org/xpl/conhome/4505270/proceeding (Proceedings)

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing 2008
Abbreviated title	ICASSP 2008
Country	United States of America
City	Las Vegas
Period	31/03/08 → 4/04/08
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4505270/proceeding (Proceedings)

Keywords

Heart-rate prediction
Markov chains
Neonatal intensive care

Access to Document

10.1109/ICASSP.2008.4517652

Link to publication in Scopus

Cite this

@inproceedings{53e6d230bffe4b828e9fa03a97b1d094,

title = "Heart rate monitoring in neonatal intensive care using Markov models",

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, long-term effects and reduced morbidity. In this paper 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. The probabilities of reaching high-risk states in predetermined time intervals are computed and the results are evaluated using the real data set.",

keywords = "Heart-rate prediction, Markov chains, Neonatal intensive care",

author = "Aleksandar Jeremi{\'c} and Kenneth Tan",

year = "2008",

doi = "10.1109/ICASSP.2008.4517652",

language = "English",

isbn = "1424414849",

pages = "485--488",

booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing 2008, ICASSP 2008 ; Conference date: 31-03-2008 Through 04-04-2008",

url = "https://ieeexplore.ieee.org/xpl/conhome/4505270/proceeding",

}

Jeremić, A & Tan, K 2008, Heart rate monitoring in neonatal intensive care using Markov models. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4517652, pp. 485-488, IEEE International Conference on Acoustics, Speech and Signal Processing 2008, Las Vegas, United States of America, 31/03/08. https://doi.org/10.1109/ICASSP.2008.4517652

TY - GEN

T1 - Heart rate monitoring in neonatal intensive care using Markov models

AU - Jeremić, Aleksandar

AU - Tan, Kenneth

PY - 2008

Y1 - 2008

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, long-term effects and reduced morbidity. In this paper 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. The probabilities of reaching high-risk states in predetermined time intervals are computed and the results are evaluated using the real data set.

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, long-term effects and reduced morbidity. In this paper 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. The probabilities of reaching high-risk states in predetermined time intervals are computed and the results are evaluated using the real data set.

KW - Heart-rate prediction

KW - Markov chains

KW - Neonatal intensive care

UR - http://www.scopus.com/inward/record.url?scp=51449092354&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517652

DO - 10.1109/ICASSP.2008.4517652

M3 - Conference Paper

AN - SCOPUS:51449092354

SN - 1424414849

SN - 9781424414840

SP - 485

EP - 488

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing 2008

Y2 - 31 March 2008 through 4 April 2008

ER -