Evaluation of on-line bradycardia boundary detectors from neonatal clinical data

François Portet*, Feng Gao, Jim Hunter, Somayajulu Sripada

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

This paper aims at investigating different methods for the detection of the start and end of bradycardias in heart rate signal of premature babies. We present two methods based on a disturbance detector and on a decision tree that are compared to classical thresholding approaches. Decision tree obtained the best detection results (Se=78.2%, PP=68.7%) against the disturbance detector (Se=90.2%, PP=61.3%) and the best thresholding method (Se=92.5%, PP=46.5%). Moreover, the decision tree exhibits better performance for the boundaries estimation (median delay = 7-5 seconds) than the disturbance detector (median delay = 8-5 seconds) with a better stability (STD=8.5 to 8.7s vs. STD=35.3 to 19.9s). These methods will be integrated to the BabyTalk project which aims at summarizing neonatal clinical data as text in order to improve data management in Neonatal ICU.

Original languageEnglish
Title of host publication29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
PublisherIEEE Explore
Pages3288-3291
Number of pages4
ISBN (Print)1424407885, 9781424407880
DOIs
Publication statusPublished - 1 Dec 2007
Event29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 - Lyon, France
Duration: 23 Aug 200726 Aug 2007

Conference

Conference29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07
CountryFrance
CityLyon
Period23/08/0726/08/07

Fingerprint

Bradycardia
Decision trees
Decision Trees
Detectors
Sexually Transmitted Diseases
Intensive care units
Information management
Neonatal Intensive Care Units
Heart Rate

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Portet, F., Gao, F., Hunter, J., & Sripada, S. (2007). Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07 (pp. 3288-3291). [4353032] IEEE Explore. https://doi.org/10.1109/IEMBS.2007.4353032

Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. / Portet, François; Gao, Feng; Hunter, Jim; Sripada, Somayajulu.

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. IEEE Explore, 2007. p. 3288-3291 4353032.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Portet, F, Gao, F, Hunter, J & Sripada, S 2007, Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. in 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07., 4353032, IEEE Explore, pp. 3288-3291, 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07, Lyon, France, 23/08/07. https://doi.org/10.1109/IEMBS.2007.4353032
Portet F, Gao F, Hunter J, Sripada S. Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. In 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. IEEE Explore. 2007. p. 3288-3291. 4353032 https://doi.org/10.1109/IEMBS.2007.4353032
Portet, François ; Gao, Feng ; Hunter, Jim ; Sripada, Somayajulu. / Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07. IEEE Explore, 2007. pp. 3288-3291
@inproceedings{c484313a25ab44be89e380d80290766e,
title = "Evaluation of on-line bradycardia boundary detectors from neonatal clinical data",
abstract = "This paper aims at investigating different methods for the detection of the start and end of bradycardias in heart rate signal of premature babies. We present two methods based on a disturbance detector and on a decision tree that are compared to classical thresholding approaches. Decision tree obtained the best detection results (Se=78.2{\%}, PP=68.7{\%}) against the disturbance detector (Se=90.2{\%}, PP=61.3{\%}) and the best thresholding method (Se=92.5{\%}, PP=46.5{\%}). Moreover, the decision tree exhibits better performance for the boundaries estimation (median delay = 7-5 seconds) than the disturbance detector (median delay = 8-5 seconds) with a better stability (STD=8.5 to 8.7s vs. STD=35.3 to 19.9s). These methods will be integrated to the BabyTalk project which aims at summarizing neonatal clinical data as text in order to improve data management in Neonatal ICU.",
author = "Fran{\cc}ois Portet and Feng Gao and Jim Hunter and Somayajulu Sripada",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IEMBS.2007.4353032",
language = "English",
isbn = "1424407885",
pages = "3288--3291",
booktitle = "29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07",
publisher = "IEEE Explore",

}

TY - GEN

T1 - Evaluation of on-line bradycardia boundary detectors from neonatal clinical data

AU - Portet, François

AU - Gao, Feng

AU - Hunter, Jim

AU - Sripada, Somayajulu

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper aims at investigating different methods for the detection of the start and end of bradycardias in heart rate signal of premature babies. We present two methods based on a disturbance detector and on a decision tree that are compared to classical thresholding approaches. Decision tree obtained the best detection results (Se=78.2%, PP=68.7%) against the disturbance detector (Se=90.2%, PP=61.3%) and the best thresholding method (Se=92.5%, PP=46.5%). Moreover, the decision tree exhibits better performance for the boundaries estimation (median delay = 7-5 seconds) than the disturbance detector (median delay = 8-5 seconds) with a better stability (STD=8.5 to 8.7s vs. STD=35.3 to 19.9s). These methods will be integrated to the BabyTalk project which aims at summarizing neonatal clinical data as text in order to improve data management in Neonatal ICU.

AB - This paper aims at investigating different methods for the detection of the start and end of bradycardias in heart rate signal of premature babies. We present two methods based on a disturbance detector and on a decision tree that are compared to classical thresholding approaches. Decision tree obtained the best detection results (Se=78.2%, PP=68.7%) against the disturbance detector (Se=90.2%, PP=61.3%) and the best thresholding method (Se=92.5%, PP=46.5%). Moreover, the decision tree exhibits better performance for the boundaries estimation (median delay = 7-5 seconds) than the disturbance detector (median delay = 8-5 seconds) with a better stability (STD=8.5 to 8.7s vs. STD=35.3 to 19.9s). These methods will be integrated to the BabyTalk project which aims at summarizing neonatal clinical data as text in order to improve data management in Neonatal ICU.

UR - http://www.scopus.com/inward/record.url?scp=57649192818&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2007.4353032

DO - 10.1109/IEMBS.2007.4353032

M3 - Conference contribution

SN - 1424407885

SN - 9781424407880

SP - 3288

EP - 3291

BT - 29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

PB - IEEE Explore

ER -