A data wavelets approach to deriving trends in historical ICU monitor data

Apkar Salatian, Francis Adepoju, Augustine Odinma

Research output: Contribution to Book/Report typesChapterResearchpeer-review

Abstract

Medical staff in the Intensive Care Unit (ICU) are confronted with large volumes of continuous noisy data from several physiological sources that require interpretation. Rather than reasoning quantitatively on a point by point basis, especially in the context of other signals, we believe that Medical Staff could benefit with assistance in the interpretation of the ICU data by providing qualitative summaries. We propose data wavelets as an approach to analysing historical ICU data for deriving trends for summarization. In this paper we will show that wavelets are particularly effective for representing various aspects of non-stationary data such as trends, cycles and discontinuities.
Original languageEnglish
Title of host publication2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings
Pages162-165
Number of pages4
DOIs
Publication statusPublished - 2010

Publication series

Name2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings

Fingerprint

wavelet
discontinuity
trend

Keywords

  • Medicine
  • Signal processing
  • Trend detection

Cite this

Salatian, A., Adepoju, F., & Odinma, A. (2010). A data wavelets approach to deriving trends in historical ICU monitor data. In 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings (pp. 162-165). (2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings). https://doi.org/10.1109/SAS.2010.5439434
Salatian, Apkar ; Adepoju, Francis ; Odinma, Augustine. / A data wavelets approach to deriving trends in historical ICU monitor data. 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings. 2010. pp. 162-165 (2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings).
@inbook{289b0706a5ef423e8ad28c1e61293968,
title = "A data wavelets approach to deriving trends in historical ICU monitor data",
abstract = "Medical staff in the Intensive Care Unit (ICU) are confronted with large volumes of continuous noisy data from several physiological sources that require interpretation. Rather than reasoning quantitatively on a point by point basis, especially in the context of other signals, we believe that Medical Staff could benefit with assistance in the interpretation of the ICU data by providing qualitative summaries. We propose data wavelets as an approach to analysing historical ICU data for deriving trends for summarization. In this paper we will show that wavelets are particularly effective for representing various aspects of non-stationary data such as trends, cycles and discontinuities.",
keywords = "Medicine, Signal processing, Trend detection",
author = "Apkar Salatian and Francis Adepoju and Augustine Odinma",
year = "2010",
doi = "10.1109/SAS.2010.5439434",
language = "English",
isbn = "9781424449897",
series = "2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings",
pages = "162--165",
booktitle = "2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings",

}

Salatian, A, Adepoju, F & Odinma, A 2010, A data wavelets approach to deriving trends in historical ICU monitor data. in 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings. 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings, pp. 162-165. https://doi.org/10.1109/SAS.2010.5439434

A data wavelets approach to deriving trends in historical ICU monitor data. / Salatian, Apkar; Adepoju, Francis; Odinma, Augustine.

2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings. 2010. p. 162-165 (2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings).

Research output: Contribution to Book/Report typesChapterResearchpeer-review

TY - CHAP

T1 - A data wavelets approach to deriving trends in historical ICU monitor data

AU - Salatian, Apkar

AU - Adepoju, Francis

AU - Odinma, Augustine

PY - 2010

Y1 - 2010

N2 - Medical staff in the Intensive Care Unit (ICU) are confronted with large volumes of continuous noisy data from several physiological sources that require interpretation. Rather than reasoning quantitatively on a point by point basis, especially in the context of other signals, we believe that Medical Staff could benefit with assistance in the interpretation of the ICU data by providing qualitative summaries. We propose data wavelets as an approach to analysing historical ICU data for deriving trends for summarization. In this paper we will show that wavelets are particularly effective for representing various aspects of non-stationary data such as trends, cycles and discontinuities.

AB - Medical staff in the Intensive Care Unit (ICU) are confronted with large volumes of continuous noisy data from several physiological sources that require interpretation. Rather than reasoning quantitatively on a point by point basis, especially in the context of other signals, we believe that Medical Staff could benefit with assistance in the interpretation of the ICU data by providing qualitative summaries. We propose data wavelets as an approach to analysing historical ICU data for deriving trends for summarization. In this paper we will show that wavelets are particularly effective for representing various aspects of non-stationary data such as trends, cycles and discontinuities.

KW - Medicine

KW - Signal processing

KW - Trend detection

UR - http://www.mendeley.com/research/data-wavelets-approach-deriving-trends-historical-icu-monitor-data

U2 - 10.1109/SAS.2010.5439434

DO - 10.1109/SAS.2010.5439434

M3 - Chapter

SN - 9781424449897

T3 - 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings

SP - 162

EP - 165

BT - 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings

ER -

Salatian A, Adepoju F, Odinma A. A data wavelets approach to deriving trends in historical ICU monitor data. In 2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings. 2010. p. 162-165. (2010 IEEE Sensors Applications Symposium, SAS 2010 - Proceedings). https://doi.org/10.1109/SAS.2010.5439434