Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs)

Michael Bowie; Edmon Begoli; Byung Park

doi:10.1109/ICDEW.2018.00015

Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs)

Michael Bowie, Edmon Begoli, Byung Park

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.

Original language	English
Title of host publication	Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	48-53
Number of pages	6
ISBN (Electronic)	9781538663066
DOIs	https://doi.org/10.1109/ICDEW.2018.00015
State	Published - Jul 2 2018
Event	34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018 - Paris, France Duration: Apr 16 2018 → Apr 19 2018

Publication series

Name	Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018

Conference

Conference	34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018
Country/Territory	France
City	Paris
Period	04/16/18 → 04/19/18

Funding

ACKNOWLEDGMENT This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). The research presented in this paper was supported in part by the joint program MVP CHAMPION between the Department of Veterans Affairs, Veterans Health Administration, Office of Research and Development and the Department of Energy.

Keywords

Anomaly detection
Encoder-decoder
LSTM
Missing data

Access to Document

10.1109/ICDEW.2018.00015

Cite this

Bowie, M., Begoli, E., & Park, B. (2018). Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs). In Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018 (pp. 48-53). (Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDEW.2018.00015

Bowie, Michael ; Begoli, Edmon ; Park, Byung. / Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs). Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 48-53 (Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018).

@inproceedings{adc786a1237448309b2878e15620091f,

title = "Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs)",

abstract = "We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.",

keywords = "Anomaly detection, Encoder-decoder, LSTM, Missing data",

author = "Michael Bowie and Edmon Begoli and Byung Park",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018 ; Conference date: 16-04-2018 Through 19-04-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/ICDEW.2018.00015",

language = "English",

series = "Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "48--53",

booktitle = "Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018",

}

Bowie, M, Begoli, E & Park, B 2018, Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs). in Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018. Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018, Institute of Electrical and Electronics Engineers Inc., pp. 48-53, 34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018, Paris, France, 04/16/18. https://doi.org/10.1109/ICDEW.2018.00015

Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs). / Bowie, Michael; Begoli, Edmon ; Park, Byung.
Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 48-53 (Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs)

AU - Bowie, Michael

AU - Begoli, Edmon

AU - Park, Byung

PY - 2018/7/2

Y1 - 2018/7/2

N2 - We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.

AB - We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.

KW - Anomaly detection

KW - Encoder-decoder

KW - LSTM

KW - Missing data

UR - http://www.scopus.com/inward/record.url?scp=85050613768&partnerID=8YFLogxK

U2 - 10.1109/ICDEW.2018.00015

DO - 10.1109/ICDEW.2018.00015

M3 - Conference contribution

AN - SCOPUS:85050613768

T3 - Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018

SP - 48

EP - 53

BT - Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018

Y2 - 16 April 2018 through 19 April 2018

ER -

Bowie M, Begoli E , Park B. Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs). In Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 48-53. (Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018). doi: 10.1109/ICDEW.2018.00015

Improving quality of observational streaming medical data by using long short-term memory networks (LSTMs)

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this