Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs

Ozgur Ozmen; Hilda B. Klasky; Olufemi A. Omitaomu; Mohammed Olama; Teja Kuruganti; Laura Pullum; Addi T. Malviya; Merry Ward; Jeanie M. Scott; Angela Laurio; Brian Sauer; Frank Drews; Jonathan Nebeker

doi:10.1109/ICHI54592.2022.00129

Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs

Ozgur Ozmen, Hilda B. Klasky, Olufemi A. Omitaomu, Mohammed Olama, Teja Kuruganti, Laura Pullum, Addi T. Malviya, Merry Ward, Jeanie M. Scott, Angela Laurio, Brian Sauer, Frank Drews, Jonathan Nebeker

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

Abstract

In highly configurable health information technology (HIT) systems, such as VistA of the Veterans Health Administration, the variations in how the system is used among different healthcare facilities and how the data are recorded can be significant. Despite the successful standardization of care efforts, some of these variations can be indicative of HIT hazards and demand further investigation. In this work, we implemented a recurrent neural network (RNN) architecture to learn clinical provider order sequences and their temporal dynamics while predicting the orders' terminal state. We demonstrate model performance and provide a use case for the model discerning novel event sequences. This model is proposed to find novel event sequences in an operational environment.

Original language	English
Title of host publication	Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	639-643
Number of pages	5
ISBN (Electronic)	9781665468459
DOIs	https://doi.org/10.1109/ICHI54592.2022.00129
State	Published - 2022
Event	10th IEEE International Conference on Healthcare Informatics, ICHI 2022 - Rochester, United States Duration: Jun 11 2022 → Jun 14 2022

Publication series

Name	Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022

Conference

Conference	10th IEEE International Conference on Healthcare Informatics, ICHI 2022
Country/Territory	United States
City	Rochester
Period	06/11/22 → 06/14/22

Funding

This work is sponsored by the US Department of Veterans Affairs.

Keywords

ehr
event sequences
feature engineering
lstm
rnn

Access to Document

10.1109/ICHI54592.2022.00129

Cite this

Ozmen, O., Klasky, H. B., Omitaomu, O. A., Olama, M., Kuruganti, T., Pullum, L., Malviya, A. T., Ward, M., Scott, J. M., Laurio, A., Sauer, B., Drews, F., & Nebeker, J. (2022). Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs. In Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022 (pp. 639-643). (Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI54592.2022.00129

Ozmen, Ozgur ; Klasky, Hilda B. ; Omitaomu, Olufemi A. et al. / Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs. Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 639-643 (Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022).

@inproceedings{526f873b136f4d27ad6c296df96165cc,

title = "Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs",

abstract = "In highly configurable health information technology (HIT) systems, such as VistA of the Veterans Health Administration, the variations in how the system is used among different healthcare facilities and how the data are recorded can be significant. Despite the successful standardization of care efforts, some of these variations can be indicative of HIT hazards and demand further investigation. In this work, we implemented a recurrent neural network (RNN) architecture to learn clinical provider order sequences and their temporal dynamics while predicting the orders' terminal state. We demonstrate model performance and provide a use case for the model discerning novel event sequences. This model is proposed to find novel event sequences in an operational environment.",

keywords = "ehr, event sequences, feature engineering, lstm, rnn",

author = "Ozgur Ozmen and Klasky, {Hilda B.} and Omitaomu, {Olufemi A.} and Mohammed Olama and Teja Kuruganti and Laura Pullum and Malviya, {Addi T.} and Merry Ward and Scott, {Jeanie M.} and Angela Laurio and Brian Sauer and Frank Drews and Jonathan Nebeker",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 10th IEEE International Conference on Healthcare Informatics, ICHI 2022 ; Conference date: 11-06-2022 Through 14-06-2022",

year = "2022",

doi = "10.1109/ICHI54592.2022.00129",

language = "English",

series = "Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022",

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

pages = "639--643",

booktitle = "Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022",

}

Ozmen, O, Klasky, HB , Omitaomu, OA , Olama, M , Kuruganti, T, Pullum, L, Malviya, AT, Ward, M, Scott, JM, Laurio, A, Sauer, B, Drews, F & Nebeker, J 2022, Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs. in Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022. Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022, Institute of Electrical and Electronics Engineers Inc., pp. 639-643, 10th IEEE International Conference on Healthcare Informatics, ICHI 2022, Rochester, United States, 06/11/22. https://doi.org/10.1109/ICHI54592.2022.00129

Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs. / Ozmen, Ozgur; Klasky, Hilda B.; Omitaomu, Olufemi A. et al.
Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 639-643 (Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022).

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

TY - GEN

T1 - Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs

AU - Ozmen, Ozgur

AU - Klasky, Hilda B.

AU - Omitaomu, Olufemi A.

AU - Olama, Mohammed

AU - Kuruganti, Teja

AU - Pullum, Laura

AU - Malviya, Addi T.

AU - Ward, Merry

AU - Scott, Jeanie M.

AU - Laurio, Angela

AU - Sauer, Brian

AU - Drews, Frank

AU - Nebeker, Jonathan

PY - 2022

Y1 - 2022

N2 - In highly configurable health information technology (HIT) systems, such as VistA of the Veterans Health Administration, the variations in how the system is used among different healthcare facilities and how the data are recorded can be significant. Despite the successful standardization of care efforts, some of these variations can be indicative of HIT hazards and demand further investigation. In this work, we implemented a recurrent neural network (RNN) architecture to learn clinical provider order sequences and their temporal dynamics while predicting the orders' terminal state. We demonstrate model performance and provide a use case for the model discerning novel event sequences. This model is proposed to find novel event sequences in an operational environment.

AB - In highly configurable health information technology (HIT) systems, such as VistA of the Veterans Health Administration, the variations in how the system is used among different healthcare facilities and how the data are recorded can be significant. Despite the successful standardization of care efforts, some of these variations can be indicative of HIT hazards and demand further investigation. In this work, we implemented a recurrent neural network (RNN) architecture to learn clinical provider order sequences and their temporal dynamics while predicting the orders' terminal state. We demonstrate model performance and provide a use case for the model discerning novel event sequences. This model is proposed to find novel event sequences in an operational environment.

KW - ehr

KW - event sequences

KW - feature engineering

KW - lstm

KW - rnn

UR - http://www.scopus.com/inward/record.url?scp=85139078926&partnerID=8YFLogxK

U2 - 10.1109/ICHI54592.2022.00129

DO - 10.1109/ICHI54592.2022.00129

M3 - Conference contribution

AN - SCOPUS:85139078926

T3 - Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022

SP - 639

EP - 643

BT - Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th IEEE International Conference on Healthcare Informatics, ICHI 2022

Y2 - 11 June 2022 through 14 June 2022

ER -

Ozmen O, Klasky HB , Omitaomu OA , Olama M , Kuruganti T, Pullum L et al. Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs. In Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 639-643. (Proceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022). doi: 10.1109/ICHI54592.2022.00129

Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this