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 proceedingConference contributionpeer-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 languageEnglish
Title of host publicationProceedings - 2022 IEEE 10th International Conference on Healthcare Informatics, ICHI 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages639-643
Number of pages5
ISBN (Electronic)9781665468459
DOIs
StatePublished - 2022
Event10th IEEE International Conference on Healthcare Informatics, ICHI 2022 - Rochester, United States
Duration: Jun 11 2022Jun 14 2022

Publication series

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

Conference

Conference10th IEEE International Conference on Healthcare Informatics, ICHI 2022
Country/TerritoryUnited States
CityRochester
Period06/11/2206/14/22

Funding

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

FundersFunder number
U.S. Department of Veterans Affairs

    Keywords

    • ehr
    • event sequences
    • feature engineering
    • lstm
    • rnn

    Fingerprint

    Dive into the research topics of 'Use of Event-Time Embeddings via RNN to Discern Novel Event Sequences in EHRs'. Together they form a unique fingerprint.

    Cite this