Journal Article

FZJ-2023-01610

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Novel architecture for gated recurrent unit autoencoder trained on time series from electronic health records enables detection of ICU patient subgroups

Merkelbach, K. ; Schaper, S. ; Diedrich, C. ; Fritsch, S. J.FZJ* ; Schuppert, A. (Corresponding author)

2023
Macmillan Publishers Limited, part of Springer Nature [London]

This record in other databases:    

Please use a persistent id in citations: http://hdl.handle.net/2128/34225  doi:10.1038/s41598-023-30986-1

Abstract: Electronic health records (EHRs) are used in hospitals to store diagnoses, clinician notes, examinations, lab results, and interventions for each patient. Grouping patients into distinct subsets, for example, via clustering, may enable the discovery of unknown disease patterns or comorbidities, which could eventually lead to better treatment through personalized medicine. Patient data derived from EHRs is heterogeneous and temporally irregular. Therefore, traditional machine learning methods like PCA are ill-suited for analysis of EHR-derived patient data. We propose to address these issues with a new methodology based on training a gated recurrent unit (GRU) autoencoder directly on health record data. Our method learns a low-dimensional feature space by training on patient data time series, where the time of each data point is expressed explicitly. We use positional encodings for time, allowing our model to better handle the temporal irregularity of the data. We apply our method to data from the Medical Information Mart for Intensive Care (MIMIC-III). Using our data-derived feature space, we can cluster patients into groups representing major classes of disease patterns. Additionally, we show that our feature space exhibits a rich substructure at multiple scales.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511) (POF4-511)
2. SMITH - Medizininformatik-Konsortium - Beitrag Forschungszentrum Jülich (01ZZ1803M) (01ZZ1803M)

Appears in the scientific report 2023

---

Database coverage:
; ; ; ; BIOSIS Previews ; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Ebsco Academic Search ; IF < 5 ; JCR ; PubMed Central ; SCOPUS ; Web of Science Core Collection ; Zoological Record

---