Dynamic Healthcare Embeddings for Improving Patient Care

Hankyu Jang; Sulyun Lee; D. M. Hasibul Hasan; Philip M Polgreen; Sriram V Pemmaraju; Bijaya Adhikari

doi:10.48550/arxiv.2303.11563

Back

Dynamic Healthcare Embeddings for Improving Patient Care

Preprint

Open access

Dynamic Healthcare Embeddings for Improving Patient Care

Hankyu Jang, Sulyun Lee, D. M. Hasibul Hasan, Philip M Polgreen, Sriram V Pemmaraju and Bijaya Adhikari

ArXiv.org

03/20/2023

DOI: 10.48550/arxiv.2303.11563

Files and links (1)

url

https://doi.org/10.48550/arxiv.2303.11563View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (C.diff) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings.

Details

Title: Subtitle: Dynamic Healthcare Embeddings for Improving Patient Care
Creators: Hankyu Jang - University of Iowa
Sulyun Lee - Interdisciplinary Graduate Program in Informatics, University of Iowa
D. M. Hasibul Hasan - Department of Computer Science, University of Iowa
Philip M Polgreen - University of Iowa
Sriram V Pemmaraju - University of Iowa
Bijaya Adhikari - University of Iowa
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2303.11563
Language: English
Date posted: 03/20/2023
Academic Unit: Infectious Diseases; Epidemiology; Injury Prevention Research Center; Computer Science; Internal Medicine
Record Identifier: 9984380659602771

Metrics

20 Record Views