Domain Adaptation Using Convolutional Autoencoder and Gradient Boosting for Adverse Events Prediction in the Intensive Care Unit

Yuanda Zhu; Janani Venugopalan; Zhenyu Zhang; Nikhil K Chanani; Kevin O Maher; May D Wang

doi:10.3389/frai.2022.640926

Domain Adaptation Using Convolutional Autoencoder and Gradient Boosting for Adverse Events Prediction in the Intensive Care Unit

Front Artif Intell. 2022 Apr 11:5:640926. doi: 10.3389/frai.2022.640926. eCollection 2022.

Authors

Yuanda Zhu¹, Janani Venugopalan², Zhenyu Zhang^{3

4}, Nikhil K Chanani⁵, Kevin O Maher⁵, May D Wang²

Affiliations

¹ School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, United States.
² Biomedical Engineering Department, Georgia Institute of Technology, Emory University, Atlanta, GA, United States.
³ Biomedical Engineering Department, Georgia Institute of Technology, Atlanta, GA, United States.
⁴ Department of Biomedical Engineering, Peking University, Beijing, China.
⁵ Pediatrics Department, Emory University, Atlanta, GA, United States.

Abstract

More than 5 million patients have admitted annually to intensive care units (ICUs) in the United States. The leading causes of mortality are cardiovascular failures, multi-organ failures, and sepsis. Data-driven techniques have been used in the analysis of patient data to predict adverse events, such as ICU mortality and ICU readmission. These models often make use of temporal or static features from a single ICU database to make predictions on subsequent adverse events. To explore the potential of domain adaptation, we propose a method of data analysis using gradient boosting and convolutional autoencoder (CAE) to predict significant adverse events in the ICU, such as ICU mortality and ICU readmission. We demonstrate our results from a retrospective data analysis using patient records from a publicly available database called Multi-parameter Intelligent Monitoring in Intensive Care-II (MIMIC-II) and a local database from Children's Healthcare of Atlanta (CHOA). We demonstrate that after adopting novel data imputation on patient ICU data, gradient boosting is effective in both the mortality prediction task and the ICU readmission prediction task. In addition, we use gradient boosting to identify top-ranking temporal and non-temporal features in both prediction tasks. We discuss the relationship between these features and the specific prediction task. Lastly, we indicate that CAE might not be effective in feature extraction on one dataset, but domain adaptation with CAE feature extraction across two datasets shows promising results.

Keywords: clinical decision support; convolutional autoencoder; domain adaptation (DA); gradient boosting; intensive care units; mortality prediction.