RIMD: A novel method for clinical prediction.

Journal: Artificial intelligence in medicine
Published Date:

Abstract

Electronic health records (EHR) are sparse, noisy, and private, with variable vital measurements and stay lengths. Deep learning models are the current state of the art in many machine learning domain; however, the EHR data is not a suitable training input for most of them. In this paper, we introduce RIMD, a novel deep learning model that consists of a decay mechanism, modular recurrent networks, and a custom loss function that learns minor classes. The decay mechanism learns from patterns in sparse data. The modular network allows multiple recurrent networks to pick only relevant input based on the attention score at a given timestamp. Finally, the custom class balance loss function is responsible for learning minor classes based on samples provided in training. This novel model is used to evaluate predictions for early mortality identification, length of stay, and acute respiratory failure on MIMIC-III dataset. Experiment results indicate that the proposed models outperform similar models in F1-Score, AUROC, and PRAUC scores.

Authors

  • Saroj Basnet
    University of Regina, 3737 Wascana Pkwy, Regina, S4S 0A2, SK, Canada. Electronic address: cs.sarojbasnet@gmail.com.
  • Sirvan Parasteh
    University of Regina, 3737 Wascana Pkwy, Regina, S4S 0A2, SK, Canada. Electronic address: sirvanparasteh@uregina.ca.
  • Alireza Manashty
    University of Regina, 3737 Wascana Pkwy, Regina, S4S 0A2, SK, Canada. Electronic address: alireza.manashty@uregina.ca.
  • Brandon Sasyniuk
    University of Regina, 3737 Wascana Pkwy, Regina, S4S 0A2, SK, Canada. Electronic address: sasyniub@uregina.ca.