Learning latent space representations to predict patient outcomes: Model development and validation

Subendhu Rongali, Adam J. Rose, David D. McManus, Adarsha S. Bajracharya, Alok Kapoor, Edgard Granillo, Hong Yu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

Background: Scalable and accurate health outcome prediction using electronic health record (EHR) data has gained much attention in research recently. Previous machine learning models mostly ignore relations between different types of clinical data (ie, laboratory components, International Classification of Diseases codes, and medications). Objective: This study aimed to model such relations and build predictive models using the EHR data from intensive care units. We developed innovative neural network models and compared them with the widely used logistic regression model and other state-of-the-art neural network models to predict the patient’s mortality using their longitudinal EHR data. Methods: We built a set of neural network models that we collectively called as long short-term memory (LSTM) outcome prediction using comprehensive feature relations or in short, CLOUT. Our CLOUT models use a correlational neural network model to identify a latent space representation between different types of discrete clinical features during a patient’s encounter and integrate the latent representation into an LSTM-based predictive model framework. In addition, we designed an ablation experiment to identify risk factors from our CLOUT models. Using physicians’ input as the gold standard, we compared the risk factors identified by both CLOUT and logistic regression models. Results: Experiments on the Medical Information Mart for Intensive Care-III dataset (selected patient population: 7537) show that CLOUT (area under the receiver operating characteristic curve=0.89) has surpassed logistic regression (0.82) and other baseline NN models (<0.86). In addition, physicians’ agreement with the CLOUT-derived risk factor rankings was statistically significantly higher than the agreement with the logistic regression model. Conclusions: Our results support the applicability of CLOUT for real-world clinical use in identifying patients at high risk of mortality.

Original languageAmerican English
Article numbere16374
JournalJournal of Medical Internet Research
Volume22
Issue number3
DOIs
StatePublished - Mar 2020
Externally publishedYes

Bibliographical note

Publisher Copyright:
©Subendhu Rongali, Adam J Rose, David D McManus, Adarsha S Bajracharya, Alok Kapoor, Edgard Granillo, Hong Yu.

Keywords

  • Ablation
  • Neural networks
  • Patient mortality
  • Predictive modeling

Fingerprint

Dive into the research topics of 'Learning latent space representations to predict patient outcomes: Model development and validation'. Together they form a unique fingerprint.

Cite this