Integrative Analysis and Imputation of Multiple Data Streams via Deep Gaussian Processes

TL;DR

This paper introduces a deep Gaussian process-based method for integrative analysis and imputation of multi-source, irregularly sampled healthcare data, effectively capturing relationships and providing uncertainty estimates.

Contribution

It presents a novel application of deep Gaussian processes with stochastic imputation for healthcare data, addressing irregular sampling, multiple data streams, and uncertainty quantification.

Findings

Outperforms traditional imputation methods like MICE and last-known value imputation.

Effectively captures relationships across different physiological measurements.

Provides reliable uncertainty estimates for imputed values.

Abstract

Healthcare data, particularly in critical care settings, presents three key challenges for analysis. First, physiological measurements come from different sources but are inherently related. Yet, traditional methods often treat each measurement type independently, losing valuable information about their relationships. Second, clinical measurements are collected at irregular intervals, and these sampling times can carry clinical meaning. Finally, the prevalence of missing values. Whilst several imputation methods exist to tackle this common problem, they often fail to address the temporal nature of the data or provide estimates of uncertainty in their predictions. We propose using deep Gaussian process emulation with stochastic imputation, a methodology initially conceived to deal with computationally expensive models and uncertainty quantification, to solve the problem of handling missing values that naturally occur in critical care data. This method leverages longitudinal and cross-sectional information and provides uncertainty estimation for the imputed values. Our evaluation of a clinical dataset shows that the proposed method performs better than conventional methods, such as multiple imputations with chained equations (MICE), last-known value imputation, and individually fitted Gaussian Processes (GPs).