Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks

TL;DR

This paper introduces a Multi-directional Recurrent Neural Network (M-RNN) for estimating missing data in irregular, multi-stream medical time series, significantly outperforming existing methods in accuracy and robustness.

Contribution

The paper presents a novel deep learning architecture, M-RNN, that effectively interpolates and imputes missing data in complex medical time series, addressing limitations of prior approaches.

Findings

M-RNN achieves 35-50% lower RMSE than benchmarks.

The method is robust across five real-world datasets.

It outperforms 11 state-of-the-art imputation techniques.

Abstract

Missing data is a ubiquitous problem. It is especially challenging in medical settings because many streams of measurements are collected at different - and often irregular - times. Accurate estimation of those missing measurements is critical for many reasons, including diagnosis, prognosis and treatment. Existing methods address this estimation problem by interpolating within data streams or imputing across data streams (both of which ignore important information) or ignoring the temporal aspect of the data and imposing strong assumptions about the nature of the data-generating process and/or the pattern of missing data (both of which are especially problematic for medical data). We propose a new approach, based on a novel deep learning architecture that we call a Multi-directional Recurrent Neural Network (M-RNN) that interpolates within data streams and imputes across data streams. We demonstrate the power of our approach by applying it to five real-world medical datasets. We show that it provides dramatically improved estimation of missing measurements in comparison to 11 state-of-the-art benchmarks (including Spline and Cubic Interpolations, MICE, MissForest, matrix completion and several RNN methods); typical improvements in Root Mean Square Error are between 35% - 50%. Additional experiments based on the same five datasets demonstrate that the improvements provided by our method are extremely robust.