MURAL: An Unsupervised Random Forest-Based Embedding for Electronic Health Record Data

TL;DR

MURAL is an unsupervised random forest method designed to embed and visualize heterogeneous EHR data, including missing not at random variables, improving classification and cohort comparison.

Contribution

This paper introduces MURAL, a novel unsupervised random forest approach that effectively handles mixed variable types and missing not at random data in EHRs for embedding and visualization.

Findings

MURAL outperforms competing methods in visualization accuracy.

MURAL enables better classification of clinical data.

Tree-sliced Wasserstein distances facilitate cohort comparisons.

Abstract

A major challenge in embedding or visualizing clinical patient data is the heterogeneity of variable types including continuous lab values, categorical diagnostic codes, as well as missing or incomplete data. In particular, in EHR data, some variables are {\em missing not at random (MNAR)} but deliberately not collected and thus are a source of information. For example, lab tests may be deemed necessary for some patients on the basis of suspected diagnosis, but not for others. Here we present the MURAL forest -- an unsupervised random forest for representing data with disparate variable types (e.g., categorical, continuous, MNAR). MURAL forests consist of a set of decision trees where node-splitting variables are chosen at random, such that the marginal entropy of all other variables is minimized by the split. This allows us to also split on MNAR variables and discrete variables in a way that is consistent with the continuous variables. The end goal is to learn the MURAL embedding of patients using average tree distances between those patients. These distances can be fed to nonlinear dimensionality reduction method like PHATE to derive visualizable embeddings. While such methods are ubiquitous in continuous-valued datasets (like single cell RNA-sequencing) they have not been used extensively in mixed variable data. We showcase the use of our method on one artificial and two clinical datasets. We show that using our approach, we can visualize and classify data more accurately than competing approaches. Finally, we show that MURAL can also be used to compare cohorts of patients via the recently proposed tree-sliced Wasserstein distances.