Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes

TL;DR

This paper introduces a recurrent neural network autoencoder that clusters longitudinal EHR data by considering both patient trajectories and clinical outcomes, aiding personalized medicine and clinical trial recruitment.

Contribution

It presents a novel autoencoder model that integrates reconstruction, outcome, and clustering losses, allowing flexible adjustment to discover diverse patient subgroups.

Findings

Successfully identified known patient clusters with data biases and outcome differences

Outperformed baseline models in clustering accuracy

Effectively distinguished patient groups with different trajectories and outcomes

Abstract

The increase in availability of longitudinal electronic health record (EHR) data is leading to improved understanding of diseases and discovery of novel phenotypes. The majority of clustering algorithms focus only on patient trajectories, yet patients with similar trajectories may have different outcomes. Finding subgroups of patients with different trajectories and outcomes can guide future drug development and improve recruitment to clinical trials. We develop a recurrent neural network autoencoder to cluster EHR data using reconstruction, outcome, and clustering losses which can be weighted to find different types of patient clusters. We show our model is able to discover known clusters from both data biases and outcome differences, outperforming baseline models. We demonstrate the model performance on $29,229$ diabetes patients, showing it finds clusters of patients with both different trajectories and different outcomes which can be utilized to aid clinical decision making.