Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
This work addresses the need for improved patient stratification in healthcare to guide drug development and clinical trial recruitment, though it is incremental as it builds on existing clustering methods with outcome adjustment.
The authors tackled the problem of clustering longitudinal electronic health record data to identify patient subgroups with distinct trajectories and clinical outcomes, developing a recurrent neural network autoencoder that outperformed baseline models on a dataset of 29,229 diabetes patients.
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.