Improving Patient Subtyping on Longitudinal Data using Representations from Mamba-based Architecture
For researchers working with temporal EHR data, this work offers a new representation learning approach that enhances patient subtyping, though improvements are incremental.
The paper proposes a self-supervised Mamba-based model for learning effective EHR representations to improve patient subtyping. The model outperforms competitive baselines in prediction tasks on both public and private EHR datasets.
Effective sub-typing (also known as grouping or clustering) of patients using their electronic health record (EHR) data can greatly inform precision medicine efforts. However, subtyping temporal EHR datasets is known to be challenging due to inherent EHR issues, including complexity and irregularity. In this study, we propose a self-supervised Mamba-based model that learns effective EHR representations and enables enhanced patient subtyping. We evaluate the proposed model on public and private real-world EHR datasets to classify the data based on the available labels and subtype patients based on the representations learned from the model. Through an extensive set of experiments, we demonstrate that our model's design choices lead to better performance compared to competitive baseline models for prediction. Moreover, we evaluate several clustering techniques to demonstrate that our findings offer valuable insights into subtyping patients based on temporal records from EHR models\footnote{Our implementations are available at https://github.com/healthylaife/triplet_mamba.