MUSE-Net: Missingness-aware mUlti-branching Self-attention Encoder for Irregular Longitudinal Electronic Health Records

TL;DR

MUSE-Net is a novel model designed to handle irregular, incomplete, and imbalanced longitudinal EHR data for disease prediction, incorporating missing data imputation, multi-branch architecture, time-aware self-attention, and interpretability.

Contribution

This paper introduces MUSE-Net, a multi-module neural network that effectively models irregular and incomplete EHR data for improved disease prediction, with built-in interpretability.

Findings

Outperforms existing methods on synthetic and real datasets.

Effectively handles missing data and irregular time intervals.

Provides interpretable insights into model decisions.

Abstract

The era of big data has made vast amounts of clinical data readily available, particularly in the form of electronic health records (EHRs), which provides unprecedented opportunities for developing data-driven diagnostic tools to enhance clinical decision making. However, the application of EHRs in data-driven modeling faces challenges such as irregularly spaced multi-variate time series, issues of incompleteness, and data imbalance. Realizing the full data potential of EHRs hinges on the development of advanced analytical models. In this paper, we propose a novel Missingness-aware mUlti-branching Self-Attention Encoder (MUSE-Net) to cope with the challenges in modeling longitudinal EHRs for data-driven disease prediction. The proposed MUSE-Net is composed by four novel modules including: (1) a multi-task Gaussian process (MGP) with missing value masks for data imputation; (2) a multi-branching architecture to address the data imbalance problem; (3) a time-aware self-attention encoder to account for the irregularly spaced time interval in longitudinal EHRs; (4) interpretable multi-head attention mechanism that provides insights into the importance of different time points in disease prediction, allowing clinicians to trace model decisions. We evaluate the proposed MUSE-Net using both synthetic and real-world datasets. Experimental results show that our MUSE-Net outperforms existing methods that are widely used to investigate longitudinal signals.