CATNet: Cross-event Attention-based Time-aware Network for Medical Event Prediction

TL;DR

This paper introduces CATNet, a novel neural network that leverages cross-event attention to effectively model complex, irregular, and heterogeneous medical time series data for improved medical event prediction.

Contribution

The paper proposes a time-aware, event-aware, and task-adaptive neural network that models correlations among different medical events using cross-event attention, addressing limitations of prior methods.

Findings

CATNet outperforms state-of-the-art methods on MIMIC-III and eICU datasets.

It effectively models heterogeneous and irregular temporal medical data.

The approach is adaptable to various medical event prediction tasks.

Abstract

Medical event prediction (MEP) is a fundamental task in the medical domain, which needs to predict medical events, including medications, diagnosis codes, laboratory tests, procedures, outcomes, and so on, according to historical medical records. The task is challenging as medical data is a type of complex time series data with heterogeneous and temporal irregular characteristics. Many machine learning methods that consider the two characteristics have been proposed for medical event prediction. However, most of them consider the two characteristics separately and ignore the correlations among different types of medical events, especially relations between historical medical events and target medical events. In this paper, we propose a novel neural network based on attention mechanism, called cross-event attention-based time-aware network (CATNet), for medical event prediction. It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering temporal irregular characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention. Experiments on two public datasets (MIMIC-III and eICU) show CATNet can be adaptive with different MEP tasks and outperforms other state-of-the-art methods on various MEP tasks. The source code of CATNet will be released after this manuscript is accepted.