Temporal Self-Attention Network for Medical Concept Embedding

TL;DR

This paper introduces TeSAN, a novel temporal self-attention network for medical concept embedding in EHRs, capturing temporal relations to improve prediction and clustering tasks, outperforming existing methods.

Contribution

It presents the first application of temporal self-attention for medical concept embedding, enhancing the representation of temporal relations in EHR data.

Findings

TeSAN outperforms five state-of-the-art embedding methods in clustering and prediction.

The model effectively captures contextual and temporal information between medical concepts.

Experimental results demonstrate superior performance of TeSAN on public EHR datasets.

Abstract

In longitudinal electronic health records (EHRs), the event records of a patient are distributed over a long period of time and the temporal relations between the events reflect sufficient domain knowledge to benefit prediction tasks such as the rate of inpatient mortality. Medical concept embedding as a feature extraction method that transforms a set of medical concepts with a specific time stamp into a vector, which will be fed into a supervised learning algorithm. The quality of the embedding significantly determines the learning performance over the medical data. In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept. We propose a novel attention mechanism which captures the contextual information and temporal relationships between medical concepts. A light-weight neural net, "Temporal Self-Attention Network (TeSAN)", is then proposed to learn medical concept embedding based solely on the proposed attention mechanism. To test the effectiveness of our proposed methods, we have conducted clustering and prediction tasks on two public EHRs datasets comparing TeSAN against five state-of-the-art embedding methods. The experimental results demonstrate that the proposed TeSAN model is superior to all the compared methods. To the best of our knowledge, this work is the first to exploit temporal self-attentive relations between medical events.