Inpatient2Vec: Medical Representation Learning for Inpatients

TL;DR

Inpatient2Vec is a novel medical representation learning model tailored for inpatient data, capturing temporal relations and activity importance, improving tasks like similarity measurement and clinical prediction.

Contribution

The paper introduces Inpatient2Vec, a new model specifically designed for inpatient data, utilizing self-attention and dual training tasks to better capture data characteristics.

Findings

Outperforms baseline methods in semantic similarity tasks

Enhances clinical event prediction accuracy

Effectively models inpatient data with temporal and activity importance features

Abstract

Representation learning (RL) plays an important role in extracting proper representations from complex medical data for various analyzing tasks, such as patient grouping, clinical endpoint prediction and medication recommendation. Medical data can be divided into two typical categories, outpatient and inpatient, that have different data characteristics. However, few of existing RL methods are specially designed for inpatients data, which have strong temporal relations and consistent diagnosis. In addition, for unordered medical activity set, existing medical RL methods utilize a simple pooling strategy, which would result in indistinguishable contributions among the activities for learning. In this work, weproposeInpatient2Vec, anovelmodel for learning three kinds of representations for inpatient, including medical activity, hospital day and diagnosis. A multi-layer self-attention mechanism with two training tasks is designed to capture the inpatient data characteristics and process the unordered set. Using a real-world dataset, we demonstrate that the proposed approach outperforms the competitive baselines on semantic similarity measurement and clinical events prediction tasks.