# TAPER: Time-Aware Patient EHR Representation

## TL;DR

TAPER is a transformer-based model that creates unified, time-aware representations of heterogeneous electronic health record data, improving performance on clinical prediction tasks.

## Contribution

The paper introduces TAPER, a novel transformer-based approach that effectively encodes irregular, multi-modal EHR data into unified patient representations for predictive modeling.

## Key findings

- Superior performance on mortality, readmission, and length of stay tasks
- Effective encoding of irregular, multi-modal EHR data
- Generalizes well across different clinical prediction tasks

## Abstract

Effective representation learning of electronic health records is a challenging task and is becoming more important as the availability of such data is becoming pervasive. The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes. They are preempted by medical conditions the patient may have, and are typically jotted down by medical staff. Accompanying codes are notes containing valuable information about patients beyond the structured information contained in electronic health records. We use transformer networks and the recently proposed BERT language model to embed these data streams into a unified vector representation. The presented approach effectively encodes a patient's visit data into a single distributed representation, which can be used for downstream tasks. Our model demonstrates superior performance and generalization on mortality, readmission and length of stay tasks using the publicly available MIMIC-III ICU dataset. Code avaialble at https://github.com/sajaddarabi/TAPER-EHR