# Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge

arXiv: https://arxiv.org/abs/2104.04377 · HTML: https://mlsanity.com/paper/2104.04377/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Multi-layer Representation Learning for Medical Concepts](https://mlsanity.com/paper/1602.05568/) (2016)
- [Neural networks versus Logistic regression for 30 days all-cause readmission prediction](https://mlsanity.com/paper/1812.09549/) (2018)

## Built on by (most cited first, 2 of 2)

- [Disease Progression Modeling Workbench 360](https://mlsanity.com/paper/2106.13265/) (2021)
- [Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Database](https://mlsanity.com/paper/2207.02445/) (2022)

## Abstract (arXiv)

Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance claims data, such as readmission at 30 days, mainly due to data sparsity issue. Consequently, classical machine learning methods, especially those that embed domain knowledge in handcrafted features, are often on par with, and sometimes outperform, deep learning approaches. In this paper, we illustrate how the potential of deep learning can be achieved by blending domain knowledge within deep learning architectures to predict adverse events at hospital discharge, including readmissions. More specifically, we introduce a learning architecture that fuses a representation of patient data computed by a self-attention based recurrent neural network, with clinically relevant features. We conduct extensive experiments on a large claims dataset and show that the blended method outperforms the standard machine learning approaches.