# Compensating trajectory bias for unsupervised patient stratification using adversarial recurrent neural networks

arXiv: https://arxiv.org/abs/2112.07239 · HTML: https://mlsanity.com/paper/2112.07239/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 8 of 8)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Multi-layer Representation Learning for Medical Concepts](https://mlsanity.com/paper/1602.05568/) (2016)
- [Meta-Learning Update Rules for Unsupervised Representation Learning](https://mlsanity.com/paper/1804.00222/) (2018)
- [Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record](https://mlsanity.com/paper/1810.04793/) (2018)
- [Temporal Phenotyping using Deep Predictive Clustering of Disease Progression](https://mlsanity.com/paper/2006.08600/) (2020)
- [TASTE: Temporal and Static Tensor Factorization for Phenotyping Electronic Health Records](https://mlsanity.com/paper/1911.05843/) (2019)
- [Medical Concept Representation Learning from Electronic Health Records and its Application on Heart Failure Prediction](https://mlsanity.com/paper/1602.03686/) (2016)
- [Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series](https://mlsanity.com/paper/1811.12050/) (2018)

## Built on by (most cited first, 1 of 1)

- [Enabling scalable clinical interpretation of ML-based phenotypes using real world data](https://mlsanity.com/paper/2208.01607/) (2022)

## Abstract (arXiv)

Electronic healthcare records are an important source of information which can be used in patient stratification to discover novel disease phenotypes. However, they can be challenging to work with as data is often sparse and irregularly sampled. One approach to solve these limitations is learning dense embeddings that represent individual patient trajectories using a recurrent neural network autoencoder (RNN-AE). This process can be susceptible to unwanted data biases. We show that patient embeddings and clusters using previously proposed RNN-AE models might be impacted by a trajectory bias, meaning that results are dominated by the amount of data contained in each patients trajectory, instead of clinically relevant details. We investigate this bias on 2 datasets (from different hospitals) and 2 disease areas as well as using different parts of the patient trajectory. Our results using 2 previously published baseline methods indicate a particularly strong bias in case of an event-to-end trajectory. We present a method that can overcome this issue using an adversarial training scheme on top of a RNN-AE. Our results show that our approach can reduce the trajectory bias in all cases.