Learning Deep Representations from Clinical Data for Chronic Kidney Disease

TL;DR

This paper improves the learning of patient representations from irregular clinical data using a modified T-LSTM autoencoder, enabling better trend capture and anomaly detection in Chronic Kidney Disease analysis.

Contribution

It identifies a key issue in current T-LSTM models and proposes a solution that significantly enhances the quality of learned patient representations.

Findings

Enhanced latent representations capture long-term trends.

Improved model handles noise effectively.

Enables detection of unusual patient profiles.

Abstract

We study the behavior of a Time-Aware Long Short-Term Memory Autoencoder, a state-of-the-art method, in the context of learning latent representations from irregularly sampled patient data. We identify a key issue in the way such recurrent neural network models are being currently used and show that the solution of the issue leads to significant improvements in the learnt representations on both synthetic and real datasets. A detailed analysis of the improved methodology for representing patients suffering from Chronic Kidney Disease (CKD) using clinical data is provided. Experimental results show that the proposed T-LSTM model is able to capture the long-term trends in the data, while effectively handling the noise in the signal. Finally, we show that by using the latent representations of the CKD patients obtained from the T-LSTM autoencoder, one can identify unusual patient profiles from the target population.