Learning Deep Representations from Clinical Data for Chronic Kidney Disease

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.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[3]  Hongfang Liu,et al.  Modeling asynchronous event sequences with RNNs , 2018, J. Biomed. Informatics.

[4]  Kebin Jia,et al.  Wave2Vec: Deep representation learning for clinical temporal data , 2019, Neurocomputing.

[5]  Duc Thanh Anh Luong,et al.  Extracting Deep Phenotypes for Chronic Kidney Disease Using Electronic Health Records , 2017, EGEMS.

[6]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[7]  Duc Thanh Anh Luong,et al.  A K-Means Approach to Clustering Disease Progressions , 2017, 2017 IEEE International Conference on Healthcare Informatics (ICHI).

[8]  Raman Arora,et al.  Disease Trajectory Maps , 2016, NIPS.

[9]  Lisa M. Schilling,et al.  The DARTNet Institute: Seeking a Sustainable Support Mechanism for Electronic Data Enabled Research Networks , 2014, EGEMS.

[10]  Bernadette A. Thomas,et al.  Global, regional, and national age–sex specific all-cause and cause-specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[11]  Prerna Singh,et al.  Automatic Extraction of Deep Phenotypes for Precision Medicine in Chronic Kidney Disease , 2017, DH.

[12]  Jimeng Sun,et al.  Multi-layer Representation Learning for Medical Concepts , 2016, KDD.

[13]  Bernadette A. Thomas,et al.  Global, regional, and national age–sex specific all-cause and cause-specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[14]  Fei Wang,et al.  Patient Subtyping via Time-Aware LSTM Networks , 2017, KDD.

[15]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[16]  Yan Liu,et al.  Recurrent Neural Networks for Multivariate Time Series with Missing Values , 2016, Scientific Reports.