TaGiTeD: Predictive Task Guided Tensor Decomposition for Representation Learning from Electronic Health Records

With the better availability of healthcare data, such as Electronic Health Records (EHR), more and more data analytics methodologies are developed aiming at digging insights from them to improve the quality of care delivery. There are many challenges on analyzing EHR, such as high dimensionality and event sparsity. Moreover, different from other application domains, the EHR analysis algorithms need to be highly interpretable to make them clinically useful. This makes representation learning from EHRs of key importance. In this paper, we propose an algorithm called Predictive Task Guided Tensor Decomposition (TaGiTeD), to analyze EHRs. Specifically, TaGiTeD learns event interaction patterns that are highly predictive for certain tasks from EHRs with supervised tensor decomposition. Compared with unsupervised methods, TaGiTeD can learn effective EHR representations in a more focused way. This is crucial because most of the medical problems have very limited patient samples, which are not enough for unsupervised algorithms to learn meaningful representations form. We apply TaGiTeD on real world EHR data warehouse and demonstrate that TaGiTeD can learn representations that are both interpretable and predictive.

[1]  Tamara G. Kolda,et al.  Numerical optimization for symmetric tensor decomposition , 2014, Mathematical Programming.

[2]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[3]  Sam T. Roweis,et al.  EM Algorithms for PCA and Sensible PCA , 1997, NIPS 1997.

[4]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

[5]  Yoshua Bengio,et al.  Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery , 2012, ArXiv.

[6]  B. Recht,et al.  Tensor completion and low-n-rank tensor recovery via convex optimization , 2011 .

[7]  Jimeng Sun,et al.  Rubik: Knowledge Guided Tensor Factorization and Completion for Health Data Analytics , 2015, KDD.

[8]  Max Welling,et al.  Positive tensor factorization , 2001, Pattern Recognit. Lett..

[9]  Tamara G. Kolda,et al.  On Tensors, Sparsity, and Nonnegative Factorizations , 2011, SIAM J. Matrix Anal. Appl..

[10]  Aditya Bhaskara,et al.  Smoothed analysis of tensor decompositions , 2013, STOC.

[11]  A. Cichocki,et al.  Tensor decompositions for feature extraction and classification of high dimensional datasets , 2010 .

[12]  Jianying Hu,et al.  A Graph Based Methodology for Temporal Signature Identification from HER. , 2015, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[13]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  T. Kolda.  Multilinear operators for higher-order decompositions , 2006 .

[15]  Pascal Vincent,et al.  Contractive Auto-Encoders: Explicit Invariance During Feature Extraction , 2011, ICML.

[16]  Jimeng Sun,et al.  Marble: high-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization , 2014, KDD.

[17]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[18]  Andrew Y. Ng,et al.  The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization , 2011, ICML.

[19]  Yoshua Bengio,et al.  Neural net language models , 2008, Scholarpedia.