Learning Representations of Missing Data for Predicting Patient Outcomes

Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches. Patients are often missing data relative to each other; the data comes in a variety of modalities, such as multivariate time series, free text, and categorical demographic information; important relationships among patients can be difficult to detect; and many others. In this work, we propose a novel approach to address these first three challenges using a representation learning scheme based on message passing. We show that our proposed approach is competitive with or outperforms the state of the art for predicting in-hospital mortality (binary classification), the length of hospital visits (regression) and the discharge destination (multiclass classification).

[1]  Aram Galstyan,et al.  Multitask learning and benchmarking with clinical time series data , 2017, Scientific Data.

[2]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[3]  Quoc V. Le,et al.  Unsupervised Pretraining for Sequence to Sequence Learning , 2016, EMNLP.

[4]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[5]  Peter Szolovits,et al.  The Use of Autoencoders for Discovering Patient Phenotypes , 2017, ArXiv.

[6]  David Sontag,et al.  Learning Low-Dimensional Representations of Medical Concepts , 2016, CRI.

[7]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[8]  Jimeng Sun,et al.  Using recurrent neural network models for early detection of heart failure onset , 2016, J. Am. Medical Informatics Assoc..

[9]  Sandra G Brauer,et al.  Prediction of discharge destination after stroke using the motor assessment scale on admission: a prospective, multisite study. , 2008, Archives of physical medicine and rehabilitation.

[10]  G. Moody,et al.  Predicting in-hospital mortality of ICU patients: The PhysioNet/Computing in cardiology challenge 2012 , 2012, 2012 Computing in Cardiology.

[11]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[12]  Constantine Frangakis,et al.  Multiple imputation by chained equations: what is it and how does it work? , 2011, International journal of methods in psychiatric research.

[13]  Jeffrey Dean,et al.  Scalable and accurate deep learning with electronic health records , 2018, npj Digital Medicine.

[14]  Mathias Niepert,et al.  Learning Graph Representations with Embedding Propagation , 2017, NIPS.

[15]  Sean L. Barnes,et al.  Real-time prediction of inpatient length of stay for discharge prioritization , 2016, J. Am. Medical Informatics Assoc..

[16]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

[17]  Jimeng Sun,et al.  RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism , 2016, NIPS.

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

[19]  Walter F. Stewart,et al.  Doctor AI: Predicting Clinical Events via Recurrent Neural Networks , 2015, MLHC.

[20]  David C. Kale,et al.  Modeling Missing Data in Clinical Time Series with RNNs , 2016 .

[21]  Richard Walker,et al.  PD Disease State Assessment in Naturalistic Environments Using Deep Learning , 2015, AAAI.

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

[23]  Jun S. Kim,et al.  Predictors for Patient Discharge Destination After Elective Anterior Cervical Discectomy and Fusion , 2017, Spine.

[24]  T. Lasko,et al.  Computational Phenotype Discovery Using Unsupervised Feature Learning over Noisy, Sparse, and Irregular Clinical Data , 2013, PloS one.

[25]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[26]  G.B. Moody,et al.  Similarity-based searching in multi-parameter time series databases , 2008, 2008 Computers in Cardiology.

[27]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[28]  Benjamin M. Marlin,et al.  Unsupervised pattern discovery in electronic health care data using probabilistic clustering models , 2012, IHI '12.

[29]  S. Bagg,et al.  The Berg balance scale as a predictor of length of stay and discharge destination in an acute stroke rehabilitation setting. , 1999, Archives of physical medicine and rehabilitation.

[30]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[31]  Yan Liu,et al.  Deep Computational Phenotyping , 2015, KDD.