Mapping Patient Trajectories using Longitudinal Extraction and Deep Learning in the MIMIC-III Critical Care Database

Electronic Health Records (EHRs) contain a wealth of patient data useful to biomedical researchers. At present, both the extraction of data and methods for analyses are frequently designed to work with a single snapshot of a patient’s record. Health care providers often perform and record actions in small batches over time. By extracting these care events, a sequence can be formed providing a trajectory for a patient’s interactions with the health care system. These care events also offer a basic heuristic for the level of attention a patient receives from health care providers. We show that is possible to learn meaningful embeddings from these care events using two deep learning techniques, unsupervised autoencoders and long short-term memory networks. We compare these methods to traditional machine learning methods which require a point in time snapshot to be extracted from an EHR.

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

[2]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[3]  Geoffrey E. Hinton,et al.  Generating Text with Recurrent Neural Networks , 2011, ICML.

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

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Ewa Dudek-Dyduch.  Algebraic Logical Meta-Model of Decision Processes - New Metaheuristics , 2015, ICAISC.

[7]  Jason H. Moore,et al.  Spatially Uniform ReliefF (SURF) for computationally-efficient filtering of gene-gene interactions , 2009, BioData Mining.

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

[9]  David C. Kale,et al.  Phenotyping of Clinical Time Series with LSTM Recurrent Neural Networks , 2015, ArXiv.

[10]  et al.,et al.  Missing Data Imputation in the Electronic Health Record Using Deeply Learned Autoencoders , 2017, PSB.

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

[12]  J. Henry,et al.  Adoption of Electronic Health Record Systems among U . S . Non-Federal Acute Care Hospitals : 2008-2015 , 2013 .

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

[14]  Brett K. Beaulieu-Jones,et al.  Reproducibility of computational workflows is automated using continuous analysis , 2017, Nature Biotechnology.

[15]  Li Li,et al.  Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records , 2016, Scientific Reports.

[16]  Marko Robnik-Sikonja,et al.  Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF , 2004, Applied Intelligence.

[17]  Krzysztof Boryczko,et al.  Parallel Approach for Visual Clustering of Protein Databases , 2012 .

[18]  Tudor I. Oprea,et al.  Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients , 2014, Nature Communications.

[19]  Koray Kavukcuoglu,et al.  Visual Attention , 2020, Computational Models for Cognitive Vision.

[20]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[21]  Casey S. Greene,et al.  Unsupervised Feature Construction and Knowledge Extraction from Genome-Wide Assays of Breast Cancer with Denoising Autoencoders , 2014, Pacific Symposium on Biocomputing.

[22]  Casey S. Greene,et al.  Semi-supervised learning of the electronic health record for phenotype stratification , 2016, J. Biomed. Informatics.