Optimizing Autoencoders for Learning Deep Representations From Health Data.

Abstract

Analyzing patients' health data using machine learning techniques can improve both patient outcomes and hospital operations. However, heterogeneous patient data (e.g., vital signs) and inefficient feature learning methods affect the implementation of machine learning-based patient data analysis. In this paper, we present a novel unsupervised deep learning-based feature learning (DFL) framework to automatically learn compact representations from patient health data for efficient clinical decision making. Real-world pneumonia patient data from the National University Hospital in Singapore are collected and analyzed to evaluate the performance of DFL. Furthermore, publicly available electroencephalogram data are extracted from the UCI Machine Learning Repository to test and support our findings. Using both data sets, we compare the performance of DFL to that of several popular feature learning methods and demonstrate its advantages.