Abstract
Multiple cause-of-death data provides a valuable source of information that can be used to enhance health standards by predicting health related trajectories in societies with large populations. These data are often available in large quantities across U.S. states and require Big Data techniques to uncover complex hidden patterns. We design two different classes of models suitable for large-scale analysis of mortality data, a Hadoop-based ensemble of random forests trained over N-grams, and the DeepDeath, a deep classifier based on the recurrent neural network (RNN). We apply both classes to the mortality data provided by the National Center for Health Statistics and show that while both perform significantly better than the random classifier, the deep model that utilizes long short-term memory networks (LSTMs), surpasses the N-gram based models and is capable of learning the temporal aspect of the data without a need for building ad-hoc, expert-driven features.
Footnotes
H. R. Hassanzadeh is with the Department of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA. (email: hassanzadeh{at}gatech.edu).
Y. Sha is with the Department of Biology, Georgia Institute of Technology, Atlanta, GA 30332 USA. (email: ysha8{at}gatech.edu)
M. D. Wang is with the Department of Biomedical Engineering, Georgia Institute of Technology and Emory University and the School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA (corresponding author, phone: 404-385-2954; e-mail: maywang{at}bme.gatech.edu).
* This work was supported in part by grants from the US Department of Health and Human Services (HHS) Centers for Disease Control and Prevention (CDC) HHSD2002015F62550B, National Science Foundation Award NSF1651, and Microsoft Research and Hewlett Packard. This article does not reflect the official policy or opinions of the CDC, NSF, or the US Department of HHS and does not constitute an endorsement of the individuals or their programs.