Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes
Machine Learning
2017-01-09 v2 Machine Learning
Abstract
We propose using canonical correlation analysis (CCA) to generate features from sequences of medical billing codes. Applying this novel use of CCA to a database of medical billing codes for patients with diverticulitis, we first demonstrate that the CCA embeddings capture meaningful relationships among the codes. We then generate features from these embeddings and establish their usefulness in predicting future elective surgery for diverticulitis, an important marker in efforts for reducing costs in healthcare.
Cite
@article{arxiv.1612.00516,
title = {Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes},
author = {Corinne L. Jones and Sham M. Kakade and Lucas W. Thornblade and David R. Flum and Abraham D. Flaxman},
journal= {arXiv preprint arXiv:1612.00516},
year = {2017}
}
Comments
Accepted at NIPS 2016 Workshop on Machine Learning for Health