Paper Info
Title
Patient flow prediction via discriminative learning of mutually-correcting processes (extended abstract)
Abstract
We focus on an important problem of predicting the so-called “patient flow” from longitudinal electronic health records (EHRs), which has not been explored via existing machine learning techniques. We develop a point process based framework for modeling patient flow through various care units (CUs) and jointly predicting patients' destination CUs and duration days. We propose a novel discriminative learning algorithm aiming at improving the prediction of transition events in the case of sparse data. By parameterizing the proposed model as mutually-correcting processes, we formulate the estimation problem via generalized linear models and solve it based on alternating direction method of multipliers (ADMM). We achieve simultaneous feature selection and learning by adding a group-lasso regularizer to the ADMM algorithm. Additionally, we synthesize auxiliary training data for the classes with extremely few samples, and improve the robustness of our learning method to the problem of data imbalance.
Year
DOI
Venue
2017
10.1109/ICDE.2017.25
2017 IEEE 33rd International Conference on Data Engineering (ICDE)
Keywords
Field
DocType
patient flow prediction,discriminative learning,mutually-correcting processes,longitudinal electronic health records,EHRs,point process based framework,care units,CUs,generalized linear models,alternating direction method of multipliers,ADMM,feature selection,group-lasso regularizer,data imbalance
Training set,Data mining,Feature selection,Patient flow,Computer science,Point process,Robustness (computer science),Generalized linear model,Artificial intelligence,Sparse matrix,Machine learning,Discriminative learning
Conference
ISSN
ISBN
Citations 
1084-4627
978-1-5090-6544-8
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Hongteng Xu128227.10
Weichang Wu242.45
Shamim Nemati37117.97
Hongyuan Zha46703422.09