Latent topic ensemble learning for hospital readmission cost optimization
Christopher Baechle,
C. Derrick Huang,
Ankur Agarwal,
Ravi S. Behara and
Jahyun Goo
European Journal of Operational Research, 2020, vol. 281, issue 3, 517-531
Abstract:
Unplanned hospital readmission is a costly problem in the United States, and in 2013 the U.S. federal government began to reduce payments to hospitals with preventable patient readmissions. Predictive modeling using machine learning and data analytics can be a useful decision support tool to help identify patients most likely to be readmitted. However, current systems have several shortcomings, such as difficulties in utilizing unstructured data and combining data from multiple hospitals. In this paper, we propose Latent Topic Ensemble Learning, which uses an ensemble of topic specific models to leverage data from multiple hospitals, as key data analytic algorithm for predicting hospital readmission. Models are built and evaluated incorporating federal financial penalties and tested using dataset containing data collected from 16 regional hospitals. It is found that LTEL significantly outperforms the best performing baseline method for readmission cost optimization.
Keywords: Analytics; Ensemble learning; Predictive analysis; Hospital readmission; Natural language processing (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0377221719304102
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:ejores:v:281:y:2020:i:3:p:517-531
DOI: 10.1016/j.ejor.2019.05.008
Access Statistics for this article
European Journal of Operational Research is currently edited by Roman Slowinski, Jesus Artalejo, Jean-Charles. Billaut, Robert Dyson and Lorenzo Peccati
More articles in European Journal of Operational Research from Elsevier
Bibliographic data for series maintained by Catherine Liu ().