Abstract
Inpatient hospital readmissions for potentially avoidable conditions are problematic and costly. In this paper, we build machine learning models using variables widely available in health claims data to predict patients' 30-day readmission risks at the time of discharge. These models show high predictive power on a U.S. nationwide readmission database. They are also capable of providing interpretable risk factors globally at the population level and locally associated with each single discharge. In addition, we propose a model-agnostic approach to provide confidence for each prediction. Altogether, using models with high predictive power, interpretable risk factors and prediction confidence may enable health care systems to accurately target high-risk patients and prevent recurrent readmissions by accurately anticipating the probability of readmission at the point of care.
Original language | English |
---|---|
Title of host publication | 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services, Healthcom 2016 |
ISBN (Electronic) | 9781509033706 |
DOIs | |
State | Published - Nov 18 2016 |
Event | 18th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2016 - Munich, Germany Duration: Sep 14 2016 → Sep 17 2016 |
Publication series
Name | 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services, Healthcom 2016 |
---|
Conference
Conference | 18th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2016 |
---|---|
Country/Territory | Germany |
City | Munich |
Period | 9/14/16 → 9/17/16 |
Bibliographical note
Publisher Copyright:© 2016 IEEE.
ASJC Scopus subject areas
- Computer Science Applications
- Computer Networks and Communications
- Health(social science)
- Health Informatics