TY - GEN
T1 - Predicting 30-day risk and cost of "all-cause" hospital readmissions
AU - Sushmita, Shanu
AU - Khulbe, Garima
AU - Hasan, Aftab
AU - Newman, Stacey
AU - Ravindra, Padmashree
AU - Roy, Senjuti Basu
AU - Cock, Martine De
AU - Teredesai, Ankur
N1 - Publisher Copyright:
Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org).
PY - 2016
Y1 - 2016
N2 - The hospital readmission rate of patients within 30 days after discharge is broadly accepted as a healthcare quality measure and cost driver in the United States. The ability to estimate hospitalization costs alongside 30 day risk-stratification for such readmissions provides additional benefit for accountable care, now a global issue and foundation for the U.S. government mandate under the Affordable Care Act. Recent data mining efforts either predict healthcare costs or risk of hospital readmission, but not both. In this paper we present a dual predictive modeling effort that utilizes healthcare data to predict the risk and cost of any hospital readmission ("all-cause"). For this purpose, we explore machine learning algorithms to do accurate predictions of healthcare costs and risk of 30-day readmission. Results on risk prediction for "all-cause" readmission compared to the standardized readmission tool (LACE) are promising, and the proposed techniques for cost prediction consistently outperform baseline models and demonstrate substantially lower mean absolute error (MAE).
AB - The hospital readmission rate of patients within 30 days after discharge is broadly accepted as a healthcare quality measure and cost driver in the United States. The ability to estimate hospitalization costs alongside 30 day risk-stratification for such readmissions provides additional benefit for accountable care, now a global issue and foundation for the U.S. government mandate under the Affordable Care Act. Recent data mining efforts either predict healthcare costs or risk of hospital readmission, but not both. In this paper we present a dual predictive modeling effort that utilizes healthcare data to predict the risk and cost of any hospital readmission ("all-cause"). For this purpose, we explore machine learning algorithms to do accurate predictions of healthcare costs and risk of 30-day readmission. Results on risk prediction for "all-cause" readmission compared to the standardized readmission tool (LACE) are promising, and the proposed techniques for cost prediction consistently outperform baseline models and demonstrate substantially lower mean absolute error (MAE).
UR - http://www.scopus.com/inward/record.url?scp=85009791273&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85009791273&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85009791273
T3 - AAAI Workshop - Technical Report
SP - 453
EP - 461
BT - WS-16-01
PB - AI Access Foundation
T2 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
Y2 - 12 February 2016 through 17 February 2016
ER -